多角度目标立体信息优化获取及识别技术
|
摘要
随着空间遥感对地观测技术的发展，不仅能够获取包括雷达信号、光学图像等传统类型的目标信息，更使得获取蕴含着表面光学特性和三维空间结构属性的目标立体信息成为可能。遥感立体信息颠覆了传统遥感信息的观念，在保留了目标表面材质与环境因素综合反映出的光学特性信息基础上，更强调目标在三维空间的存在感，更真实的反映目标的本质属性，这是一种从之前仅仅视觉可见到如今已经触手可及的变革。充分地获取和分析目标遥感立体信息，能够从根本上解决传统遥感信息由于对目标描述能力不足而导致的诸多应用难题。深入挖掘目标立体信息的应用潜力，将能大幅提升包括城市规划、地理勘探、防震减灾以及军事侦察等领域的执行效力，对国民经济发展和国防建设有着极为重大的意义。因而，研究并建立一套完整的遥感立体信息处理理论体系迫在眉睫，而目标立体信息的优化获取、立体特征提取和目标识别三项技术分别对应着立体信息的获取、分析和应用过程，是该体系中实现立体信息应用价值的关键环节。不同于一般的遥感地物分类，目标识别更强调相似目标之间的精细区分，因而对目标特征的描述能力和分类器性能的要求更高。而针对立体信息的优化获取和特征提取决定着对目标的描述能力，分类器的优化是改善其性能，提高目标识别率的关键。可见，解决相应技术难题将为完善遥感立体信息处理理论体系做出不可磨灭的贡献。
首先，目标遥感立体信息可分为表面三维结构信息和表面光学信息两部分。针对目标遥感立体信息的表面光学信息部分获取的充分性(完整且高质量)问题，本文提出了一种多角度立体信息优化获取方法。该方法的出发点是利用多个观测角度观测，针对观测点数量和各观测点的观测角度两方面进行优化，以减少由于观测角度不足或不当而造成的立体信息损失。而针对该优化问题难以构建目标函数的问题，提出了多角度目标立体信息获取充分性评估模型。该模型能够有效描述在不同的多角度观测方式下，目标立体信息获取的充分性情况。进而，采用人工蜂群算法求解该多变量优化问题。实验表明，本文方法能够针对不同类型的目标，获得高效的多角度观测方案，即确定能够充分获取目标立体信息的观测点数和各点的观测角度。经验证，在优化后的观测方案下获取目标立体信息的充分性显著提高。
其次，在目标立体信息充分获取的基础上，目标立体特征提取技术是从所获取立体信息中挖掘能够有效表征目标关键属性的描述量，是提高目标识别率等应用的关键。针对传统特征对目标描述能力不足问题，提出了囊括目标光学特征和三维特征的目标遥感立体特征。重点针对传统遥感三维特征提取技术无法充分描述目标三维结构的问题，基于球谐函数理论，提出了面向目标遥感三维结构信息的球谐描述子特征提取方法，并进一步提出遥感三维结构信息的3D-Zernike描述子特征提取方法，解决球谐描述子在应用中存在分解球面半径难以选择、数据量大、误差敏感等问题。球谐描述子与3D-Zernike描述子能够充分描述目标三维特征，有利于描述不同三维结构的差异性；且具有三维空间旋转不变性，有利于描述不同坐标系或不同朝向的相同目标的一致性。通过实验比较分析了本文三维特征提取技术的优越性。此外，分析验证了目标表面光学特征对三维特征的重要补充作用，证明了立体特征能够有效增大目标之间的类内相似度和类间差异度，通过立体特征为高相似度之间的目标识别提供了更可靠的线索。
最后，目标识别技术是根据所提取的特征对目标类别进行准确判别的过程。针对基于传统特征难以解决的高相似度目标识别的问题，本文一方面提出基于高性能立体特征的目标识别方法，以提高高相似度目标识别时的识别率；另一方面，提出基于人工蜂群算法的分类器优化方法，解决基于低性能的立体特征进行识别时，常规的分类器参数设置难以保证识别率的问题，该方法通过优化支持向量机的参数向量，调整广义最优分类面的位置，实现分类器性能的提高。进一步地，提出一种基于动态蜂群算法的支持向量机参数优化方法。该方法在面对多类目标识别时，能够有效改善由于待优化参数向量维数较大，导致的优化收敛慢和求解质量差的问题。通过实验验证了本文提出的分类器优化方法能够改善分类器性能。尤其是对于多类目标识别问题，相比于传统群智能优化算法，本文方法大幅提高了参数优化效率，有效的改善了分类器性能，从而为提高目标识别率提供了可靠保证。
值得注意的是，本文研究突破传统遥感信息处理中以场景为对象的思路，而是完全针对目标个体，不但顺应了遥感信息的精细化、立体化的发展趋势，更为未来遥感立体信息处理理论体系的发展提供了依据。
With the development of remote sensing earth-observation technology, not onlytraditional types of object information could be acquired such as radar signals,optical image and etc, but also makes it possible to obtain stereo information whichcontains optical characteristics and three-dimensional structural properties of object.Remote sensing stereo information subvert the traditional concept of remote sensinginformation, while retaining optical properties comprehensive reflected by ofsurface material and environmental, more emphasis on sense of presence in athree-dimensional of the object,which more truely reflects the nature property of theobject. It changes from just in sight before to now at your fingertips. Fulllyacquisition and analysis of remote sensing stereo information of the object, canfundamentally solve many application problems which traditional remote sensinginformation could not do owing to lack of describing ability. Digging the potentialapplications of stereo information will greatly enhance effectiveness ofimplementation for many fields, including urban planning, geographic exploration,earthquake disaster reduction, as well as military reconnaissance. They all havemajor significance for the development of national economy and national defense.Thus, it is a urgent mission to establish a complete theoretical system for remotesensing stereo information processing. Optimization of stereo informationacquisition, stereo feature extraction and object recognition are three keytechnologies of the theoretical system, which corresponding to processes ofacquisition, analysis and application of stereo information, respectively. Differentfrom remote sensing classification, object recognition more emphasis on the finedistinction between the similar objects. Therefore, feature with higher describeability and better performance of classifier are needed. Techniques of optimizationacquisition and feature extraction are for increasing the ability to describe the object,and optimization of classifier is to improve its performance for object recognition.Obviously, it will make an indelible contribution for improving the theoreticalsystem of stereo remote sensing information processing, if above problems aresolved.
First of all, remote sensing stereo information of object could be divided intotwo parts which are three-dimensional structure and optical information of thesurface. For full acquisition of surface optical information part (the word ‘full’means complete and high quality), a multi-angle based optimized stereo informationacquisition method is proposed. The method solves the planning optimizing problemfor multi-angle observing, which including optimizing work for number of observing points and observing angles of each observation point. In this way,efficient multi-angle based information acquiring program could be obtained, whichcould decrease the loss of information caused by bad observation angles. Owing tothe objective function for this optimizating problem is difficult to build, adequacyevaluation model for multi-angle based stereo information acquisition (AE-MSIA) isproposed. The model can effectively describe adequacy of stereo informationacquired by different types of multi-angle programs. Furthermore, to solve thismulti-variable optimizing problem, artificial bee colony algorithm is utilized.Experiments show that for different types of objects, efficient multi-angle basedobserving programs could be obtained by method proposed in this paper, and mostefficient observing points and observing angles of each point are got. Proven,adequacy of stereo information could be significantly improved under optimiziedobserving program.
Further, basing on full acquisition of stereo information of object, to improverecognition accuracy, feature extraction technique is to excavate key attributedescription which can effectively characterize the object. For poor performance oftraditional features for target description, stereo feature including opticalcharacteristics and three-dimensional structural features of object is proposed. Andfocusing on the traditional remote sensing three-dimensional feature extractiontechnology can not adequately describe three-dimensional structure of object, basedon the theory of spherical harmonics,‘spherical harmonic descriptors’ is proposedfor remote sensing three-dimensional information based feature extraction.Moreover,‘3D-Zernike descriptors’ based feature extraction method is introduced to solve theapplication proplems of spherical harmonic descriptors, such as radius ofdecomposition sphere is difficult to choose, large volumes of data, noise-sensitiveand etc. Spherical harmonic descriptors and3D-Zernike descriptors couldadequately describe three-dimensional structure of object. They are conducive todescribe the differences between objects with different three-dimensional structures,and they have rotation invariance in three-dimensional space, which is conducive todescribe consistency between same objects in different coordinate systems or withdifferent towards. The superiority the three-dimensional feature extractiontechniques is proved by comparative analysis. In addition, the importantcomplementary role of optical features is verified, which prove that the stereofeatures can effectively increase the degree of difference between different objectsand the degree of similarity between same objects, which provides more reliableclues for high similarity objects recognition.
Finally, remote sensing target recognition technology is to accurately judgecategory of objects based on the extracted features. To solve the poor performanceproblem of traditional features based high similarity recognition, on the one hand object recognition method based on high-performance stereo features to improve therecognition rate of high similarity recognition; On the other hand, a classifieroptimization method is proposed based on artificial bee colony algorithm,whichfocused on when doing recognition with poor stereo features, conventional classifierparameter settings could hardly guarantee recognition accuracy. In this method, byparameter-vector optimization of support vector machine, position of thegeneralized optimal hyper-plane is adjusted, and performance of the classifier couldbe improved. Furthermore, when facing multi-category recognition problem,traditional optimizing algorithm based parameter-optimization of classifier lead tolow efficiency, dynamic artificial bee colony algorithm is proposed for supportvector machine parameter-optimization. This method can effectively improveproblems of slow convergence and solution quality, which are caused by largerdimension of optimized parameter-vector. Experiments show that the proposedmethod could improve performance of classifier. Especially for multi-categoryrecognition problems, compared with traditional heuristic algorithms, the proposedmethod significantly improves the efficiency for parameter-optimization, andeffectively improve performance of classifier, and provides a reliable guarantee foraccuracy of object recognition.
It is worth noting that this study exceed the idea of scene based work in thetraditional remote sensing information processing, and completely target individuals.Not only it conforms refinement and stereo trends of remote sensing information,moreover, it provide a basis for future development of theoretical system for remotesensing stereo information processing.
首先，目标遥感立体信息可分为表面三维结构信息和表面光学信息两部分。针对目标遥感立体信息的表面光学信息部分获取的充分性(完整且高质量)问题，本文提出了一种多角度立体信息优化获取方法。该方法的出发点是利用多个观测角度观测，针对观测点数量和各观测点的观测角度两方面进行优化，以减少由于观测角度不足或不当而造成的立体信息损失。而针对该优化问题难以构建目标函数的问题，提出了多角度目标立体信息获取充分性评估模型。该模型能够有效描述在不同的多角度观测方式下，目标立体信息获取的充分性情况。进而，采用人工蜂群算法求解该多变量优化问题。实验表明，本文方法能够针对不同类型的目标，获得高效的多角度观测方案，即确定能够充分获取目标立体信息的观测点数和各点的观测角度。经验证，在优化后的观测方案下获取目标立体信息的充分性显著提高。
其次，在目标立体信息充分获取的基础上，目标立体特征提取技术是从所获取立体信息中挖掘能够有效表征目标关键属性的描述量，是提高目标识别率等应用的关键。针对传统特征对目标描述能力不足问题，提出了囊括目标光学特征和三维特征的目标遥感立体特征。重点针对传统遥感三维特征提取技术无法充分描述目标三维结构的问题，基于球谐函数理论，提出了面向目标遥感三维结构信息的球谐描述子特征提取方法，并进一步提出遥感三维结构信息的3D-Zernike描述子特征提取方法，解决球谐描述子在应用中存在分解球面半径难以选择、数据量大、误差敏感等问题。球谐描述子与3D-Zernike描述子能够充分描述目标三维特征，有利于描述不同三维结构的差异性；且具有三维空间旋转不变性，有利于描述不同坐标系或不同朝向的相同目标的一致性。通过实验比较分析了本文三维特征提取技术的优越性。此外，分析验证了目标表面光学特征对三维特征的重要补充作用，证明了立体特征能够有效增大目标之间的类内相似度和类间差异度，通过立体特征为高相似度之间的目标识别提供了更可靠的线索。
最后，目标识别技术是根据所提取的特征对目标类别进行准确判别的过程。针对基于传统特征难以解决的高相似度目标识别的问题，本文一方面提出基于高性能立体特征的目标识别方法，以提高高相似度目标识别时的识别率；另一方面，提出基于人工蜂群算法的分类器优化方法，解决基于低性能的立体特征进行识别时，常规的分类器参数设置难以保证识别率的问题，该方法通过优化支持向量机的参数向量，调整广义最优分类面的位置，实现分类器性能的提高。进一步地，提出一种基于动态蜂群算法的支持向量机参数优化方法。该方法在面对多类目标识别时，能够有效改善由于待优化参数向量维数较大，导致的优化收敛慢和求解质量差的问题。通过实验验证了本文提出的分类器优化方法能够改善分类器性能。尤其是对于多类目标识别问题，相比于传统群智能优化算法，本文方法大幅提高了参数优化效率，有效的改善了分类器性能，从而为提高目标识别率提供了可靠保证。
值得注意的是，本文研究突破传统遥感信息处理中以场景为对象的思路，而是完全针对目标个体，不但顺应了遥感信息的精细化、立体化的发展趋势，更为未来遥感立体信息处理理论体系的发展提供了依据。
With the development of remote sensing earth-observation technology, not onlytraditional types of object information could be acquired such as radar signals,optical image and etc, but also makes it possible to obtain stereo information whichcontains optical characteristics and three-dimensional structural properties of object.Remote sensing stereo information subvert the traditional concept of remote sensinginformation, while retaining optical properties comprehensive reflected by ofsurface material and environmental, more emphasis on sense of presence in athree-dimensional of the object,which more truely reflects the nature property of theobject. It changes from just in sight before to now at your fingertips. Fulllyacquisition and analysis of remote sensing stereo information of the object, canfundamentally solve many application problems which traditional remote sensinginformation could not do owing to lack of describing ability. Digging the potentialapplications of stereo information will greatly enhance effectiveness ofimplementation for many fields, including urban planning, geographic exploration,earthquake disaster reduction, as well as military reconnaissance. They all havemajor significance for the development of national economy and national defense.Thus, it is a urgent mission to establish a complete theoretical system for remotesensing stereo information processing. Optimization of stereo informationacquisition, stereo feature extraction and object recognition are three keytechnologies of the theoretical system, which corresponding to processes ofacquisition, analysis and application of stereo information, respectively. Differentfrom remote sensing classification, object recognition more emphasis on the finedistinction between the similar objects. Therefore, feature with higher describeability and better performance of classifier are needed. Techniques of optimizationacquisition and feature extraction are for increasing the ability to describe the object,and optimization of classifier is to improve its performance for object recognition.Obviously, it will make an indelible contribution for improving the theoreticalsystem of stereo remote sensing information processing, if above problems aresolved.
First of all, remote sensing stereo information of object could be divided intotwo parts which are three-dimensional structure and optical information of thesurface. For full acquisition of surface optical information part (the word ‘full’means complete and high quality), a multi-angle based optimized stereo informationacquisition method is proposed. The method solves the planning optimizing problemfor multi-angle observing, which including optimizing work for number of observing points and observing angles of each observation point. In this way,efficient multi-angle based information acquiring program could be obtained, whichcould decrease the loss of information caused by bad observation angles. Owing tothe objective function for this optimizating problem is difficult to build, adequacyevaluation model for multi-angle based stereo information acquisition (AE-MSIA) isproposed. The model can effectively describe adequacy of stereo informationacquired by different types of multi-angle programs. Furthermore, to solve thismulti-variable optimizing problem, artificial bee colony algorithm is utilized.Experiments show that for different types of objects, efficient multi-angle basedobserving programs could be obtained by method proposed in this paper, and mostefficient observing points and observing angles of each point are got. Proven,adequacy of stereo information could be significantly improved under optimiziedobserving program.
Further, basing on full acquisition of stereo information of object, to improverecognition accuracy, feature extraction technique is to excavate key attributedescription which can effectively characterize the object. For poor performance oftraditional features for target description, stereo feature including opticalcharacteristics and three-dimensional structural features of object is proposed. Andfocusing on the traditional remote sensing three-dimensional feature extractiontechnology can not adequately describe three-dimensional structure of object, basedon the theory of spherical harmonics,‘spherical harmonic descriptors’ is proposedfor remote sensing three-dimensional information based feature extraction.Moreover,‘3D-Zernike descriptors’ based feature extraction method is introduced to solve theapplication proplems of spherical harmonic descriptors, such as radius ofdecomposition sphere is difficult to choose, large volumes of data, noise-sensitiveand etc. Spherical harmonic descriptors and3D-Zernike descriptors couldadequately describe three-dimensional structure of object. They are conducive todescribe the differences between objects with different three-dimensional structures,and they have rotation invariance in three-dimensional space, which is conducive todescribe consistency between same objects in different coordinate systems or withdifferent towards. The superiority the three-dimensional feature extractiontechniques is proved by comparative analysis. In addition, the importantcomplementary role of optical features is verified, which prove that the stereofeatures can effectively increase the degree of difference between different objectsand the degree of similarity between same objects, which provides more reliableclues for high similarity objects recognition.
Finally, remote sensing target recognition technology is to accurately judgecategory of objects based on the extracted features. To solve the poor performanceproblem of traditional features based high similarity recognition, on the one hand object recognition method based on high-performance stereo features to improve therecognition rate of high similarity recognition; On the other hand, a classifieroptimization method is proposed based on artificial bee colony algorithm,whichfocused on when doing recognition with poor stereo features, conventional classifierparameter settings could hardly guarantee recognition accuracy. In this method, byparameter-vector optimization of support vector machine, position of thegeneralized optimal hyper-plane is adjusted, and performance of the classifier couldbe improved. Furthermore, when facing multi-category recognition problem,traditional optimizing algorithm based parameter-optimization of classifier lead tolow efficiency, dynamic artificial bee colony algorithm is proposed for supportvector machine parameter-optimization. This method can effectively improveproblems of slow convergence and solution quality, which are caused by largerdimension of optimized parameter-vector. Experiments show that the proposedmethod could improve performance of classifier. Especially for multi-categoryrecognition problems, compared with traditional heuristic algorithms, the proposedmethod significantly improves the efficiency for parameter-optimization, andeffectively improve performance of classifier, and provides a reliable guarantee foraccuracy of object recognition.
It is worth noting that this study exceed the idea of scene based work in thetraditional remote sensing information processing, and completely target individuals.Not only it conforms refinement and stereo trends of remote sensing information,moreover, it provide a basis for future development of theoretical system for remotesensing stereo information processing.
引文
[1] Ulrich M, Hauber E, Herzschuh U, et al. Polygon pattern geomorphometry onSvalbard (Norway) and western Utopia Planitia (Mars) using high-resolutionstereo remote-sensing data [J]. Geomorphology,2011,134(3):197-216.
[2] Pour A B, Hashim M. The application of ASTER remote sensing data toporphyry copper and epithermal gold deposits [J]. Ore Geology Reviews,2012,44:1-9.
[3] Ok A O, Wegner J D, Heipke C, et al. Accurate Reconstruction ofNear-Epipolar Line Segments from Stereo Aerial Images [J].Photogrammetrie-Fernerkundung-Geoinformation,2012,2012(4):345-358.
[4] Van der Meer F D, van der Werff H, van Ruitenbeek F J A, et al. Multi-andhyperspectral geologic remote sensing: A review [J]. International Journal ofApplied Earth Observation and Geoinformation,2012,14(1):112-128.
[5] Ulrich M, Hauber E, Herzschuh U, et al. Polygon pattern geomorphometry onSvalbard (Norway) and western Utopia Planitia (Mars) using high-resolutionstereo remote-sensing data[J]. Geomorphology,2011,134(3):197-216.
[6] Palubinskas G, Reinartz P, Bamler R. Image acquisition geometry analysis forthe fusion of optical and radar remote sensing data[J]. International Journal ofImage and Data Fusion,2010,1(3):271-282.
[7] Esch T, Taubenb ck H, Heldens W, et al. Urban remote sensing—how can earthobservation support the sustainable development of urban environments?[J].REAL CORP,2010:837-847.
[8] Schiewe J, Ehlers M. A novel method for generating3D city models from highresolution and multi‐sensor remote sensing data[J]. International journal ofremote sensing,2005,26(4):683-698.
[9] De Vries S, Hill D F, de Schipper M A, et al. Remote sensing of surf zone wavesusing stereo imaging [J]. Coastal Engineering,2011,58(3):239-250.
[10] Frolking S, Palace M W, Clark D B, et al. Forest disturbance and recovery: Ageneral review in the context of spaceborne remote sensing of impacts onaboveground biomass and canopy structure [J]. Journal of GeophysicalResearch: Biogeosciences (2005–2012),2009,114(G2).
[11] Nichol J E, Shaker A, Wong M S. Application of high-resolution stereo satelliteimages to detailed landslide hazard assessment [J]. Geomorphology,2006,76(1):68-75.
[12] Xu M, Cao C, Zhang H, et al. Change detection of an earthquake-inducedbarrier lake based on remote sensing image classification[J]. InternationalJournal of Remote Sensing,2010,31(13):3521-3534.
[13] Li S, Xu T, Wang G, et al. Information war countermeasures based on nearspace vehicles[C]//Second International Conference on Spatial InformationTechnology. International Society for Optics and Photonics,2007:679533-679533-6.
[14] Wang W Q. Near-Space Remote Sensing: Potential and Challenges [M].Springer,2011.
[15] Vodacek A, Kerekes J P, Hoffman M J. Adaptive Optical Sensing in an ObjectTracking DDDAS[J]. Procedia Computer Science,2012,9:1159-1166.
[16] O'Connell M J, Shugart H H, Okin G S. Measurement and Monitoring ofBarrier Island Forest Sensitivity to Ecohydrological Change Using LIDARRemote Sensing[J]. Journal of Coastal Research,2011.
[17] Xupu G, Chunzhu D, Chao W, et al. SAR modeling and simulation of complexextended scenes[C]//Antennas, Propagation&EM Theory (ISAPE),201210thInternational Symposium on. IEEE,2012:440-443.
[18] Dillon K J, Fainman Y. Computational Lightcurve Imaging[C]//ComputationalOptical Sensing and Imaging. Optical Society of America,2012.
[19] Dasgupta P. A multiagent swarming system for distributed automatic targetrecognition using unmanned aerial vehicles [J]. Systems, Man and Cybernetics,Part A: Systems and Humans, IEEE Transactions on,2008,38(3):549-563.
[20] Fink W, Dohm J M, Tarbell M A, et al. Next-generation robotic planetaryreconnaissance missions: a paradigm shift[J]. Planetary and Space Science,2005,53(14):1419-1426.
[21] Qi J, Huete A R, Moran M S, et al. Interpretation of vegetation indices derivedfrom multi-temporal SPOT images [J]. Remote Sensing of Environment,1993,44(1):89-101.
[22] Su L, Chopping M J, Rango A, et al. Differentiation of semi‐arid vegetationtypes based on multi‐angular observations from MISR and MODIS[J].International Journal of Remote Sensing,2007,28(6):1419-1424.
[23] Benediktsson J A, Pesaresi M, Amason K. Classification and feature extractionfor remote sensing images from urban areas based on morphologicaltransformations [J]. Geoscience and Remote Sensing, IEEE Transactions on,2003,41(9):1940-1949.
[24] Noble W S. What is a support vector machine?[J]. Nature biotechnology,2006,24(12):1565-1567.
[25] Richards J A. Remote sensing digital image analysis: an introduction [M].Springer,2012.
[26] Niethammer U, James M R, Rothmund S, et al. UAV-based remote sensing ofthe Super-Sauze landslide: Evaluation and results[J]. Engineering Geology,2012,128:2-11.
[27] Wang W Q. Near-space vehicles: Supply a gap between satellites and airplanesfor remote sensing [J]. Aerospace and Electronic Systems Magazine, IEEE,2011,26(4):4-9.
[28]常建龙,赵良玉,李克勇.临近空间平台与空天飞机在未来战争中的协同作用[J].飞航导弹,2012,9:81-96.
[29] Mountrakis G, Triantakonstantis D. Inquiry-based learning in remote sensing: Aspace balloon educational experiment [J]. Journal of Geography in HigherEducation,2012,36(3):385-401.
[30] Wang W Q. Near-space vehicle-borne SAR with reflector antenna forhigh-resolution and wide-swath remote sensing [J]. Geoscience and RemoteSensing, IEEE Transactions on,2012,50(2):338-348.
[31] Matsushita T. Camera equipped with red-eye correction feature: U.S. PatentApplication10/942,784[P].2004-9-17.
[32] Innocenti M, Pollini L, Binetti P, et al. The Flight Control System of theHovereye (Trademark) VTOL UAV [J].2007.
[33] Peng Cheng Zhan David W. Casbeer A. Lee Swindlehurst. Adaptive MobileSensor Positioning for Multi-Static Target Tracking. IEEE TRANSACTIONSON AEROSPACE AND ELECTRONIC SYSTEMS VOL.46, NO.1JANUARY2010.pp:120-132
[34] Chen Huiying, Li Youfu. Dynamic view planning by effective particles forthree-dimensional tracking [J]. IEEE Transaction on Systems, Man, andCybernetics—Part B: Cybernetics,2009,39(1), pp:242-253.
[35] X. C. Ding, A. Rahmani, and M. Egerstedt,“Optimal multi-UAV convoyprotection,” presented at the Int. Conf. Robot Commun. Coord.,Odense,Denmark, Apr.2009
[36] Xu Chu (Dennis) Ding, Amir R. Rahmani, and Magnus Egerstedt. Multi-UAVConvoy Protection: An Optimal Approach to Path Planning and Coordination.IEEE TRANSACTIONS ON ROBOTICS, VOL.26, NO.2, APRIL2010.pp:256-268
[37] Y. Yang, A. Minai, and P. Polycarpou,“Decentralized cooperative search inUAVs using opportunistic learning,” in Proc. AIAA Guid., Navigat., ControlConf., Monterey, CA,2002
[38] F. Gaudiano, E. Bonabeau, and B. Shargel,“Evolving behaviors for a swarm ofunmanned air vehicles,” in Proc. IEEE Swarm Intell. Symp., Pasadena, CA,2005, pp.317–324
[39] Laliberte Andrea S, Rango Albert. Texture and scale in object-based analysis ofsubdecimeter resolution unmanned aerial vehicle (UAV) imagery [J]. IEEETransaction on Geoscience and Remote Sensing,2009,47(3), pp:761-770.
[40] Parunak H V D，Purcell M，Connell P0. Digital Pheromones for AutonomousCoordination of Swarming UAVs [A]. The First AIAA Unmanned AerospaceVehicles Systems Technologies and operations Conference [C].2002.AIAA, pp:2002-3446.
[41] Prithviraj Dasgupta. A Multiagent Swarming System for Distributed AutomaticTarget Recognition Using Unmanned Aerial Vehicles. IEEE TRANSACTIONSON SYSTEMS, MAN, AND CYBERNETICS—PART A: SYSTEMS ANDHUMANS, VOL.38, NO.3, MAY2008, pp:549-563
[42]陈岩.蚁群优化理论在无人机战术控制中的应用研究。国防科技大学博士论文。2007年4月,pp:3-13
[43] J. Zhang Y. Wu w. Liu X. Chen. Novel Approach to Position and OrientationEstimation in Vision-Based UAV Navigation. IEEE TRANSACTIONS ONAEROSPACE AND ELECTRONIC SYSTEMS VOL.46, NO.2APRIL2010.pp:687-700
[44] Y. Yang, A. Minai, and P. Polycarpou,“Decentralized cooperative search inUAVs using opportunistic learning,” in Proc. AIAA Guid., Navigat., ControlConf., Monterey, CA,2002
[45] Mukherjee I, Ray P K. A review of optimization techniques in metal cuttingprocesses [J]. Computers&Industrial Engineering,2006,50(1):15-34.
[46] Zitzler E, Thiele L, Zitzler E, et al. An evolutionary algorithm formultiobjective optimization: The strength Pareto approach [M]. ComputerEngineering and Networks Laboratory (TIK), Swiss Federal Institute ofTechnology Zürich (ETH),1998.
[47] Pehlivanoglu Y V. A new vibrational genetic algorithm enhanced with aVoronoi diagram for path planning of autonomous UAV [J]. Aerospace Scienceand Technology,2012,16(1):47-55.
[48] KENNEDY J, EBERHARTR. Particle swarm optimization[C].IEEE Int’t confon Neural Networks. Perth: IEEE,1995, pp:1942-1948
[49] Colorni A，Dorigo M，Maniezzo V. Distributed Optimization by Ant Colonies[A]. Proc lst European Conf Artifieial Life Plans [C]. France:Elsevier，1991,pp:134-142.
[50]欧阳自远,李春来,邹永廖等.嫦娥一号的初步科学成果[J].中国科技成果,2011(9):27-31.
[51] Wolfgang Pitz, David Miler. The TerraSAR-X Satellite. IEEE Transacations ongeoscience and remote sesing, Vol48, NO.2, February2010, pp:615-622.
[52] Perissin D, Wang T. Repeat-pass SAR interferometry with partially coherenttargets[J]. Geoscience and Remote Sensing, IEEE Transactions on,2012,50(1):271-280.
[53] Hu J, Li Z W, Sun Q, et al. Three-Dimensional Surface Displacements FromInSAR and GPS Measurements With Variance Component Estimation [J].Geoscience and Remote Sensing Letters, IEEE,2012,9(4):754-758.
[54] Aguilera E, Nannini M, Reigber A. Multisignal compressed sensing forpolarimetric SAR tomography [J]. Geoscience and Remote Sensing Letters,IEEE,2012,9(5):871-875.
[55] Wan Aziz, W.A., Syahmi, M.Z. and Anuar, A, Terrain Slope Analyses betweenTerrestrial Laser Scanner and Airborne Laser Scanning,2012IEEE Controland System Graduate Research Colloquium, Shah Alam, Selangor, Malaysia,16-17July,2012, pp:242~247
[56] Harding D, Abshire J, Dabney P. The Slope Imaging Multi-polarizationPhoto-counting Lidar: development and performance results[J]. IGARSS,2010,653-656.
[57] Ackemann F. Airborne Laser Scanning-Present Status and FutureExpectations[J]. ISPRS Journal of Photogrammetry and Remote Sensing,1999,54:64-67.
[58] Sima A, Buckley S J, Kurz T H, et al. Semi-automatic Integration of PanoramicHyperspectral Imagery with Photorealistic Lidar Models[J].Photogrammetrie-Fernerkundung-Geoinformation,2012,2012(4):443-454.
[59]张良,马洪超,邬建伟.联合机载LiDAR数据和潮汐数据自动提取潮位线[J].遥感学报,2012,2:015.
[60]黄先锋,王潇,张帆.基于带权点法向量的LiDAR数据屋顶检测方法[J].武汉大学学报:信息科学版,2009,34(1):24-27.
[61] Nixon M, Aguado A S. Feature Extraction&Image Processing for ComputerVision[M]. Academic Press,2012.
[62] B. S rma ek and C. ünsalan,“Urban area and building detection using SIFTkeypoints and graph theory,” IEEE Trans. Geosci. Remote Sens.,vol.47, no.4,Apr.2009, pp:1156-1167
[63] L. M. Fonte, S. Gautama,W. Philips, and W. Goeman,“Evaluating cornerdetectors for the extraction of man made structures in urban areas,” in Proc.IEEE Int. Geosci. Remote Sens. Symp.,2005
[64] D. Ziou, S. Tabbone, Edge detection techniques-an overview, http://citeseer.nj.nec. com/ziou97edge.html,1997
[65] Jon Atli Benediktsson and Kolbeinn Arnason. Classification and FeatureExtraction for Remote Sensing Images From Urban Areas Based onMorphological TransformationsIEEE TRANSACTIONS ON GEOSCIENCEAND REMOTE SENSING, VOL.41, NO.9, SEPTEMBER2003
[66] Caroline Lacoste, Xavier Descombes, and Josiane Zerubia, Point Processes forUnsupervised Line Network Extraction in Remote SensingIEEETRANSACTIONS ON PATTERN ANALYSIS AND MACHINEINTELLIGENCE, VOL.27, NO.10, OCTOBER2005
[67] C. ünsalan,“Gradient magnitude based support regions in structural land useclassification,” IEEE Geosci. Remote Sens. Lett., vol.3, no.4, Oct.2006, pp:546–550
[68] C. ünsalan and K. L. Boyer,“Classifying land development in high resolutionpanchromatic satellite images using straight line statistics,” IEEE Trans.Geosci. Remote Sens., vol.42, no.4, Apr.2004, pp:907–919
[69] X. Xialgang, S. Zhengxing, and P. Binin el. An Online Composite GraphicsRecognition Approach Based on Matching of Spatial Relation Graphs.International Journal on Document Analysis and Recognition,2004,7(1),pp:44~55
[70] Y. Liu, L. Wenyin, and C. Jiang. A structural Approach to RecognizingIncomplete Graphic Objects. Proceedings of the17th International Conferenceon Pattern Recognition, Cambridge, UK,2004,pp:371~375
[71] C. Ah-Soon, K. Tombre. Architectural Symbol Recognition Using a Network ofConstrains. Pattern Recognition Letters.2001,22(2),pp:231~248
[72] B. Yu. Automatic Understanding of Symbol-Connected Diagrams. Proceedingsof the3rd International Conference on Document Analysis and Recognition,Montreal, Canada,1995,pp:803~806
[73] H. Hse, R.R. Newton. Sketched Symbol Recognition Using ZernikeMovements. Proceedings of the17th International Conference on PatternRecognition, Cambridge, UK,2004,pp:367~370
[74] S. Benlonie, J. Malik, and J. Puzicha. Shape Matching and Object RecognitionUsing Shape Contexts. IEEE Transaction on Pattern Analysis and MachineIntelligence.2002,24(4),pp:509~522
[75] P. Dosch and J. Lladós. Vectorial Signatures for Symbol Discrimination.Proceedings of5th International Workshop on Graphics Recognition: RecentAdvances and Perspectives, Springer, German,2003:154~165
[76] T. Peli, An algorithm for recognition and localization of rotated and scaledobjects, Proceedings of the IEEE1981,69, pp:483–485.
[77] A. Taza, C.Y. Suen, Description of planar shapes using shape matrices, IEEETransactions on Systems, Man, and Cybernetics1989,19, pp:1281–1289.
[78] H. Li, B.S. Manjunath, S.K. Mitra, A contour-based approach tomultisensorimage registration, IEEE Transactions on ImageProcessing1995,4:320–334.
[79] J. Flusser, T. Suk, A moment-based approach to registration of images withaffine geometric distortion, IEEE Transactions on Geoscience and RemoteSensing1994,32,pp::382–387.
[80] D. Bhattacharya, S. Sinha, Invariance of stereo images via theory of complexmoments, Pattern Recognition1997,30, pp::1373–1386.
[81] L. Bruzzone and L. Carlin,“A multilevel context-based system forclassification of very high spatial resolution images,” IEEE Trans.Geosci.Remote Sens., vol.44, no.9, pp.2587–2600, Sep.2006.
[82] V. C. Chen, F. Li, S. S. Ho, and H. Wechsler,“Micro-Doppler effect in radar:Phenomenon, model, and simulation study,” IEEE Trans. Aerosp. Electron.Syst., vol.42, no.1, pp.2–21, Jan.2006.
[83] C. J. S. deSilva, G. Lee, and R. Johnson,“All-aspect ship recognition ininfrared images,” in Proc. Electron. Technol. Directions Year2000, May23–25,1995, pp.194–198.
[84] Rulon Mayer and Richard Priest，Object Detection Using TransformedSignatures in Multitemporal Hyperspectral Imagery. IEEE TRANSACTIONSON GEOSCIENCE AND REMOTE SENSING, VOL.40, NO.4, APRIL2002
[85] HSUAN REN, QIAN DU,Automatic Target Recognition for HyperspectralImagery using High-Order Statistics IEEE TRANSACTIONS ONAEROSPACE AND ELECTRONIC SYSTEMS VOL.42, NO.4OCTOBER2006.
[86] C. Corbane, F. Marre, and M. Petit,“Using SPOT-5HRG data in panchromaticmode for operational detection of small ships in tropical area,”Sensors, vol.8,no.5, pp.2959–2973, May2008.
[87] L. De Lathauwer, B. De Moor, and J. Vandewalle,“An introduction toindependent component analysis,” J. Chemom., Multi-Way Anal., vol.14, no.3, pp.123–149, May/Jun.2000.
[88] V. Shah, N. Younan, S. Durbha, and R. King,“Wavelet features for informationmining in remote sensing imagery,” in IEEE Int. Conf. Geosci. Remote Sens.Symp., Jul.2005, vol.8, pp.5630–5633.
[89] Yeom S, Javidi B, Watson E. Photon counting passive3D image sensing forautomatic target recognition[J]. Optics Express,2005,13(23):9310-9330.
[90] P.J. Besl, N.D. McKay, A method for registration of3D shapes, IEEETransactions on Pattern Analysis and Machine Intellinegce1992,14:239–254.
[91] Z. Zhang, Iterative Point Matching for Registration of Free-form Curves andSurfaces, Int. J. Comput. Vision，1994,13:119–152.
[92] Y. Chen, G. Medioni, Object modeling by registration of multiple range images,Image Vision Comput.1992,10:145–155.
[93] V. Ayyagari, F. Boughorbel, A. Koschan, M.. Abidi, A new method forautomatic3D face registration, IEEE CVPR,2005:119-1122.
[94] Allen P K, Troccoli A, Smith B, et al. New methods for digital modeling ofhistoric sites[J]. Computer Graphics and Applications, IEEE,2003,23(6):32-41.
[95] Vanden Wyngaerd J, Van Gool L. Automatic crude patch registration: towardautomatic3D model building[J]. Computer Vision and Image Understanding,2002,87(1):8-26.
[96] S. Yamany, A Farag, Surface Signatures: An Orientation IndependentFree-Form Surface Representation Scheme for the Purpose of ObjectsRegistration and Matching, IEEE PAMI,2002,24(8):1105-1120
[97] A. Flint A. Dick A. van den Hengel. Local3D structure recognition in rangeimages IET Comput. Vis.,2008, Vol.2, No.4, pp.208–217
[98] LOWE D:‘Distinctive image features from scale-invariant keypoints’, Int. J.Comput. Vis,2004,60,(2), pp.91–110
[99] BAY H., TUYTELAARS T., VAN GOOL L.:‘SURF: speeded up robustfeatures’.9-European Conf. Computer Vision, May2006
[100] Hilla Ben-Yaacov, David Malah Recognition of3D Objects Based on ImplicitPolynomials, IEEE Transaction on Pattern Analysis and Machine Intelligence,vol.32, no.5, May2010. pp:954-960.
[101] A. Brennecke and T. Isenberg.3D Shape Matching Using Skeleton Graphs. InProc. Sim. and Vis.,2004:299-310.
[102] H. Sundar et al.Skeleton Based Shape Matching and Retrieval. SMA,2003:130-142.
[103] Frome A, Huber D, Kolluri R, et al. Recognizing objects in range data usingregional point descriptors[J]. Computer Vision-ECCV2004,2004:224-237.
[104] Andrew Zisserman, David Forsyth, Joe Mundy.“3D Object Recognition usingInvariance” Univerity of Oxford Department of Engineering Science19ParksRoad Oxford OXI3PJ U.K Nov.1994.
[105] Florent Lafarge, Xavier Descombes, Josiane Zerubia, Structural Approach forBuilding Reconstruction from a Single DSM, IEEE Transaction on PatternAnalysis and Machine Intelligence, vol.32, no.1, Jan.2010, pp:135~147.
[106] Aparajithan Sampath and Jie Shan, Segmentation and Reconstruction ofPolyhedral Building Roofs From Aerial Lidar Point Clouds, IEEETRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, VOL.48,NO.3, MARCH2010pp:1554~1565
[107] Jain A K, Duin R P W, Mao J. Statistical pattern recognition: A review[J].Pattern Analysis and Machine Intelligence, IEEE Transactions on,2000,22(1):4-37.
[108] Haykin S S, Haykin S S, Haykin S S, et al. Neural networks and learningmachines[M]. Prentice Hall,2009.
[109] Mandic D P, Chambers J. Recurrent neural networks for prediction: Learningalgorithms, architectures and stability [M]. John Wiley&Sons, Inc.,2001.
[110] Michael E. Tipping. Sparse Bayesian Learning and the Relevance VectorMachine. Journal of Machine Learning Research. Vol.12001, pp:211~244.
[111] Gopal S, Woodcock C E, Strahler A H. Fuzzy neural network classification ofglobal land cover from a1AVHRR data set[J]. Remote sensing ofEnvironment,1999,67(2):230-243.
[112] Benz U C, Hofmann P, Willhauck G, et al. Multi-resolution, object-orientedfuzzy analysis of remote sensing data for GIS-ready information[J]. ISPRSJournal of Photogrammetry and Remote Sensing,2004,58(3):239-258.
[113] Du P, Xia J, Zhang W, et al. Multiple classifier system for remote sensingimage classification: a review [J]. Sensors (Basel, Switzerland),2012,12(4):4764.
[114] Foody G M, Boyd D S, Sanchez‐Hernandez C. Mapping a specific class withan ensemble of classifiers[J]. International Journal of Remote Sensing,2007,28(8):1733-1746.
[115] Benediktsson J A, Swain P H. Consensus theoretic classification methods[J].Systems, Man and Cybernetics, IEEE Transactions on,1992,22(4):688-704.
[116] Doan H T X, Foody G M. Increasing soft classification accuracy through theuse of an ensemble of classifiers[J]. International Journal of Remote Sensing,2007,28(20):4609-4623.
[117] Fauvel M, Chanussot J, Benediktsson J A. Decision fusion for theclassification of urban remote sensing images[J]. Geoscience and RemoteSensing, IEEE Transactions on,2006,44(10):2828-2838.
[118] Debeir O, Latinne P, Van Den Steen I. Remote sensing classification ofspectral, spatial and contextual data using multiple classifier systems[J].2001.
[119] Kumar S, Ghosh J, Crawford M M. Hierarchical fusion of multiple classifiersfor hyperspectral data analysis[J]. Pattern Analysis&Applications,2002,5(2):210-220.
[120] Waske B, Benediktsson J A. Fusion of support vector machines forclassification of multisensor data[J]. Geoscience and Remote Sensing, IEEETransactions on,2007,45(12):3858-3866.
[121] Brown G, Wyatt J, Harris R, et al. Diversity creation methods: a survey andcategorisation[J]. Information Fusion,2005,6(1):5-20.
[122] Min S H, Lee J, Han I. Hybrid genetic algorithms and support vector machinesfor bankruptcy prediction[J]. Expert Systems with Applications,2006,31(3):652-660.
[123] Deeb O, Goodarzi M. Exploring QSARs for Inhibitory Activity of Non‐peptide HIV‐1Protease Inhibitors by GA‐PLS and GA‐SVM[J]. Chemicalbiology&drug design,2010,75(5):506-514.
[124] Zhou X, Li Z, Dai Z, et al. QSAR modeling of peptide biological activity bycoupling support vector machine with particle swarm optimization algorithmand genetic algorithm[J]. Journal of Molecular Graphics and Modelling,2010,29(2):188-196.
[125] Zou H Y, Wu H L, Fu H Y, et al. Variable-weighted least-squares supportvector machine for multivariate spectral analysis[J]. Talanta,2010,80(5):1698-1701.
[126] Huang C L, Dun J F. A distributed PSO–SVM hybrid system with featureselection and parameter optimization[J]. Applied Soft Computing,2008,8(4):1381-1391.
[127] Wu Q, Law R. Cauchy mutation based on objective variable of Gaussianparticle swarm optimization for parameters selection of SVM[J]. ExpertSystems with Applications,2011,38(6):6405-6411.
[128] Dervis Karaboga, Bahriye Akay. A comparative study of Artificial BeeColony algorithm[J]. Applied Mathematics and Computation,2009,214:108–132
[129] Mostafa M M R, Schwarz K P. Digital image georeferencing from a multiplecamera system by GPS/INS [J]. ISPRS journal of photogrammetry and remotesensing,2001,56(1):1-12.
[130]成晓倩,赵红强.基于区域生长的LiDAR点云数据滤波[J].国土资源遥感,2008,78(4):6-8.
[131]覃丹.基于多特征组合和SVM的视频内容自动分类算法研究[D].上海交通大学硕士论文,2009.
[132] Cramer M. The DGPF-Test on Digital Airborne Camera Evaluation Overviewand Test Design[J]. Photogrammetrie-Fernerkundung-Geoinformation,2010,2010(2):73-82.
[133] Vapnik V. The nature of statistical learning theory[M]. springer,1999.
[134] Basturk B, Karaboga D. An artificial bee colony (ABC) algorithm for numericfunction optimization[C]//IEEE swarm intelligence symposium.2006:12-14.
[135] Kazhdan M, Funkhouser T, Rusinkiewicz S. Rotation invariant sphericalharmonic representation of3D shape descriptors[C]//Proceedings of the2003Eurographics/ACM SIGGRAPH symposium on Geometry processing.Eurographics Association,2003:156-164.
[136] Morris R J, Najmanovich R J, Kahraman A, et al. Real spherical harmonicexpansion coefficients as3D shape descriptors for protein binding pocket andligand comparisons[J]. Bioinformatics,2005,21(10):2347-2355.
[137] Mak L, Grandison S, Morris R J. An extension of spherical harmonics toregion-based rotationally invariant descriptors for molecular shape descriptionand comparison[J]. Journal of Molecular Graphics and Modelling,2008,26(7):1035-1045.
[138] Canterakis N.3D Zernike moments and Zernike affine invariants for3Dimage analysis and recognition[J].1999.
[139] Novotni M, Klein R.3D Zernike descriptors for content based shaperetrieval[C]//Proceedings of the eighth ACM symposium on Solid modelingand applications. ACM,2003:216-225.
[140] Millán R D, Dempere-Marco L, Pozo J M, et al. Morphologicalcharacterization of intracranial aneurysms using3-D moment invariants[J].Medical Imaging, IEEE Transactions on,2007,26(9):1270-1282.
[141] Venkatraman V, Sael L, Kihara D. Potential for protein surface shape analysisusing spherical harmonics and3D Zernike descriptors[J]. Cell biochemistryand biophysics,2009,54(1):23-32.
[142] Chang C C, Lin C J. LIBSVM: a library for support vector machines[J]. ACMTransactions on Intelligent Systems and Technology (TIST),2011,2(3):27.
[143] Kohavi R. A study of cross-validation and bootstrap for accuracy estimationand model selection[C]//International joint Conference on artificialintelligence. Lawrence Erlbaum Associates Ltd,1995,14:1137-1145.
[144] Keerthi S S, Lin C J. Asymptotic behaviors of support vector machines withGaussian kernel[J]. Neural computation,2003,15(7):1667-1689.
[145] Lee C P, Lin C J. A study on l2-loss (squared hinge-loss) multi-class SVM[R].Technical report, National Taiwan University,2012. UR L http://www. csie.ntu. edu. tw/~cjlin/papers/l2mcsvm/l2mcsvm. pdf.
[146] Hsieh T J, Yeh W C. Knowledge discovery employing grid scheme leastsquares support vector machines based on orthogonal design bee colonyalgorithm[J]. Systems, Man, and Cybernetics, Part B: Cybernetics, IEEETransactions on,2011,41(5):1198-1212.
[147] Karaboga D, Akay B. A modified Artificial Bee Colony (ABC) algorithm forconstrained optimization problems[J]. Applied soft computing,2011,11(3):3021-3031.
[2] Pour A B, Hashim M. The application of ASTER remote sensing data toporphyry copper and epithermal gold deposits [J]. Ore Geology Reviews,2012,44:1-9.
[3] Ok A O, Wegner J D, Heipke C, et al. Accurate Reconstruction ofNear-Epipolar Line Segments from Stereo Aerial Images [J].Photogrammetrie-Fernerkundung-Geoinformation,2012,2012(4):345-358.
[4] Van der Meer F D, van der Werff H, van Ruitenbeek F J A, et al. Multi-andhyperspectral geologic remote sensing: A review [J]. International Journal ofApplied Earth Observation and Geoinformation,2012,14(1):112-128.
[5] Ulrich M, Hauber E, Herzschuh U, et al. Polygon pattern geomorphometry onSvalbard (Norway) and western Utopia Planitia (Mars) using high-resolutionstereo remote-sensing data[J]. Geomorphology,2011,134(3):197-216.
[6] Palubinskas G, Reinartz P, Bamler R. Image acquisition geometry analysis forthe fusion of optical and radar remote sensing data[J]. International Journal ofImage and Data Fusion,2010,1(3):271-282.
[7] Esch T, Taubenb ck H, Heldens W, et al. Urban remote sensing—how can earthobservation support the sustainable development of urban environments?[J].REAL CORP,2010:837-847.
[8] Schiewe J, Ehlers M. A novel method for generating3D city models from highresolution and multi‐sensor remote sensing data[J]. International journal ofremote sensing,2005,26(4):683-698.
[9] De Vries S, Hill D F, de Schipper M A, et al. Remote sensing of surf zone wavesusing stereo imaging [J]. Coastal Engineering,2011,58(3):239-250.
[10] Frolking S, Palace M W, Clark D B, et al. Forest disturbance and recovery: Ageneral review in the context of spaceborne remote sensing of impacts onaboveground biomass and canopy structure [J]. Journal of GeophysicalResearch: Biogeosciences (2005–2012),2009,114(G2).
[11] Nichol J E, Shaker A, Wong M S. Application of high-resolution stereo satelliteimages to detailed landslide hazard assessment [J]. Geomorphology,2006,76(1):68-75.
[12] Xu M, Cao C, Zhang H, et al. Change detection of an earthquake-inducedbarrier lake based on remote sensing image classification[J]. InternationalJournal of Remote Sensing,2010,31(13):3521-3534.
[13] Li S, Xu T, Wang G, et al. Information war countermeasures based on nearspace vehicles[C]//Second International Conference on Spatial InformationTechnology. International Society for Optics and Photonics,2007:679533-679533-6.
[14] Wang W Q. Near-Space Remote Sensing: Potential and Challenges [M].Springer,2011.
[15] Vodacek A, Kerekes J P, Hoffman M J. Adaptive Optical Sensing in an ObjectTracking DDDAS[J]. Procedia Computer Science,2012,9:1159-1166.
[16] O'Connell M J, Shugart H H, Okin G S. Measurement and Monitoring ofBarrier Island Forest Sensitivity to Ecohydrological Change Using LIDARRemote Sensing[J]. Journal of Coastal Research,2011.
[17] Xupu G, Chunzhu D, Chao W, et al. SAR modeling and simulation of complexextended scenes[C]//Antennas, Propagation&EM Theory (ISAPE),201210thInternational Symposium on. IEEE,2012:440-443.
[18] Dillon K J, Fainman Y. Computational Lightcurve Imaging[C]//ComputationalOptical Sensing and Imaging. Optical Society of America,2012.
[19] Dasgupta P. A multiagent swarming system for distributed automatic targetrecognition using unmanned aerial vehicles [J]. Systems, Man and Cybernetics,Part A: Systems and Humans, IEEE Transactions on,2008,38(3):549-563.
[20] Fink W, Dohm J M, Tarbell M A, et al. Next-generation robotic planetaryreconnaissance missions: a paradigm shift[J]. Planetary and Space Science,2005,53(14):1419-1426.
[21] Qi J, Huete A R, Moran M S, et al. Interpretation of vegetation indices derivedfrom multi-temporal SPOT images [J]. Remote Sensing of Environment,1993,44(1):89-101.
[22] Su L, Chopping M J, Rango A, et al. Differentiation of semi‐arid vegetationtypes based on multi‐angular observations from MISR and MODIS[J].International Journal of Remote Sensing,2007,28(6):1419-1424.
[23] Benediktsson J A, Pesaresi M, Amason K. Classification and feature extractionfor remote sensing images from urban areas based on morphologicaltransformations [J]. Geoscience and Remote Sensing, IEEE Transactions on,2003,41(9):1940-1949.
[24] Noble W S. What is a support vector machine?[J]. Nature biotechnology,2006,24(12):1565-1567.
[25] Richards J A. Remote sensing digital image analysis: an introduction [M].Springer,2012.
[26] Niethammer U, James M R, Rothmund S, et al. UAV-based remote sensing ofthe Super-Sauze landslide: Evaluation and results[J]. Engineering Geology,2012,128:2-11.
[27] Wang W Q. Near-space vehicles: Supply a gap between satellites and airplanesfor remote sensing [J]. Aerospace and Electronic Systems Magazine, IEEE,2011,26(4):4-9.
[28]常建龙,赵良玉,李克勇.临近空间平台与空天飞机在未来战争中的协同作用[J].飞航导弹,2012,9:81-96.
[29] Mountrakis G, Triantakonstantis D. Inquiry-based learning in remote sensing: Aspace balloon educational experiment [J]. Journal of Geography in HigherEducation,2012,36(3):385-401.
[30] Wang W Q. Near-space vehicle-borne SAR with reflector antenna forhigh-resolution and wide-swath remote sensing [J]. Geoscience and RemoteSensing, IEEE Transactions on,2012,50(2):338-348.
[31] Matsushita T. Camera equipped with red-eye correction feature: U.S. PatentApplication10/942,784[P].2004-9-17.
[32] Innocenti M, Pollini L, Binetti P, et al. The Flight Control System of theHovereye (Trademark) VTOL UAV [J].2007.
[33] Peng Cheng Zhan David W. Casbeer A. Lee Swindlehurst. Adaptive MobileSensor Positioning for Multi-Static Target Tracking. IEEE TRANSACTIONSON AEROSPACE AND ELECTRONIC SYSTEMS VOL.46, NO.1JANUARY2010.pp:120-132
[34] Chen Huiying, Li Youfu. Dynamic view planning by effective particles forthree-dimensional tracking [J]. IEEE Transaction on Systems, Man, andCybernetics—Part B: Cybernetics,2009,39(1), pp:242-253.
[35] X. C. Ding, A. Rahmani, and M. Egerstedt,“Optimal multi-UAV convoyprotection,” presented at the Int. Conf. Robot Commun. Coord.,Odense,Denmark, Apr.2009
[36] Xu Chu (Dennis) Ding, Amir R. Rahmani, and Magnus Egerstedt. Multi-UAVConvoy Protection: An Optimal Approach to Path Planning and Coordination.IEEE TRANSACTIONS ON ROBOTICS, VOL.26, NO.2, APRIL2010.pp:256-268
[37] Y. Yang, A. Minai, and P. Polycarpou,“Decentralized cooperative search inUAVs using opportunistic learning,” in Proc. AIAA Guid., Navigat., ControlConf., Monterey, CA,2002
[38] F. Gaudiano, E. Bonabeau, and B. Shargel,“Evolving behaviors for a swarm ofunmanned air vehicles,” in Proc. IEEE Swarm Intell. Symp., Pasadena, CA,2005, pp.317–324
[39] Laliberte Andrea S, Rango Albert. Texture and scale in object-based analysis ofsubdecimeter resolution unmanned aerial vehicle (UAV) imagery [J]. IEEETransaction on Geoscience and Remote Sensing,2009,47(3), pp:761-770.
[40] Parunak H V D，Purcell M，Connell P0. Digital Pheromones for AutonomousCoordination of Swarming UAVs [A]. The First AIAA Unmanned AerospaceVehicles Systems Technologies and operations Conference [C].2002.AIAA, pp:2002-3446.
[41] Prithviraj Dasgupta. A Multiagent Swarming System for Distributed AutomaticTarget Recognition Using Unmanned Aerial Vehicles. IEEE TRANSACTIONSON SYSTEMS, MAN, AND CYBERNETICS—PART A: SYSTEMS ANDHUMANS, VOL.38, NO.3, MAY2008, pp:549-563
[42]陈岩.蚁群优化理论在无人机战术控制中的应用研究。国防科技大学博士论文。2007年4月,pp:3-13
[43] J. Zhang Y. Wu w. Liu X. Chen. Novel Approach to Position and OrientationEstimation in Vision-Based UAV Navigation. IEEE TRANSACTIONS ONAEROSPACE AND ELECTRONIC SYSTEMS VOL.46, NO.2APRIL2010.pp:687-700
[44] Y. Yang, A. Minai, and P. Polycarpou,“Decentralized cooperative search inUAVs using opportunistic learning,” in Proc. AIAA Guid., Navigat., ControlConf., Monterey, CA,2002
[45] Mukherjee I, Ray P K. A review of optimization techniques in metal cuttingprocesses [J]. Computers&Industrial Engineering,2006,50(1):15-34.
[46] Zitzler E, Thiele L, Zitzler E, et al. An evolutionary algorithm formultiobjective optimization: The strength Pareto approach [M]. ComputerEngineering and Networks Laboratory (TIK), Swiss Federal Institute ofTechnology Zürich (ETH),1998.
[47] Pehlivanoglu Y V. A new vibrational genetic algorithm enhanced with aVoronoi diagram for path planning of autonomous UAV [J]. Aerospace Scienceand Technology,2012,16(1):47-55.
[48] KENNEDY J, EBERHARTR. Particle swarm optimization[C].IEEE Int’t confon Neural Networks. Perth: IEEE,1995, pp:1942-1948
[49] Colorni A，Dorigo M，Maniezzo V. Distributed Optimization by Ant Colonies[A]. Proc lst European Conf Artifieial Life Plans [C]. France:Elsevier，1991,pp:134-142.
[50]欧阳自远,李春来,邹永廖等.嫦娥一号的初步科学成果[J].中国科技成果,2011(9):27-31.
[51] Wolfgang Pitz, David Miler. The TerraSAR-X Satellite. IEEE Transacations ongeoscience and remote sesing, Vol48, NO.2, February2010, pp:615-622.
[52] Perissin D, Wang T. Repeat-pass SAR interferometry with partially coherenttargets[J]. Geoscience and Remote Sensing, IEEE Transactions on,2012,50(1):271-280.
[53] Hu J, Li Z W, Sun Q, et al. Three-Dimensional Surface Displacements FromInSAR and GPS Measurements With Variance Component Estimation [J].Geoscience and Remote Sensing Letters, IEEE,2012,9(4):754-758.
[54] Aguilera E, Nannini M, Reigber A. Multisignal compressed sensing forpolarimetric SAR tomography [J]. Geoscience and Remote Sensing Letters,IEEE,2012,9(5):871-875.
[55] Wan Aziz, W.A., Syahmi, M.Z. and Anuar, A, Terrain Slope Analyses betweenTerrestrial Laser Scanner and Airborne Laser Scanning,2012IEEE Controland System Graduate Research Colloquium, Shah Alam, Selangor, Malaysia,16-17July,2012, pp:242~247
[56] Harding D, Abshire J, Dabney P. The Slope Imaging Multi-polarizationPhoto-counting Lidar: development and performance results[J]. IGARSS,2010,653-656.
[57] Ackemann F. Airborne Laser Scanning-Present Status and FutureExpectations[J]. ISPRS Journal of Photogrammetry and Remote Sensing,1999,54:64-67.
[58] Sima A, Buckley S J, Kurz T H, et al. Semi-automatic Integration of PanoramicHyperspectral Imagery with Photorealistic Lidar Models[J].Photogrammetrie-Fernerkundung-Geoinformation,2012,2012(4):443-454.
[59]张良,马洪超,邬建伟.联合机载LiDAR数据和潮汐数据自动提取潮位线[J].遥感学报,2012,2:015.
[60]黄先锋,王潇,张帆.基于带权点法向量的LiDAR数据屋顶检测方法[J].武汉大学学报:信息科学版,2009,34(1):24-27.
[61] Nixon M, Aguado A S. Feature Extraction&Image Processing for ComputerVision[M]. Academic Press,2012.
[62] B. S rma ek and C. ünsalan,“Urban area and building detection using SIFTkeypoints and graph theory,” IEEE Trans. Geosci. Remote Sens.,vol.47, no.4,Apr.2009, pp:1156-1167
[63] L. M. Fonte, S. Gautama,W. Philips, and W. Goeman,“Evaluating cornerdetectors for the extraction of man made structures in urban areas,” in Proc.IEEE Int. Geosci. Remote Sens. Symp.,2005
[64] D. Ziou, S. Tabbone, Edge detection techniques-an overview, http://citeseer.nj.nec. com/ziou97edge.html,1997
[65] Jon Atli Benediktsson and Kolbeinn Arnason. Classification and FeatureExtraction for Remote Sensing Images From Urban Areas Based onMorphological TransformationsIEEE TRANSACTIONS ON GEOSCIENCEAND REMOTE SENSING, VOL.41, NO.9, SEPTEMBER2003
[66] Caroline Lacoste, Xavier Descombes, and Josiane Zerubia, Point Processes forUnsupervised Line Network Extraction in Remote SensingIEEETRANSACTIONS ON PATTERN ANALYSIS AND MACHINEINTELLIGENCE, VOL.27, NO.10, OCTOBER2005
[67] C. ünsalan,“Gradient magnitude based support regions in structural land useclassification,” IEEE Geosci. Remote Sens. Lett., vol.3, no.4, Oct.2006, pp:546–550
[68] C. ünsalan and K. L. Boyer,“Classifying land development in high resolutionpanchromatic satellite images using straight line statistics,” IEEE Trans.Geosci. Remote Sens., vol.42, no.4, Apr.2004, pp:907–919
[69] X. Xialgang, S. Zhengxing, and P. Binin el. An Online Composite GraphicsRecognition Approach Based on Matching of Spatial Relation Graphs.International Journal on Document Analysis and Recognition,2004,7(1),pp:44~55
[70] Y. Liu, L. Wenyin, and C. Jiang. A structural Approach to RecognizingIncomplete Graphic Objects. Proceedings of the17th International Conferenceon Pattern Recognition, Cambridge, UK,2004,pp:371~375
[71] C. Ah-Soon, K. Tombre. Architectural Symbol Recognition Using a Network ofConstrains. Pattern Recognition Letters.2001,22(2),pp:231~248
[72] B. Yu. Automatic Understanding of Symbol-Connected Diagrams. Proceedingsof the3rd International Conference on Document Analysis and Recognition,Montreal, Canada,1995,pp:803~806
[73] H. Hse, R.R. Newton. Sketched Symbol Recognition Using ZernikeMovements. Proceedings of the17th International Conference on PatternRecognition, Cambridge, UK,2004,pp:367~370
[74] S. Benlonie, J. Malik, and J. Puzicha. Shape Matching and Object RecognitionUsing Shape Contexts. IEEE Transaction on Pattern Analysis and MachineIntelligence.2002,24(4),pp:509~522
[75] P. Dosch and J. Lladós. Vectorial Signatures for Symbol Discrimination.Proceedings of5th International Workshop on Graphics Recognition: RecentAdvances and Perspectives, Springer, German,2003:154~165
[76] T. Peli, An algorithm for recognition and localization of rotated and scaledobjects, Proceedings of the IEEE1981,69, pp:483–485.
[77] A. Taza, C.Y. Suen, Description of planar shapes using shape matrices, IEEETransactions on Systems, Man, and Cybernetics1989,19, pp:1281–1289.
[78] H. Li, B.S. Manjunath, S.K. Mitra, A contour-based approach tomultisensorimage registration, IEEE Transactions on ImageProcessing1995,4:320–334.
[79] J. Flusser, T. Suk, A moment-based approach to registration of images withaffine geometric distortion, IEEE Transactions on Geoscience and RemoteSensing1994,32,pp::382–387.
[80] D. Bhattacharya, S. Sinha, Invariance of stereo images via theory of complexmoments, Pattern Recognition1997,30, pp::1373–1386.
[81] L. Bruzzone and L. Carlin,“A multilevel context-based system forclassification of very high spatial resolution images,” IEEE Trans.Geosci.Remote Sens., vol.44, no.9, pp.2587–2600, Sep.2006.
[82] V. C. Chen, F. Li, S. S. Ho, and H. Wechsler,“Micro-Doppler effect in radar:Phenomenon, model, and simulation study,” IEEE Trans. Aerosp. Electron.Syst., vol.42, no.1, pp.2–21, Jan.2006.
[83] C. J. S. deSilva, G. Lee, and R. Johnson,“All-aspect ship recognition ininfrared images,” in Proc. Electron. Technol. Directions Year2000, May23–25,1995, pp.194–198.
[84] Rulon Mayer and Richard Priest，Object Detection Using TransformedSignatures in Multitemporal Hyperspectral Imagery. IEEE TRANSACTIONSON GEOSCIENCE AND REMOTE SENSING, VOL.40, NO.4, APRIL2002
[85] HSUAN REN, QIAN DU,Automatic Target Recognition for HyperspectralImagery using High-Order Statistics IEEE TRANSACTIONS ONAEROSPACE AND ELECTRONIC SYSTEMS VOL.42, NO.4OCTOBER2006.
[86] C. Corbane, F. Marre, and M. Petit,“Using SPOT-5HRG data in panchromaticmode for operational detection of small ships in tropical area,”Sensors, vol.8,no.5, pp.2959–2973, May2008.
[87] L. De Lathauwer, B. De Moor, and J. Vandewalle,“An introduction toindependent component analysis,” J. Chemom., Multi-Way Anal., vol.14, no.3, pp.123–149, May/Jun.2000.
[88] V. Shah, N. Younan, S. Durbha, and R. King,“Wavelet features for informationmining in remote sensing imagery,” in IEEE Int. Conf. Geosci. Remote Sens.Symp., Jul.2005, vol.8, pp.5630–5633.
[89] Yeom S, Javidi B, Watson E. Photon counting passive3D image sensing forautomatic target recognition[J]. Optics Express,2005,13(23):9310-9330.
[90] P.J. Besl, N.D. McKay, A method for registration of3D shapes, IEEETransactions on Pattern Analysis and Machine Intellinegce1992,14:239–254.
[91] Z. Zhang, Iterative Point Matching for Registration of Free-form Curves andSurfaces, Int. J. Comput. Vision，1994,13:119–152.
[92] Y. Chen, G. Medioni, Object modeling by registration of multiple range images,Image Vision Comput.1992,10:145–155.
[93] V. Ayyagari, F. Boughorbel, A. Koschan, M.. Abidi, A new method forautomatic3D face registration, IEEE CVPR,2005:119-1122.
[94] Allen P K, Troccoli A, Smith B, et al. New methods for digital modeling ofhistoric sites[J]. Computer Graphics and Applications, IEEE,2003,23(6):32-41.
[95] Vanden Wyngaerd J, Van Gool L. Automatic crude patch registration: towardautomatic3D model building[J]. Computer Vision and Image Understanding,2002,87(1):8-26.
[96] S. Yamany, A Farag, Surface Signatures: An Orientation IndependentFree-Form Surface Representation Scheme for the Purpose of ObjectsRegistration and Matching, IEEE PAMI,2002,24(8):1105-1120
[97] A. Flint A. Dick A. van den Hengel. Local3D structure recognition in rangeimages IET Comput. Vis.,2008, Vol.2, No.4, pp.208–217
[98] LOWE D:‘Distinctive image features from scale-invariant keypoints’, Int. J.Comput. Vis,2004,60,(2), pp.91–110
[99] BAY H., TUYTELAARS T., VAN GOOL L.:‘SURF: speeded up robustfeatures’.9-European Conf. Computer Vision, May2006
[100] Hilla Ben-Yaacov, David Malah Recognition of3D Objects Based on ImplicitPolynomials, IEEE Transaction on Pattern Analysis and Machine Intelligence,vol.32, no.5, May2010. pp:954-960.
[101] A. Brennecke and T. Isenberg.3D Shape Matching Using Skeleton Graphs. InProc. Sim. and Vis.,2004:299-310.
[102] H. Sundar et al.Skeleton Based Shape Matching and Retrieval. SMA,2003:130-142.
[103] Frome A, Huber D, Kolluri R, et al. Recognizing objects in range data usingregional point descriptors[J]. Computer Vision-ECCV2004,2004:224-237.
[104] Andrew Zisserman, David Forsyth, Joe Mundy.“3D Object Recognition usingInvariance” Univerity of Oxford Department of Engineering Science19ParksRoad Oxford OXI3PJ U.K Nov.1994.
[105] Florent Lafarge, Xavier Descombes, Josiane Zerubia, Structural Approach forBuilding Reconstruction from a Single DSM, IEEE Transaction on PatternAnalysis and Machine Intelligence, vol.32, no.1, Jan.2010, pp:135~147.
[106] Aparajithan Sampath and Jie Shan, Segmentation and Reconstruction ofPolyhedral Building Roofs From Aerial Lidar Point Clouds, IEEETRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, VOL.48,NO.3, MARCH2010pp:1554~1565
[107] Jain A K, Duin R P W, Mao J. Statistical pattern recognition: A review[J].Pattern Analysis and Machine Intelligence, IEEE Transactions on,2000,22(1):4-37.
[108] Haykin S S, Haykin S S, Haykin S S, et al. Neural networks and learningmachines[M]. Prentice Hall,2009.
[109] Mandic D P, Chambers J. Recurrent neural networks for prediction: Learningalgorithms, architectures and stability [M]. John Wiley&Sons, Inc.,2001.
[110] Michael E. Tipping. Sparse Bayesian Learning and the Relevance VectorMachine. Journal of Machine Learning Research. Vol.12001, pp:211~244.
[111] Gopal S, Woodcock C E, Strahler A H. Fuzzy neural network classification ofglobal land cover from a1AVHRR data set[J]. Remote sensing ofEnvironment,1999,67(2):230-243.
[112] Benz U C, Hofmann P, Willhauck G, et al. Multi-resolution, object-orientedfuzzy analysis of remote sensing data for GIS-ready information[J]. ISPRSJournal of Photogrammetry and Remote Sensing,2004,58(3):239-258.
[113] Du P, Xia J, Zhang W, et al. Multiple classifier system for remote sensingimage classification: a review [J]. Sensors (Basel, Switzerland),2012,12(4):4764.
[114] Foody G M, Boyd D S, Sanchez‐Hernandez C. Mapping a specific class withan ensemble of classifiers[J]. International Journal of Remote Sensing,2007,28(8):1733-1746.
[115] Benediktsson J A, Swain P H. Consensus theoretic classification methods[J].Systems, Man and Cybernetics, IEEE Transactions on,1992,22(4):688-704.
[116] Doan H T X, Foody G M. Increasing soft classification accuracy through theuse of an ensemble of classifiers[J]. International Journal of Remote Sensing,2007,28(20):4609-4623.
[117] Fauvel M, Chanussot J, Benediktsson J A. Decision fusion for theclassification of urban remote sensing images[J]. Geoscience and RemoteSensing, IEEE Transactions on,2006,44(10):2828-2838.
[118] Debeir O, Latinne P, Van Den Steen I. Remote sensing classification ofspectral, spatial and contextual data using multiple classifier systems[J].2001.
[119] Kumar S, Ghosh J, Crawford M M. Hierarchical fusion of multiple classifiersfor hyperspectral data analysis[J]. Pattern Analysis&Applications,2002,5(2):210-220.
[120] Waske B, Benediktsson J A. Fusion of support vector machines forclassification of multisensor data[J]. Geoscience and Remote Sensing, IEEETransactions on,2007,45(12):3858-3866.
[121] Brown G, Wyatt J, Harris R, et al. Diversity creation methods: a survey andcategorisation[J]. Information Fusion,2005,6(1):5-20.
[122] Min S H, Lee J, Han I. Hybrid genetic algorithms and support vector machinesfor bankruptcy prediction[J]. Expert Systems with Applications,2006,31(3):652-660.
[123] Deeb O, Goodarzi M. Exploring QSARs for Inhibitory Activity of Non‐peptide HIV‐1Protease Inhibitors by GA‐PLS and GA‐SVM[J]. Chemicalbiology&drug design,2010,75(5):506-514.
[124] Zhou X, Li Z, Dai Z, et al. QSAR modeling of peptide biological activity bycoupling support vector machine with particle swarm optimization algorithmand genetic algorithm[J]. Journal of Molecular Graphics and Modelling,2010,29(2):188-196.
[125] Zou H Y, Wu H L, Fu H Y, et al. Variable-weighted least-squares supportvector machine for multivariate spectral analysis[J]. Talanta,2010,80(5):1698-1701.
[126] Huang C L, Dun J F. A distributed PSO–SVM hybrid system with featureselection and parameter optimization[J]. Applied Soft Computing,2008,8(4):1381-1391.
[127] Wu Q, Law R. Cauchy mutation based on objective variable of Gaussianparticle swarm optimization for parameters selection of SVM[J]. ExpertSystems with Applications,2011,38(6):6405-6411.
[128] Dervis Karaboga, Bahriye Akay. A comparative study of Artificial BeeColony algorithm[J]. Applied Mathematics and Computation,2009,214:108–132
[129] Mostafa M M R, Schwarz K P. Digital image georeferencing from a multiplecamera system by GPS/INS [J]. ISPRS journal of photogrammetry and remotesensing,2001,56(1):1-12.
[130]成晓倩,赵红强.基于区域生长的LiDAR点云数据滤波[J].国土资源遥感,2008,78(4):6-8.
[131]覃丹.基于多特征组合和SVM的视频内容自动分类算法研究[D].上海交通大学硕士论文,2009.
[132] Cramer M. The DGPF-Test on Digital Airborne Camera Evaluation Overviewand Test Design[J]. Photogrammetrie-Fernerkundung-Geoinformation,2010,2010(2):73-82.
[133] Vapnik V. The nature of statistical learning theory[M]. springer,1999.
[134] Basturk B, Karaboga D. An artificial bee colony (ABC) algorithm for numericfunction optimization[C]//IEEE swarm intelligence symposium.2006:12-14.
[135] Kazhdan M, Funkhouser T, Rusinkiewicz S. Rotation invariant sphericalharmonic representation of3D shape descriptors[C]//Proceedings of the2003Eurographics/ACM SIGGRAPH symposium on Geometry processing.Eurographics Association,2003:156-164.
[136] Morris R J, Najmanovich R J, Kahraman A, et al. Real spherical harmonicexpansion coefficients as3D shape descriptors for protein binding pocket andligand comparisons[J]. Bioinformatics,2005,21(10):2347-2355.
[137] Mak L, Grandison S, Morris R J. An extension of spherical harmonics toregion-based rotationally invariant descriptors for molecular shape descriptionand comparison[J]. Journal of Molecular Graphics and Modelling,2008,26(7):1035-1045.
[138] Canterakis N.3D Zernike moments and Zernike affine invariants for3Dimage analysis and recognition[J].1999.
[139] Novotni M, Klein R.3D Zernike descriptors for content based shaperetrieval[C]//Proceedings of the eighth ACM symposium on Solid modelingand applications. ACM,2003:216-225.
[140] Millán R D, Dempere-Marco L, Pozo J M, et al. Morphologicalcharacterization of intracranial aneurysms using3-D moment invariants[J].Medical Imaging, IEEE Transactions on,2007,26(9):1270-1282.
[141] Venkatraman V, Sael L, Kihara D. Potential for protein surface shape analysisusing spherical harmonics and3D Zernike descriptors[J]. Cell biochemistryand biophysics,2009,54(1):23-32.
[142] Chang C C, Lin C J. LIBSVM: a library for support vector machines[J]. ACMTransactions on Intelligent Systems and Technology (TIST),2011,2(3):27.
[143] Kohavi R. A study of cross-validation and bootstrap for accuracy estimationand model selection[C]//International joint Conference on artificialintelligence. Lawrence Erlbaum Associates Ltd,1995,14:1137-1145.
[144] Keerthi S S, Lin C J. Asymptotic behaviors of support vector machines withGaussian kernel[J]. Neural computation,2003,15(7):1667-1689.
[145] Lee C P, Lin C J. A study on l2-loss (squared hinge-loss) multi-class SVM[R].Technical report, National Taiwan University,2012. UR L http://www. csie.ntu. edu. tw/~cjlin/papers/l2mcsvm/l2mcsvm. pdf.
[146] Hsieh T J, Yeh W C. Knowledge discovery employing grid scheme leastsquares support vector machines based on orthogonal design bee colonyalgorithm[J]. Systems, Man, and Cybernetics, Part B: Cybernetics, IEEETransactions on,2011,41(5):1198-1212.
[147] Karaboga D, Akay B. A modified Artificial Bee Colony (ABC) algorithm forconstrained optimization problems[J]. Applied soft computing,2011,11(3):3021-3031.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |