基于机器视觉的室外场景图像理解方法研究
|
摘要
对于工作在非结构化环境中的移动机器人,能够具有良好的场景感知与理解能力是其实现自主导航并自主探索环境的前提条件。由于非结构化环境具有多样性、复杂性、随机性等特点,同时机器人可获得的视觉导航先验信息不稳定,且对非结构化环境中多类物体的辨识技术仍不成熟,因此如何使机器人更好地感知并理解非结构化环境成为近年来机器视觉领域密切关注的具有挑战性的研究热点,本文从以下方面对这一问题展开进一步研究。首先,对非结构化环境中的路标信息从不同于地面水平视角的航拍角度进行识别,使移动机器人获得从地面视角难以获得的稳定路标信息,从而更有效地完成视觉导航。其次,为提高室外非结构化环境中多类物体的识别正确率,辅助机器人更加智能化地工作,在求得最佳图像分割块数后,对室外场景中多类物体的识别方法展开进一步研究。
本文以HSP电动攀爬车为平台,建立室外场景图像理解原型系统。根据机器人在非结构化环境中实现基于视觉的导航与环境探索的特点和要求,对基于阴影的航拍图像建筑物检测算法、结合深度信息和图模型求得最佳图像分割块数的算法以及基于条件随机场的多类物体识别算法展开研究。
论文的主要研究工作如下：
第一,对场景理解在机器人视觉中的研究及应用进行回顾,对本文涉及三项关键技术的国内外研究现状进行详细分析。针对目前基于机器视觉的室外场景理解在导航和多类物体辨识上的不足,提出航拍图像建筑物检测和地面场景物体识别的研究方案。
第二,针对基于阴影的航拍图像建筑物检测在建筑物位置搜索及边界提取的不足,提出在简化的建筑物-阴影模型下检测航拍图像中任意轮廓建筑物的算法。该算法在提取建筑物的阴影后,结合航拍图像的拍摄地点及拍摄时间,参照建筑物-阴影模型,能够快速搜索到建筑物方位及建筑物和阴影边界,省去边界的直线逼近过程并加快边界的提取速度。当确定建筑物的初步位置后,通过对比种子和周围区域的灰度直方图得到最终建筑物区域。因此该算法能够更为快速准确地检测出航拍图像中的建筑物。
第三,针对目前研究中图像分割块数和区域合并阈值是根据经验值人为设定,提出通过深度信息和图模型相结合的三维聚类图模型,来确定最优图像分割块数和区域合并闽值。构造以图像分割块数和区域合并阈值为自变量的三维聚类图模型正确率评估函数,通过分析该函数的极值,得到最优图像分割块数和区域合并阈值的组合。在此基础上,利用三维深度信息对二维平面图模型进行编辑,得到整个场景的三维聚类图模型。
第四,为了识别环境中多类物体,对基于分类器的物体辨识展开研究。分析并提取每类物体有效的图像特征,将不同特征进行融合,通过可变长的样本选择方法来选择训练数据,对不同类型的物体设计对应的分类器,以实现对室外场景图像中主要物体的初步识别。
第五,针对基于中低层特征构造的分类器对物体识别时忽略了物体间的相关性,提出基于多分类器初步识别基础上的条件随机场模型。引入针对每类分类器置信度评分的比例系数,构造条件随机场模型的单节点项函数。在使用初步检测特征的基础上加入三维深度特征,利用相邻超级像素间特征的相关性构造条件随机场模型的相邻节点项函数。最后,通过置信传播实现对室外场景物体的最终识别。
最后,论文以HSP电动攀爬车为平台,设计室外场景理解原型系统,该系统由航拍图像建筑物检测模块和地面场景物体识别模块组成。航拍图像建筑物检测模块通过识别航拍图像中的建筑物,获得全局导航的先验信息；地面场景物体识别模块在对采集到的图像提取深度信息后,得到该场景的三维聚类图模型,最后通过基于多分类器初步识别基础上的条件随机场模型实现场景中物体的最终辨识,以实现局部环境感知。
Outdoor scene perception and understanding are indispensable abilities for mobile robot to navigate and explore outdoor environment automatically. However, one main nature of outdoor scene is that it is unstructured, which is always random, diversified and complex. Moreover, the priori vision information of outdoor scene is quit often poor and object recognition technology is thus still immature. So in recent years research on unstructured environment understanding has become a hot research topic in machine vision. In this research for the purpose of navigating automatically, we get the priori information from the aerial image to recognize symbolic objects in unstructured environments. After achieving vision navigation, the robot then locates itself by binocular visual information, and then recognizes multiclass objects by conditional random field model.
We design outdoor scene understanding prototype system based on HSP Electric remote control climb car. According to the requirements on visual-based outdoor navigation and environment exploration, we emphasize on three areas of research:the shadow-based building detection from aerial image, a3D graph model based on depth information and graph model, a multi-class objects recognition process based on conditional random fields.
The main research and achievements of the thesis are as follows:
Firstly, we review state-of-the-art research on scene understanding in robot vision, focusing on three key technologies particularly relevant to this paper. Noticing the shortcoming of current research on outdoor scene understanding and multi-class objects recognition, we formulate the whole plan of the thesis on building detection from aerial image and on an improved outdoor scene objects recognition methods.
Secondly, for shadow-based building detection from aerial image, because the current research has weakness on location detection and boundary extraction, a novel building detection algorithm based on a simplified building-shadow model is proposed. After extracting the shadow of the building, we can quickly search for buildings site and building-shadow boundary by checking shooting time based on the building-shadow model. This process therefore can eliminate straight-line approaching and speed up boundary extraction. After getting the initial building site, we can get the final building areas by comparing the histogram of the seed and the surrounding area.
Thirdly, state-of-the-art research on setting the number of segmentation and threshold of region merging are arbitrary. Therefore we propose a3D clustering graph model which combines depth information and graph model to optimize the segmentation number and the threshold of region merging. We then construct accuracy evaluation function of3D clustering graph model based on segmentation number and threshold of region merging. By obtaining maximum accuracy evaluation function, we get the optimal combination of the segmentation number and the clustering threshold. By editing a two-dimensional graphic model according to the three-dimensional depth information, we can finally get3D clustering graph model of the whole scene.
Fourthly, for the purpose of understanding multi-class objects, the method on classifier-based object recognition is proposed. We analyze, extract, and merge the different features of the objects. We then propose a variable-length sample selection method to select the training data. Finally we design different classifiers to achieve preliminary recognition of the main objects.
Fifthly, because low level feature ignores the relationship among objects, we propose the conditional random fields based on multi-classifier object preliminary recognition. To achieve better segmentation and recognition, our work elaborate on how to model the conditional random fields based on preliminary recognition, how to get single node function and pairwise node function, how to train and learn the model.
Finally, we design a prototype system of outdoor scene understanding based on HSP Electric remote control climb car. The system consists of building detection from aerial image module and outdoor scene objects recognition module. The building detection from aerial image module can get priori global information by detecting buildings from aerial image. The outdoor scene objects recognition module can recognize objects by extracting depth information, by getting3D clustering graph model of the whole scene, and by building the conditional random field based on multi-classifier objects preliminary recognition.
本文以HSP电动攀爬车为平台,建立室外场景图像理解原型系统。根据机器人在非结构化环境中实现基于视觉的导航与环境探索的特点和要求,对基于阴影的航拍图像建筑物检测算法、结合深度信息和图模型求得最佳图像分割块数的算法以及基于条件随机场的多类物体识别算法展开研究。
论文的主要研究工作如下：
第一,对场景理解在机器人视觉中的研究及应用进行回顾,对本文涉及三项关键技术的国内外研究现状进行详细分析。针对目前基于机器视觉的室外场景理解在导航和多类物体辨识上的不足,提出航拍图像建筑物检测和地面场景物体识别的研究方案。
第二,针对基于阴影的航拍图像建筑物检测在建筑物位置搜索及边界提取的不足,提出在简化的建筑物-阴影模型下检测航拍图像中任意轮廓建筑物的算法。该算法在提取建筑物的阴影后,结合航拍图像的拍摄地点及拍摄时间,参照建筑物-阴影模型,能够快速搜索到建筑物方位及建筑物和阴影边界,省去边界的直线逼近过程并加快边界的提取速度。当确定建筑物的初步位置后,通过对比种子和周围区域的灰度直方图得到最终建筑物区域。因此该算法能够更为快速准确地检测出航拍图像中的建筑物。
第三,针对目前研究中图像分割块数和区域合并阈值是根据经验值人为设定,提出通过深度信息和图模型相结合的三维聚类图模型,来确定最优图像分割块数和区域合并闽值。构造以图像分割块数和区域合并阈值为自变量的三维聚类图模型正确率评估函数,通过分析该函数的极值,得到最优图像分割块数和区域合并阈值的组合。在此基础上,利用三维深度信息对二维平面图模型进行编辑,得到整个场景的三维聚类图模型。
第四,为了识别环境中多类物体,对基于分类器的物体辨识展开研究。分析并提取每类物体有效的图像特征,将不同特征进行融合,通过可变长的样本选择方法来选择训练数据,对不同类型的物体设计对应的分类器,以实现对室外场景图像中主要物体的初步识别。
第五,针对基于中低层特征构造的分类器对物体识别时忽略了物体间的相关性,提出基于多分类器初步识别基础上的条件随机场模型。引入针对每类分类器置信度评分的比例系数,构造条件随机场模型的单节点项函数。在使用初步检测特征的基础上加入三维深度特征,利用相邻超级像素间特征的相关性构造条件随机场模型的相邻节点项函数。最后,通过置信传播实现对室外场景物体的最终识别。
最后,论文以HSP电动攀爬车为平台,设计室外场景理解原型系统,该系统由航拍图像建筑物检测模块和地面场景物体识别模块组成。航拍图像建筑物检测模块通过识别航拍图像中的建筑物,获得全局导航的先验信息；地面场景物体识别模块在对采集到的图像提取深度信息后,得到该场景的三维聚类图模型,最后通过基于多分类器初步识别基础上的条件随机场模型实现场景中物体的最终辨识,以实现局部环境感知。
Outdoor scene perception and understanding are indispensable abilities for mobile robot to navigate and explore outdoor environment automatically. However, one main nature of outdoor scene is that it is unstructured, which is always random, diversified and complex. Moreover, the priori vision information of outdoor scene is quit often poor and object recognition technology is thus still immature. So in recent years research on unstructured environment understanding has become a hot research topic in machine vision. In this research for the purpose of navigating automatically, we get the priori information from the aerial image to recognize symbolic objects in unstructured environments. After achieving vision navigation, the robot then locates itself by binocular visual information, and then recognizes multiclass objects by conditional random field model.
We design outdoor scene understanding prototype system based on HSP Electric remote control climb car. According to the requirements on visual-based outdoor navigation and environment exploration, we emphasize on three areas of research:the shadow-based building detection from aerial image, a3D graph model based on depth information and graph model, a multi-class objects recognition process based on conditional random fields.
The main research and achievements of the thesis are as follows:
Firstly, we review state-of-the-art research on scene understanding in robot vision, focusing on three key technologies particularly relevant to this paper. Noticing the shortcoming of current research on outdoor scene understanding and multi-class objects recognition, we formulate the whole plan of the thesis on building detection from aerial image and on an improved outdoor scene objects recognition methods.
Secondly, for shadow-based building detection from aerial image, because the current research has weakness on location detection and boundary extraction, a novel building detection algorithm based on a simplified building-shadow model is proposed. After extracting the shadow of the building, we can quickly search for buildings site and building-shadow boundary by checking shooting time based on the building-shadow model. This process therefore can eliminate straight-line approaching and speed up boundary extraction. After getting the initial building site, we can get the final building areas by comparing the histogram of the seed and the surrounding area.
Thirdly, state-of-the-art research on setting the number of segmentation and threshold of region merging are arbitrary. Therefore we propose a3D clustering graph model which combines depth information and graph model to optimize the segmentation number and the threshold of region merging. We then construct accuracy evaluation function of3D clustering graph model based on segmentation number and threshold of region merging. By obtaining maximum accuracy evaluation function, we get the optimal combination of the segmentation number and the clustering threshold. By editing a two-dimensional graphic model according to the three-dimensional depth information, we can finally get3D clustering graph model of the whole scene.
Fourthly, for the purpose of understanding multi-class objects, the method on classifier-based object recognition is proposed. We analyze, extract, and merge the different features of the objects. We then propose a variable-length sample selection method to select the training data. Finally we design different classifiers to achieve preliminary recognition of the main objects.
Fifthly, because low level feature ignores the relationship among objects, we propose the conditional random fields based on multi-classifier object preliminary recognition. To achieve better segmentation and recognition, our work elaborate on how to model the conditional random fields based on preliminary recognition, how to get single node function and pairwise node function, how to train and learn the model.
Finally, we design a prototype system of outdoor scene understanding based on HSP Electric remote control climb car. The system consists of building detection from aerial image module and outdoor scene objects recognition module. The building detection from aerial image module can get priori global information by detecting buildings from aerial image. The outdoor scene objects recognition module can recognize objects by extracting depth information, by getting3D clustering graph model of the whole scene, and by building the conditional random field based on multi-classifier objects preliminary recognition.
引文
[1]Henderson J M, Hollingworth M. High-level scene perception[J]. Annual Review of Psychology,1999(50):243-271.
[2]谢昭,图像理解的关键问题和方法研究[D].合肥工业大学,2007.
[3]Desouza G N, Kak A C. Vision for mobile robot navigation:a survey[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(2):237-267
[4]Lowed.G. Distinetive image features from seale invariant keypoints[J]. International Journals Computer Vision,2004,60(2):91-110.
[5]Roberts L G., Machine perception of three-dimensional solids[M].1980, New York.
[6]Zahn C. Graph-theoretical methods for detecting and describing gestalt clusters[J]. IEEETransactions on Computers,1971,20:68-86.
[7]Kelly M D. Edge detection in pictures by computer using planning. Machine Intelligence[M]. New York:Elsevier,1971:397-410.
[8]Fischler M A. Aspects of the detection of scene congruence[J]. Artificial Intelligence (Advance Paper).1971:88-100.
[9]Fischler M A, Elschlager R A. The representation and matching of pictorial structures [J]. IEEE Transactions on Computers,1973,22(1):67-92.
[10]Biederman I. Recognition-by-components:a theory of human image understanding[J]. Psychological Review,1987,94(2):115-147.
[11]庄严,陈东,王伟等.移动机器人基于视觉室外自然场景理解的研究与进展[J].自动化学报,2010,36(1)：1-11.
[12]Marr D., Poggi T., Cooperative Computation of Stereo Disparity[J]. Science,1976. 194(4262):p.283-287.
[13]Jain A K, Dubes R C. Algorithms for clustering data[M]. Englewood Cliffs. Prentice Hall, 1988.
[14]Lowe D G. Perceptual organization and visual recognition[M]. Kluwer Academic Publishers. Boston,1985.
[15]Lowe D G, Object recognition from local scale-invariant features[C]. ICCV,1999, 2:1150-1157.
[16]Harris C, Stephens M. A combined Corner and Edge Detector[C]. Proceedings of the Fourth Alvey Vision Conference,1988:147-151.
[17]Jain A K, Hoffman D. Evidence-Based Recognition of 3-D Objects[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.1988,10:783-802.
[18]Pomerleau D A. Knowledge-based training of articial neural networks for autonomous robot driving[J]. Robot Learning.Norwell:Kluwer,1993.19-43.
[19]Jochem T M, Pomerleau D A, Thorpe C E. Vision-based neural network road and intersection detection and traversal[A]. In:Proceedings of the International Conference on Intelligent Robots and Systems[C]. Pittsburgh, USA:IEEE,1995.344-349.
[20]Jochem T M, Pomerleau D A, Thorpe C E. Vision based intersection navigation [A]. Intelligent Vehicles Symposium[C],1996:391-396.
[21]Bischof W F, Caelli T. Scene understanding by rule evaluation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1997,19(11):1284-288.
[22]Draper B A, Hanson A R, Riseman E M. Knowledgedirected vision:control, learning, and integration[J]. Proceedings of the IEEE,1996,84(11):1625-1637.
[23]Batlle J, Casals A, Freixenet J, Marti J. A review on strategies for recognizing natural objects in colour images of outdoor scenes[J]. Image and Vision Computing,2000, 18(6-7):515-530.
[24]Efenberger W, Graefe V. Distance-invariant object recognition in natural scenes[A]. Proeeedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems[C],1996:1433-1439.
[25]Oliva A, Torralba A. The role of context in object recognition[J]. Trends in Cognitive Sciences,2007,11(12):520-527.
[26]Li F F, Perona P, Fergus R. One-shot learning of object categories[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28(4):594-611.
[27]Oliva A, Torralba A. Building the gist of a scene:the role of global image features in recognition[J]. Progress in Brain Research,2006,155(1):23-36.
[28]Larlus D, Jurie F. Combining appearance models and Markov random fields for category level object segmentation[A]. Proceedings of the Conference on Computer Vision and Pattern Recognition[C]. Alaska, USA.2008:1-7.
[29]Lafferty J, McCallum A, Fernando Pereira Conditional Random Fields:Probabilistic Models for Segmenting and Labeling Sequence Data[A].'01 Proceedings of the Eighteenth International Conference on Machine Learning(ICML)[C],2001:282-289.
[30]Belongie S, Malik J, Puzicha J. Shape matching and object recognition using shape contexts[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002, 24(4):509-522.
[31]Lowe D G. Distinctive image features from scale-invariant key-points [J]. International Journal of Computer Vision,2004,60(2):91-110.
[32]Singh S, Markou M, Haddon J. Natural object classification using artificial neural networks[A]. Proceedings of the International Joint Conference on Neural Nerworks[C], 2000,3:139-144.
[33]Singh S, Haddon J, Markou M. Nearest-neighbour classifiers in natural scene analysis[J]. Pattern Recognition,.2001,34(8):1601-1612.
[34]Li s x, Chang H X, Zhu C F. Adaptive pyramid mean shift for global real-time visual tracking[J]. Image and Vision Computing,2010,28(3):424-437.
[35]Fauqueur J, Brostow G, Cipolla R. Assisted video object labeling by joint tracking of regions and keypoints[A]. Proceedings of the 11th IEEE International Conference on Computer Vision[C],2007.1-7.
[36]Torralba A, Murphy K P, Freeman W T. Sharing visual features for multiclass and multiview object detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2007, 29(5):854-869.
[37]Kumar M P, Koller D. Efficiently selecting regions for scene understanding[J]. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition[C], 2010:3217-3224.
[38]Nilsson N J. A mobile automaton:An application of artificial intelligence techniques[A]. Proceedings of the 1st International Joint Conference on Artificial Intelligence[C].1969: 509-520.
[39]Turk M A, Morgenthaler D G, Gremban K D. Video Road-Following for the Autonomous Land Vehiele[J], IEEE Trans.on Roboties and Automation.1987,2413(3):273-279.
[40]Turk M A, Morgenthaler D G. Gremban K D. VITS-AVision System for Autonomous Land Vehiele Navigation[J], IEEE Trans PAMI.1988,10(3):342-361.
[41]Thorpe C, Herbert M, et al.Toward autonomous driving:the CMU Navlab. I. Perception[J]. IEEE Expert,1991,6(4):31-42.
[42]Thorpe C, Herbert M, et al.Toward autonomous driving:the CMU Navlab. II:Architecture and systems[J]. IEEE Expert.1991,6(4):44-52.
[43]Regensburger U, Graefe V, Visual Recognition of Obstacles on Roads[A]. Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems[C],1994:980-987.
[44]Schafer H, Proetzsch M, Braun T, et al. RAVON-A Robust Autonomous Vehicle for Off-road Navigation[A]. European Land Robot Trial-ELROB[C],2006:1-15.
[45]Grudic G, Mulligan J, Otte M, et al. Online Learning of Multiple Perceptual Models for Navigation in Unknown Terrain[A]. Proceedings of the International Conference on Field and Service Robotics[C].2007,42:411-420.
[46]Jon B, Tully F, Jim K, Alex K, Daniel L, et al.Little Ben:The Ben Franklin Racing Team's entry in the 2007 DARPA Urban Challenge. Brian Source:Springer Tracts in Advanced Robotics[J],2009,56:231-255. The DARPA Urban Challenge-Autonomous Vehicles in City Traffic.
[47]Meng X Q, Hu Z Y. A New Easy Camera Calibration Technique Based on Circular Points[J]. Pattern Recognition,2003,36(5):1155-1164.
[48]Ying X H, Hu Z Y. Catadioptric Camera Calibration Using Geometric Invariants[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(10):1260-1271.
[49]Zhang B, Li Y F, Wu Y H. Self-Recalibration of a Structured Light System via Plane-Based Homography[J]. Pattern Recognition,2007,40(4):1368-1377.
[50]Wang Z H, Wu F C, Hu Z Y. MSLD:A robust descriptor for line matching[J]. Pattern Recognition,2009,42(5):941-953.
[51]邵泽明,视觉移动机器人自主导航关键技术研究[D],南京航空航天大学,2009.
[52]Benedek C S, Bayesian Foreground and Shadow Detection in Uncertain Frame Rate Surveillance Videos[J]. IEEE Transactions on Image Processing.2008,17(4):608-621.
[53]Singhal A, Luo J, Zhu W, Probabilistic spatial context models for scene content understanding[J]. CVPR,2003,1:235-241.
[54]Porway J, Wang K, Yao B, Zhu S C, A Hierarchical and Contextual Model for Aerial Image Understanding[J]. CVPR,2008:1-8.
[55]Herman M, Kanade T, The 3D MOSAIC scene understanding system:Incremental reconstruction of 3D scenes from complex images[J]. Robotics Institute, Carnegie Mellon University,1984.
[56]Mohan R N, Using Perceptual Organisation to Extract 3-D Structures [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1989:1121-1139.
[57]Noronha S, Nevatia R, Detecting buildings in aerial images[J]. Computer Vision, Graphics, and Image Processing,1988,14(2):135-152.
[58]Karantzalos K, Argialas D, A Region-based Level Set Segmentation for Automatic Detection of Man-made Objects from Aerial and Satellite Images[J]. Photogrammetric Engineering and Remote Sensing,2009,75(6):667-677.
[59]Zimmermann P, A new framework for automatic building detection analysing multiple cue data[A]. XIXth ISPRS Congress 2000[C],33(B3):1063-1070.
[60]Lin C, Nevatia R, Building detection and description from a single intensity image[J]. Computer Vision and Image Understanding,1998.72(2):p.101-121.
[61]Irvin RB, McKeown DM, Methods for Exploiting the Relationship Between Buildings and Their Shadows in Aerial Imagery[J]. IEEE Transactions on Systems, Man and Cybernetics,1989,19(6):1564-1575.
[62]Matsuoka T T, Yamazaki M, Shadow analysis in assisting damage detection due to earthquakes from QuickBird imagery[A]. Proceedings of the 10th international society for photogrammetry and remote sensing congress[C],2004:607-611.
[63]Tison C, Tupin F, Maitre H, Retrieval of building shapes from shadows in high resolution SAR interferometric images[J]. IGARSS 2004,3:1788-1791.
[64]Kim T, Muller J P, Development of a graph-based approach for building detection[J]. Image and Vision Computing,1999,17(1):3-14.
[65]Thiele A, Cadario E, Schulz K, Thonnessen U, Soergel U, Building Recognition From Multi-Aspect High-Resolution lnSAR Data in Urban Areas[J]. Geoscience and Remote Sensing,2007,45(11):3583-3593.
[66]Roberts L. Machine perception of three-dimensional solids[M]. Optical and Electron Optical Information Processing.1965 Cambridge, MA:MIT Press.
[67]Douglass R J. Interpreting three-dimensional seenes:a model building approach[J], Computer Graphics and Image Proeessing,1981,17:91-113.
[68]蔡清华,刘伟军等.基于surfacer的点云数据的预处理研究[J].机械与制造,2003,4：65-67.
[69]Snidero M, Amilibia A, Gratacos O, ect.The 3D reconstruction of geological structures based on remote sensing data:Example from the Anaran Anticline, Lurestan province, Zagros fold and thrust belt, Iran[J]. Journal of the Geological Society,2011,168(3):769-782.
[70]Harati A, Gachter S, Siegwart R. Fast Range Image Segmentation for Indoor 3D-SLAM[A]. The 6th IFAC Symposium on Intelligent Autonomous Vehicles[C],2007.
[71]Ducke B, Score D, Reeves J. Multiview 3D reconstruction of the archaeological site at Weymouth from image series[J]. Computers and Graphics (Pergamon),2011,35(2):375-382.
[72]Snidero M, Amilibia A, Gratacos O, et al. The 3D reconstruction of geological structures based on remote sensing data:Example from the Anaran Anticline, Lurestan province, Zagros fold and thrust belt, Iran[J]. Journal of the Geological Society,2011,168(3)769-782.
[73]Fischer D, Kohlhepp P.3D Geometry Reconstruction from Multiple Segmented Surface Descriptions Using Neuro-Fuzzy Similarity Measures[J]. Journal of Intelligent & Robotic Systems,2000,29(4):389-431.
[74]Gupta G, Balasubramanian R, Rawat M S, et al. Stereo matching for 3D building reconstruction[J]. Communications in Computer and Information Science,2011:522-529.
[75]Hwang E. Apparatus and method of compressing dynamic range of image[P]. Assignee: Samsung Electronics Co., Ltd. Publication Number:US7382941 Publication date: 06/03/2008.
[76]Besl P J, Jain R C. Segmentation Through Variable Order Surface Fitting[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1988,10(2):167-192.
[77]范剑英,于舒春,王洋等.基于法向分量边缘融合的深度图像分割[J].计算机工程,2009,36(17)：221-225.
[78]Stormer A, Hofmann M, Rigoll G. Depth gradient based segmentation of overlapping foreground objects in range images[A].13th Conference on Information Fusion[C].,2010.
[79]陶曼.深度图像的分割与压缩[D].首都师范大学,2006.
[80]Zhu X I, Zha H B. Segmentation and classification of range image from an intelligent vehicle in urban environment[A]. IEEE/RSJ 2010 International Conference on Intelligent Robots and Systems[C],2010:1457-1462.
[81]Pamplona S M, Silva L, Bellon O, et al. Automatic face segmentation and facial landmark detection in range images[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics,2010,40(5):1319-1330.
[82]Pedersoli M, Vedaldi A, Gonzalez J. A Coarse-to-fine approach for fast deformable object detection[C]. IEEE. Conference on Computer Vision and Pattern(CVPR).2011:1353-1360.
[83]He X, Zemel R S, Ray D, Learning and incorporating top-down cues in image segmentation[C]. ECCV,2006,1:338-351.
[84]Levin A, Weiss Y. Learning to combine bottom-up and top-down segmentation[J]. International Journal of Computer Vision,.2009,81(1):105-118.
[85]Yao B, Khosla A, and Li. Fei-Fei. Combining Randomization and Discrimination for Fine-Grained Image Categorization[C]. IEEE. Conference on Computer Vision and Pattern(CVPR).2011:1577-1584.
[86]郁生阳,基于能量最小化图割得图像与视频目标精确分割研究[D].上海交通大学,2009.
[87]Deng J, Berg A, Li F F. Hierarchical Semantic Indexing for Large Scale Image Retrieval(J). IEEE. Conference on Computer Vision and Pattern(CVPR).2011:785-792.
[88]Li J L, Su H, Xing E P and Li F F. Object Bank:A High-Level Image Representation for Scene Classification and Semantic Feature Sparsification[C]. Proceedings of the Neural Information Processing Systems (NIPS),2010.
[89]Anil K. Jain, R.P.W.D., Jianchang Mao Statistical pattern recognition:A review[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI),2000,22(1):4-37.
[90]Srinivasan P, Shi J, Bottom-up Recognition and Parsing of the Human Body[C]. IEEE Conference on Computer Vision and Pattern (CVPR),2007:1-8.
[91]王利明,机器视觉中物体识别方法的研究与探讨[M].复旦大学,2009.
[92]Cross G R, Markov Random Field Texture Models[J]. IEEE Trans.on PAMI,1993. 5(1):25-39.
[93]郁生阳,基于能量最小化图割的图像与视频目标精确分割研究[D].上海交通大学,2009.
[94]Dolce, Paul F. An expectation maximization solution for fusing 2-D and 3-D LADAR data[J]. Proceedings of SPIE-The International Society for Optical Engineering.2011, v7873.
[95]Jin Q N, Tautenhahn U. Implicit iteration methods in Hilbert scales under general smoothness conditions[J]. Inverse Problems.2011,27(4).
[96]熊英,中文自然语言理解中基于条件随机场理论的词法分析研究[D].上海交通大学,2009.
[97]McEliece R J. MacKay D J C, Cheng J F. Turbo decoding as an instance of Pearl's'belief propagation'algorithm[J]. IEEE Journal on Selected Areas in Communications, 1998,16(2):140-152.
[98]Murphy K, Weiss Y and Jordan M. Loopy belief propagation for approximate inference:an empirical study[C].Proceedings of the Fifteenth Conference on Uncertainty in Artificial Intelligence.1999.
[99]Anna B, et al. A review:Which is the best way to organize/classify images by content[J]. Image and Vision Computing,2007,25(6):778-791.
[100]Sapiro G, Caselles V, Histogram modification via partial differential equations[C]. ICIP, 1995,3:632-635.
[101]Fischler M A, Elschlager R A, The representation and matching of pictorial structures[J]. IEEE Transactions on In Computers,1973,22(1):67-92.
[102]Felzenszwalb P, Huttenlocher D, Efficient Matching of Pictorial Structures[C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR),2000, 2:66-73.
[103]He X, Zemel R and Carreira-Perpinan M, Multiscale conditional random fields for image labelling[C]. CVPR,2004.
[104]He X, Zemel R, multiscale conditional random fields for image labelling[C]. CVPR, 2004,2:695-702.
[105]Gould S, Rodgers J, Cohen D, Elidan E, Koller D. Multiclass segmentation with relative location prior[C]. IJCV,2008,80(3):300-316.
[106]Levin A, Weiss Y, Learning to combine bottom-up and top-down segmentation [A]. Proc.of ECCV[C],2006,3954:581-594.
[107]Borenstein E, Ullman S. Combined Top-Down Bottom-Up Segmentation [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,30(12):2109-2125.
[108]Bileschi S M. StreetScenes:Towards Scene Understanding in Still Images[D]. Massachusetts Institute of Technology,2006..
[109]Liu C, Yuen J, Torralba A. Nonparametric scene parsing:label transfer via dense scene alignment. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition (CVPR'09).2009:1972-1979.
[110]Shotton J, Winn J, Rother C, Criminisi A. TextonBoost for image understanding: multi-class object recognition and segmentation by jointly modeling texture, layout, and context[J]. International Journal of Computer Vision,2009,81(1):2-23.
[111]李福文,金伟其,陈伟力.基于Retinex模型的彩色图像全局增强算法[D],北京理工大学学报,2010,20(8).
[112]Khaytun F I, Kadzov D A. Calculation of the reflection from Lambertian suefaces when the irradiation is unsteady[J]. Soviet Journal of Optical Technology,1972,39(8):511-512.
[113]Shi J and Malik J. Normalized Cuts and Image Segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence(PAMI),2000,22(8):888-905.
[114]Chung K L, Lin Y R, Huang Y H. Efficient Shadow Detection of Color Aerial Images[J]. Transactions on Geoscience and Remote Sensing,2009,47(2):671-682.
[115]Felzenszwalb P F, Huttenlocher D P. Efficient Graph-Based Image Segmentation[J]. International Journal of Computer Vision.2004,59(2):167-181.
[116]刘维,基于双目立体视觉的物体深度信息提取系统[D].中南大学,2009.
[117]韩云生,基于双目立体视觉的移动机器人目标定位[D].江南大学,2009.
[118]马颂德,张正友.计算机视觉-计算机理论与算法基础[M].北京：科学出版社,1998.
[119]邵泽明,视觉移动机器人自主导航关键技术研究[D].南京航空航天大学,2009.
[120]万定锐,基于PTZ双目视觉的运动目标检测[D].清华大学,2009.
[121]Lankton S M. Localized Statistical Models in Computer Vision[D]. Georgia Institute of Technology,2009.
[122]Gevers T, Smeulders A. W. M, PicToSeek:combining color and shape invariant features for image retriev[J]. IEEE Trans, on Image Processing,2002.9(1):102-119.
[123]Malik J, Belongie S, Leung T, Shi J, Contour and Texture analysis for image segmentation[J]. International Journals computerVision,2001,43(1):7-27.
[124]Torralba A, Murphy K P, Freeman W T. Contextual Models for objeet deteetion using boosted random fields[J]. Advanees in Neural Information Proeessing Systems, 2005:1401-1408.
[125]Neubeck A, Van G L. Efficient non-maximum suppression[C]. International Conference on Pattern Recognition, ICPR.2006(3):850-855.
[126]Pham T Q. Non-maximum suppression using fewer than two comparisons per pixel[A]. Lecture Notes in Computer Science[C],2010,1:438-451.
[127]Richardson A, Kaminka G, Kraus S. CUBS:Multivariate sequence classification using bounded Z-Score with sampling[C]. IEEE International Conference on Data Mining, ICDM, 2010:72-79.
[128]Lai C C, Jhan C F, Wang W S. Digital image watermarking using DCT and Z-score transform[C].2010 International Conference on Machine Learning and Cybernetics, ICMLC,2010(6):2933-2937.
[129]Leung T, Malik J. Representing and Recognizing the Visual Appearance of Materials using Three-dimensional Textons[J]. International Journal of Computer Vision,2001,43(1): 29-44.
[130]Canny J. Computational approach to edge detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI,.1986,8(6):679-698.
[131]Zhang J, Kamber M, Video compass[C]. ECCV,2002:476-490.
[132]项建英,基于决策树和AdaBoost的孟加拉文数字识别研究[D].华东师范大学,2008.
[133]McCreary E A. How to grow a decision tree[J]. IEEE Engineering Management Review, 1973,1(1):67-72.
[134]Gao W, Hu X B. CLS-based arithmetic for the knowledge discovery of decision process[J]. Journal of Sichuan University (Engineering Science Edition),2006,38(2):79-83.
[135]Wu Z H, Chen Y F, Zhang J. Adaptive rules mining in ACVis based on ID3 algorithm in decision tree[C].2010 2nd Conference on Environmental Science and Information Application Technology,2010(1):446-449.
[136]Setsirichok D, Piroonratana T, Wongseree W, Usavanarong T etc. Classification of complete blood count and haemoglobin typing data by a C4.5 decision tree, a nai've Bayes classifier and a multilayer perceptron for thalassaemia screening[M]. Biomedical Signal Processing and Control,2011
[137]Taherkhani A. Recognizing sorting algorithms with the C4.5 decision tree classifier[C]. IEEE International Conference on Program Comprehension,2010:72-75.
[138]Khosmood F, Turner C. Discovery in negligence analysis:Evolution of a sufficiently safe spec[A]. Proceedings of the IASTED International Conference on Software Engineering and Applications[C].2003(7):687-690.
[139]Thangaparvathi B, Anandhavalli D. An improved algorithm of decision tree for classifying large data set based on rainforest framework[C].2010 IEEE International Conference on Communication Control and Computing Technologies, ICCCCT,2010:800-805.
[140]Murphey Y L, Chen Z H, Guo H. Neural learning using AdaBoost[A]. Proceedings of the International Joint Conference on Neural Networks[C],2001(2):1037-1042.
[141]Bezdek J,Gunderson R, Ehrlich R, Meloy T. On the extension of fuzzy K-means algorithms for detection of linear clusters[C]. Proceedings of the IEEE Conference on Decision and Contro[C]1.1978:1438-1443.
[142]Swami D K. PAMC:Partitioning around Medoids for Classification[J]. Information Technology Journal,2006,5(6):1102-1105.
[143]AINajjar M, Karlapudi S, Bayoumi M. A compact single-pass architecture for hysteresis thresholding and component labeling, Proceedings[C]. International Conference on Image Processing, ICIP.2010:101-104.
[144]Dalal N, Triggs B, Histograms of oriented Gradients for Human Detection[C]. CVPR, 2005,1:886-893.
[145]Dalal N, Finding People in Images and Videos[J]. Institut National Polytechnique de Grenoble,2006.
[146]Felzenszwalb P, Mcallester D, Ramanan D. A Discriminatively Trained, Multiscale, Deformable Part Model[C]. ICCV,2008:1-8.
[147]Vapnik N, The Nature of Statistical Learning Theory[M]. Springer-Verlag,1995.
[148]Chapelle O, Haffner P, Vapnik V N. Support vector machines for histogram-based image classification[J]. IEEE Transactions on Neural Networks,1999,10(5):1055-1064.
[149]Vapnik, V. SVM method of estimating density, conditional probability, and conditional density[A]. Proceedings-IEEE International Symposium on Circuits and Systems,[C] 2000(2):Ⅱ-749-Ⅱ-752.
[150]Sutton R S, Barto A G. Reinforcement Learning:An Introduction[M]. The MIT Press, Cambridge, MA,1998. Softmax Action Selection.
[151]Shotton J, Winn J, Rother C, Criminisi A. TextonBoost for image understanding: multi-class object recognition and segmentation by jointly modeling texture, layout, and context[J]. International Journal of Computer Vision,2009,81(1):2-23.
[152]Sutton C, McCallum A. Piecewise Training for Undirected Models[C]. Conference on Uncertainty in Artificial Intelligence (UAI).2005.
[153]Yedidia J S, Freeman W T, Weis Y. Understanding Belief Propagation and its Generalizations[J]. Exploring Artifieial Inielligence in the New Millennium,2003:239-236.
[2]谢昭,图像理解的关键问题和方法研究[D].合肥工业大学,2007.
[3]Desouza G N, Kak A C. Vision for mobile robot navigation:a survey[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(2):237-267
[4]Lowed.G. Distinetive image features from seale invariant keypoints[J]. International Journals Computer Vision,2004,60(2):91-110.
[5]Roberts L G., Machine perception of three-dimensional solids[M].1980, New York.
[6]Zahn C. Graph-theoretical methods for detecting and describing gestalt clusters[J]. IEEETransactions on Computers,1971,20:68-86.
[7]Kelly M D. Edge detection in pictures by computer using planning. Machine Intelligence[M]. New York:Elsevier,1971:397-410.
[8]Fischler M A. Aspects of the detection of scene congruence[J]. Artificial Intelligence (Advance Paper).1971:88-100.
[9]Fischler M A, Elschlager R A. The representation and matching of pictorial structures [J]. IEEE Transactions on Computers,1973,22(1):67-92.
[10]Biederman I. Recognition-by-components:a theory of human image understanding[J]. Psychological Review,1987,94(2):115-147.
[11]庄严,陈东,王伟等.移动机器人基于视觉室外自然场景理解的研究与进展[J].自动化学报,2010,36(1)：1-11.
[12]Marr D., Poggi T., Cooperative Computation of Stereo Disparity[J]. Science,1976. 194(4262):p.283-287.
[13]Jain A K, Dubes R C. Algorithms for clustering data[M]. Englewood Cliffs. Prentice Hall, 1988.
[14]Lowe D G. Perceptual organization and visual recognition[M]. Kluwer Academic Publishers. Boston,1985.
[15]Lowe D G, Object recognition from local scale-invariant features[C]. ICCV,1999, 2:1150-1157.
[16]Harris C, Stephens M. A combined Corner and Edge Detector[C]. Proceedings of the Fourth Alvey Vision Conference,1988:147-151.
[17]Jain A K, Hoffman D. Evidence-Based Recognition of 3-D Objects[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.1988,10:783-802.
[18]Pomerleau D A. Knowledge-based training of articial neural networks for autonomous robot driving[J]. Robot Learning.Norwell:Kluwer,1993.19-43.
[19]Jochem T M, Pomerleau D A, Thorpe C E. Vision-based neural network road and intersection detection and traversal[A]. In:Proceedings of the International Conference on Intelligent Robots and Systems[C]. Pittsburgh, USA:IEEE,1995.344-349.
[20]Jochem T M, Pomerleau D A, Thorpe C E. Vision based intersection navigation [A]. Intelligent Vehicles Symposium[C],1996:391-396.
[21]Bischof W F, Caelli T. Scene understanding by rule evaluation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1997,19(11):1284-288.
[22]Draper B A, Hanson A R, Riseman E M. Knowledgedirected vision:control, learning, and integration[J]. Proceedings of the IEEE,1996,84(11):1625-1637.
[23]Batlle J, Casals A, Freixenet J, Marti J. A review on strategies for recognizing natural objects in colour images of outdoor scenes[J]. Image and Vision Computing,2000, 18(6-7):515-530.
[24]Efenberger W, Graefe V. Distance-invariant object recognition in natural scenes[A]. Proeeedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems[C],1996:1433-1439.
[25]Oliva A, Torralba A. The role of context in object recognition[J]. Trends in Cognitive Sciences,2007,11(12):520-527.
[26]Li F F, Perona P, Fergus R. One-shot learning of object categories[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28(4):594-611.
[27]Oliva A, Torralba A. Building the gist of a scene:the role of global image features in recognition[J]. Progress in Brain Research,2006,155(1):23-36.
[28]Larlus D, Jurie F. Combining appearance models and Markov random fields for category level object segmentation[A]. Proceedings of the Conference on Computer Vision and Pattern Recognition[C]. Alaska, USA.2008:1-7.
[29]Lafferty J, McCallum A, Fernando Pereira Conditional Random Fields:Probabilistic Models for Segmenting and Labeling Sequence Data[A].'01 Proceedings of the Eighteenth International Conference on Machine Learning(ICML)[C],2001:282-289.
[30]Belongie S, Malik J, Puzicha J. Shape matching and object recognition using shape contexts[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002, 24(4):509-522.
[31]Lowe D G. Distinctive image features from scale-invariant key-points [J]. International Journal of Computer Vision,2004,60(2):91-110.
[32]Singh S, Markou M, Haddon J. Natural object classification using artificial neural networks[A]. Proceedings of the International Joint Conference on Neural Nerworks[C], 2000,3:139-144.
[33]Singh S, Haddon J, Markou M. Nearest-neighbour classifiers in natural scene analysis[J]. Pattern Recognition,.2001,34(8):1601-1612.
[34]Li s x, Chang H X, Zhu C F. Adaptive pyramid mean shift for global real-time visual tracking[J]. Image and Vision Computing,2010,28(3):424-437.
[35]Fauqueur J, Brostow G, Cipolla R. Assisted video object labeling by joint tracking of regions and keypoints[A]. Proceedings of the 11th IEEE International Conference on Computer Vision[C],2007.1-7.
[36]Torralba A, Murphy K P, Freeman W T. Sharing visual features for multiclass and multiview object detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2007, 29(5):854-869.
[37]Kumar M P, Koller D. Efficiently selecting regions for scene understanding[J]. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition[C], 2010:3217-3224.
[38]Nilsson N J. A mobile automaton:An application of artificial intelligence techniques[A]. Proceedings of the 1st International Joint Conference on Artificial Intelligence[C].1969: 509-520.
[39]Turk M A, Morgenthaler D G, Gremban K D. Video Road-Following for the Autonomous Land Vehiele[J], IEEE Trans.on Roboties and Automation.1987,2413(3):273-279.
[40]Turk M A, Morgenthaler D G. Gremban K D. VITS-AVision System for Autonomous Land Vehiele Navigation[J], IEEE Trans PAMI.1988,10(3):342-361.
[41]Thorpe C, Herbert M, et al.Toward autonomous driving:the CMU Navlab. I. Perception[J]. IEEE Expert,1991,6(4):31-42.
[42]Thorpe C, Herbert M, et al.Toward autonomous driving:the CMU Navlab. II:Architecture and systems[J]. IEEE Expert.1991,6(4):44-52.
[43]Regensburger U, Graefe V, Visual Recognition of Obstacles on Roads[A]. Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems[C],1994:980-987.
[44]Schafer H, Proetzsch M, Braun T, et al. RAVON-A Robust Autonomous Vehicle for Off-road Navigation[A]. European Land Robot Trial-ELROB[C],2006:1-15.
[45]Grudic G, Mulligan J, Otte M, et al. Online Learning of Multiple Perceptual Models for Navigation in Unknown Terrain[A]. Proceedings of the International Conference on Field and Service Robotics[C].2007,42:411-420.
[46]Jon B, Tully F, Jim K, Alex K, Daniel L, et al.Little Ben:The Ben Franklin Racing Team's entry in the 2007 DARPA Urban Challenge. Brian Source:Springer Tracts in Advanced Robotics[J],2009,56:231-255. The DARPA Urban Challenge-Autonomous Vehicles in City Traffic.
[47]Meng X Q, Hu Z Y. A New Easy Camera Calibration Technique Based on Circular Points[J]. Pattern Recognition,2003,36(5):1155-1164.
[48]Ying X H, Hu Z Y. Catadioptric Camera Calibration Using Geometric Invariants[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(10):1260-1271.
[49]Zhang B, Li Y F, Wu Y H. Self-Recalibration of a Structured Light System via Plane-Based Homography[J]. Pattern Recognition,2007,40(4):1368-1377.
[50]Wang Z H, Wu F C, Hu Z Y. MSLD:A robust descriptor for line matching[J]. Pattern Recognition,2009,42(5):941-953.
[51]邵泽明,视觉移动机器人自主导航关键技术研究[D],南京航空航天大学,2009.
[52]Benedek C S, Bayesian Foreground and Shadow Detection in Uncertain Frame Rate Surveillance Videos[J]. IEEE Transactions on Image Processing.2008,17(4):608-621.
[53]Singhal A, Luo J, Zhu W, Probabilistic spatial context models for scene content understanding[J]. CVPR,2003,1:235-241.
[54]Porway J, Wang K, Yao B, Zhu S C, A Hierarchical and Contextual Model for Aerial Image Understanding[J]. CVPR,2008:1-8.
[55]Herman M, Kanade T, The 3D MOSAIC scene understanding system:Incremental reconstruction of 3D scenes from complex images[J]. Robotics Institute, Carnegie Mellon University,1984.
[56]Mohan R N, Using Perceptual Organisation to Extract 3-D Structures [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1989:1121-1139.
[57]Noronha S, Nevatia R, Detecting buildings in aerial images[J]. Computer Vision, Graphics, and Image Processing,1988,14(2):135-152.
[58]Karantzalos K, Argialas D, A Region-based Level Set Segmentation for Automatic Detection of Man-made Objects from Aerial and Satellite Images[J]. Photogrammetric Engineering and Remote Sensing,2009,75(6):667-677.
[59]Zimmermann P, A new framework for automatic building detection analysing multiple cue data[A]. XIXth ISPRS Congress 2000[C],33(B3):1063-1070.
[60]Lin C, Nevatia R, Building detection and description from a single intensity image[J]. Computer Vision and Image Understanding,1998.72(2):p.101-121.
[61]Irvin RB, McKeown DM, Methods for Exploiting the Relationship Between Buildings and Their Shadows in Aerial Imagery[J]. IEEE Transactions on Systems, Man and Cybernetics,1989,19(6):1564-1575.
[62]Matsuoka T T, Yamazaki M, Shadow analysis in assisting damage detection due to earthquakes from QuickBird imagery[A]. Proceedings of the 10th international society for photogrammetry and remote sensing congress[C],2004:607-611.
[63]Tison C, Tupin F, Maitre H, Retrieval of building shapes from shadows in high resolution SAR interferometric images[J]. IGARSS 2004,3:1788-1791.
[64]Kim T, Muller J P, Development of a graph-based approach for building detection[J]. Image and Vision Computing,1999,17(1):3-14.
[65]Thiele A, Cadario E, Schulz K, Thonnessen U, Soergel U, Building Recognition From Multi-Aspect High-Resolution lnSAR Data in Urban Areas[J]. Geoscience and Remote Sensing,2007,45(11):3583-3593.
[66]Roberts L. Machine perception of three-dimensional solids[M]. Optical and Electron Optical Information Processing.1965 Cambridge, MA:MIT Press.
[67]Douglass R J. Interpreting three-dimensional seenes:a model building approach[J], Computer Graphics and Image Proeessing,1981,17:91-113.
[68]蔡清华,刘伟军等.基于surfacer的点云数据的预处理研究[J].机械与制造,2003,4：65-67.
[69]Snidero M, Amilibia A, Gratacos O, ect.The 3D reconstruction of geological structures based on remote sensing data:Example from the Anaran Anticline, Lurestan province, Zagros fold and thrust belt, Iran[J]. Journal of the Geological Society,2011,168(3):769-782.
[70]Harati A, Gachter S, Siegwart R. Fast Range Image Segmentation for Indoor 3D-SLAM[A]. The 6th IFAC Symposium on Intelligent Autonomous Vehicles[C],2007.
[71]Ducke B, Score D, Reeves J. Multiview 3D reconstruction of the archaeological site at Weymouth from image series[J]. Computers and Graphics (Pergamon),2011,35(2):375-382.
[72]Snidero M, Amilibia A, Gratacos O, et al. The 3D reconstruction of geological structures based on remote sensing data:Example from the Anaran Anticline, Lurestan province, Zagros fold and thrust belt, Iran[J]. Journal of the Geological Society,2011,168(3)769-782.
[73]Fischer D, Kohlhepp P.3D Geometry Reconstruction from Multiple Segmented Surface Descriptions Using Neuro-Fuzzy Similarity Measures[J]. Journal of Intelligent & Robotic Systems,2000,29(4):389-431.
[74]Gupta G, Balasubramanian R, Rawat M S, et al. Stereo matching for 3D building reconstruction[J]. Communications in Computer and Information Science,2011:522-529.
[75]Hwang E. Apparatus and method of compressing dynamic range of image[P]. Assignee: Samsung Electronics Co., Ltd. Publication Number:US7382941 Publication date: 06/03/2008.
[76]Besl P J, Jain R C. Segmentation Through Variable Order Surface Fitting[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1988,10(2):167-192.
[77]范剑英,于舒春,王洋等.基于法向分量边缘融合的深度图像分割[J].计算机工程,2009,36(17)：221-225.
[78]Stormer A, Hofmann M, Rigoll G. Depth gradient based segmentation of overlapping foreground objects in range images[A].13th Conference on Information Fusion[C].,2010.
[79]陶曼.深度图像的分割与压缩[D].首都师范大学,2006.
[80]Zhu X I, Zha H B. Segmentation and classification of range image from an intelligent vehicle in urban environment[A]. IEEE/RSJ 2010 International Conference on Intelligent Robots and Systems[C],2010:1457-1462.
[81]Pamplona S M, Silva L, Bellon O, et al. Automatic face segmentation and facial landmark detection in range images[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics,2010,40(5):1319-1330.
[82]Pedersoli M, Vedaldi A, Gonzalez J. A Coarse-to-fine approach for fast deformable object detection[C]. IEEE. Conference on Computer Vision and Pattern(CVPR).2011:1353-1360.
[83]He X, Zemel R S, Ray D, Learning and incorporating top-down cues in image segmentation[C]. ECCV,2006,1:338-351.
[84]Levin A, Weiss Y. Learning to combine bottom-up and top-down segmentation[J]. International Journal of Computer Vision,.2009,81(1):105-118.
[85]Yao B, Khosla A, and Li. Fei-Fei. Combining Randomization and Discrimination for Fine-Grained Image Categorization[C]. IEEE. Conference on Computer Vision and Pattern(CVPR).2011:1577-1584.
[86]郁生阳,基于能量最小化图割得图像与视频目标精确分割研究[D].上海交通大学,2009.
[87]Deng J, Berg A, Li F F. Hierarchical Semantic Indexing for Large Scale Image Retrieval(J). IEEE. Conference on Computer Vision and Pattern(CVPR).2011:785-792.
[88]Li J L, Su H, Xing E P and Li F F. Object Bank:A High-Level Image Representation for Scene Classification and Semantic Feature Sparsification[C]. Proceedings of the Neural Information Processing Systems (NIPS),2010.
[89]Anil K. Jain, R.P.W.D., Jianchang Mao Statistical pattern recognition:A review[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI),2000,22(1):4-37.
[90]Srinivasan P, Shi J, Bottom-up Recognition and Parsing of the Human Body[C]. IEEE Conference on Computer Vision and Pattern (CVPR),2007:1-8.
[91]王利明,机器视觉中物体识别方法的研究与探讨[M].复旦大学,2009.
[92]Cross G R, Markov Random Field Texture Models[J]. IEEE Trans.on PAMI,1993. 5(1):25-39.
[93]郁生阳,基于能量最小化图割的图像与视频目标精确分割研究[D].上海交通大学,2009.
[94]Dolce, Paul F. An expectation maximization solution for fusing 2-D and 3-D LADAR data[J]. Proceedings of SPIE-The International Society for Optical Engineering.2011, v7873.
[95]Jin Q N, Tautenhahn U. Implicit iteration methods in Hilbert scales under general smoothness conditions[J]. Inverse Problems.2011,27(4).
[96]熊英,中文自然语言理解中基于条件随机场理论的词法分析研究[D].上海交通大学,2009.
[97]McEliece R J. MacKay D J C, Cheng J F. Turbo decoding as an instance of Pearl's'belief propagation'algorithm[J]. IEEE Journal on Selected Areas in Communications, 1998,16(2):140-152.
[98]Murphy K, Weiss Y and Jordan M. Loopy belief propagation for approximate inference:an empirical study[C].Proceedings of the Fifteenth Conference on Uncertainty in Artificial Intelligence.1999.
[99]Anna B, et al. A review:Which is the best way to organize/classify images by content[J]. Image and Vision Computing,2007,25(6):778-791.
[100]Sapiro G, Caselles V, Histogram modification via partial differential equations[C]. ICIP, 1995,3:632-635.
[101]Fischler M A, Elschlager R A, The representation and matching of pictorial structures[J]. IEEE Transactions on In Computers,1973,22(1):67-92.
[102]Felzenszwalb P, Huttenlocher D, Efficient Matching of Pictorial Structures[C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR),2000, 2:66-73.
[103]He X, Zemel R and Carreira-Perpinan M, Multiscale conditional random fields for image labelling[C]. CVPR,2004.
[104]He X, Zemel R, multiscale conditional random fields for image labelling[C]. CVPR, 2004,2:695-702.
[105]Gould S, Rodgers J, Cohen D, Elidan E, Koller D. Multiclass segmentation with relative location prior[C]. IJCV,2008,80(3):300-316.
[106]Levin A, Weiss Y, Learning to combine bottom-up and top-down segmentation [A]. Proc.of ECCV[C],2006,3954:581-594.
[107]Borenstein E, Ullman S. Combined Top-Down Bottom-Up Segmentation [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,30(12):2109-2125.
[108]Bileschi S M. StreetScenes:Towards Scene Understanding in Still Images[D]. Massachusetts Institute of Technology,2006..
[109]Liu C, Yuen J, Torralba A. Nonparametric scene parsing:label transfer via dense scene alignment. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition (CVPR'09).2009:1972-1979.
[110]Shotton J, Winn J, Rother C, Criminisi A. TextonBoost for image understanding: multi-class object recognition and segmentation by jointly modeling texture, layout, and context[J]. International Journal of Computer Vision,2009,81(1):2-23.
[111]李福文,金伟其,陈伟力.基于Retinex模型的彩色图像全局增强算法[D],北京理工大学学报,2010,20(8).
[112]Khaytun F I, Kadzov D A. Calculation of the reflection from Lambertian suefaces when the irradiation is unsteady[J]. Soviet Journal of Optical Technology,1972,39(8):511-512.
[113]Shi J and Malik J. Normalized Cuts and Image Segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence(PAMI),2000,22(8):888-905.
[114]Chung K L, Lin Y R, Huang Y H. Efficient Shadow Detection of Color Aerial Images[J]. Transactions on Geoscience and Remote Sensing,2009,47(2):671-682.
[115]Felzenszwalb P F, Huttenlocher D P. Efficient Graph-Based Image Segmentation[J]. International Journal of Computer Vision.2004,59(2):167-181.
[116]刘维,基于双目立体视觉的物体深度信息提取系统[D].中南大学,2009.
[117]韩云生,基于双目立体视觉的移动机器人目标定位[D].江南大学,2009.
[118]马颂德,张正友.计算机视觉-计算机理论与算法基础[M].北京：科学出版社,1998.
[119]邵泽明,视觉移动机器人自主导航关键技术研究[D].南京航空航天大学,2009.
[120]万定锐,基于PTZ双目视觉的运动目标检测[D].清华大学,2009.
[121]Lankton S M. Localized Statistical Models in Computer Vision[D]. Georgia Institute of Technology,2009.
[122]Gevers T, Smeulders A. W. M, PicToSeek:combining color and shape invariant features for image retriev[J]. IEEE Trans, on Image Processing,2002.9(1):102-119.
[123]Malik J, Belongie S, Leung T, Shi J, Contour and Texture analysis for image segmentation[J]. International Journals computerVision,2001,43(1):7-27.
[124]Torralba A, Murphy K P, Freeman W T. Contextual Models for objeet deteetion using boosted random fields[J]. Advanees in Neural Information Proeessing Systems, 2005:1401-1408.
[125]Neubeck A, Van G L. Efficient non-maximum suppression[C]. International Conference on Pattern Recognition, ICPR.2006(3):850-855.
[126]Pham T Q. Non-maximum suppression using fewer than two comparisons per pixel[A]. Lecture Notes in Computer Science[C],2010,1:438-451.
[127]Richardson A, Kaminka G, Kraus S. CUBS:Multivariate sequence classification using bounded Z-Score with sampling[C]. IEEE International Conference on Data Mining, ICDM, 2010:72-79.
[128]Lai C C, Jhan C F, Wang W S. Digital image watermarking using DCT and Z-score transform[C].2010 International Conference on Machine Learning and Cybernetics, ICMLC,2010(6):2933-2937.
[129]Leung T, Malik J. Representing and Recognizing the Visual Appearance of Materials using Three-dimensional Textons[J]. International Journal of Computer Vision,2001,43(1): 29-44.
[130]Canny J. Computational approach to edge detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI,.1986,8(6):679-698.
[131]Zhang J, Kamber M, Video compass[C]. ECCV,2002:476-490.
[132]项建英,基于决策树和AdaBoost的孟加拉文数字识别研究[D].华东师范大学,2008.
[133]McCreary E A. How to grow a decision tree[J]. IEEE Engineering Management Review, 1973,1(1):67-72.
[134]Gao W, Hu X B. CLS-based arithmetic for the knowledge discovery of decision process[J]. Journal of Sichuan University (Engineering Science Edition),2006,38(2):79-83.
[135]Wu Z H, Chen Y F, Zhang J. Adaptive rules mining in ACVis based on ID3 algorithm in decision tree[C].2010 2nd Conference on Environmental Science and Information Application Technology,2010(1):446-449.
[136]Setsirichok D, Piroonratana T, Wongseree W, Usavanarong T etc. Classification of complete blood count and haemoglobin typing data by a C4.5 decision tree, a nai've Bayes classifier and a multilayer perceptron for thalassaemia screening[M]. Biomedical Signal Processing and Control,2011
[137]Taherkhani A. Recognizing sorting algorithms with the C4.5 decision tree classifier[C]. IEEE International Conference on Program Comprehension,2010:72-75.
[138]Khosmood F, Turner C. Discovery in negligence analysis:Evolution of a sufficiently safe spec[A]. Proceedings of the IASTED International Conference on Software Engineering and Applications[C].2003(7):687-690.
[139]Thangaparvathi B, Anandhavalli D. An improved algorithm of decision tree for classifying large data set based on rainforest framework[C].2010 IEEE International Conference on Communication Control and Computing Technologies, ICCCCT,2010:800-805.
[140]Murphey Y L, Chen Z H, Guo H. Neural learning using AdaBoost[A]. Proceedings of the International Joint Conference on Neural Networks[C],2001(2):1037-1042.
[141]Bezdek J,Gunderson R, Ehrlich R, Meloy T. On the extension of fuzzy K-means algorithms for detection of linear clusters[C]. Proceedings of the IEEE Conference on Decision and Contro[C]1.1978:1438-1443.
[142]Swami D K. PAMC:Partitioning around Medoids for Classification[J]. Information Technology Journal,2006,5(6):1102-1105.
[143]AINajjar M, Karlapudi S, Bayoumi M. A compact single-pass architecture for hysteresis thresholding and component labeling, Proceedings[C]. International Conference on Image Processing, ICIP.2010:101-104.
[144]Dalal N, Triggs B, Histograms of oriented Gradients for Human Detection[C]. CVPR, 2005,1:886-893.
[145]Dalal N, Finding People in Images and Videos[J]. Institut National Polytechnique de Grenoble,2006.
[146]Felzenszwalb P, Mcallester D, Ramanan D. A Discriminatively Trained, Multiscale, Deformable Part Model[C]. ICCV,2008:1-8.
[147]Vapnik N, The Nature of Statistical Learning Theory[M]. Springer-Verlag,1995.
[148]Chapelle O, Haffner P, Vapnik V N. Support vector machines for histogram-based image classification[J]. IEEE Transactions on Neural Networks,1999,10(5):1055-1064.
[149]Vapnik, V. SVM method of estimating density, conditional probability, and conditional density[A]. Proceedings-IEEE International Symposium on Circuits and Systems,[C] 2000(2):Ⅱ-749-Ⅱ-752.
[150]Sutton R S, Barto A G. Reinforcement Learning:An Introduction[M]. The MIT Press, Cambridge, MA,1998. Softmax Action Selection.
[151]Shotton J, Winn J, Rother C, Criminisi A. TextonBoost for image understanding: multi-class object recognition and segmentation by jointly modeling texture, layout, and context[J]. International Journal of Computer Vision,2009,81(1):2-23.
[152]Sutton C, McCallum A. Piecewise Training for Undirected Models[C]. Conference on Uncertainty in Artificial Intelligence (UAI).2005.
[153]Yedidia J S, Freeman W T, Weis Y. Understanding Belief Propagation and its Generalizations[J]. Exploring Artifieial Inielligence in the New Millennium,2003:239-236.
© 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 |