基于模型的飞机识别方法研究
摘要
本文的研究得到西北工业大学研究生创业种子基金项目资助(Z20030060)。
世界局势的局部动荡和经济与科技的发展使得飞机识别在当今国防军事以及民用领域的作用日益显著。从航拍及遥感图像中实现飞机的自动识别在近些年来取得了长足的发展，但仍有许多方面需要作更进一步的研究，其中的困难不仅表现在目标的复杂多样性，也有对人类视觉机制认识不足的原因。
目前对三维物体识别的研究方法大体可分为基于视觉计算理论、基于感知组织理论、主动视觉以及基于模型的视觉等类型。本文对飞机识别的研究应用了基于模型的视觉方法——将CAD模型转换为适合视觉应用的二维模型，通过目标的单幅灰度图像与二维模型的识别匹配达到对三维目标识别的目的。
建模型的过程中，首先运用逆向工程测量方法，获得曲面物体上不同截面轮廓线的测量数据点列，接着对测量数据点进行平滑处理，用最小二乘法求解基于数据点列的控制多边形，以非均匀三次B样条曲线拟合截面轮廓曲线；然后利用基于垂距的数据采样算法，对拟合曲线上的数据点进行重新采样，达到优化数据点的分布及减少描述曲线数据量的目的。将重新采样得到的曲线特征点列写成CAD造型软件Pro／E的接口文件格式，在Pro／E完成物体外形轮廓曲面重构和建模。仿真结果表明算法简便、有效。对飞机的识别还提出了一种利用仿射不变量——同底三角形的面积比，进行自动识别的新算法。该方法用多边形近似代替已提取出的飞机边缘轮廓，通过对该特征多边形的识别从而达到对飞机的识别。在对多边形进行识别时，用描述子即多边形的顶点个数以及以最长线段为底的同底三角形面积比向量，来描述多边形的形状。利用建立的三维CAD模型生成全方位姿态模型库来克服飞机姿态不同时飞机部件相互遮挡所造成的图像差异。进而建立姿态匹配特征模板库，通过搜索姿态模板库匹配多边形描述子来识别目标。整个识别过程逐层递进，由简到繁，从而避免了大量的冗余操作。实验表明该算法是高效可行的。
Today, aircraft recognizing become more important in field of national defence and civil aviation due to the development of economy and technology and local confliction. It has gained a great deal of achievement in identifying aircraft automatically from airphoto and remote sensing image. But the deeper study is necessary in many fields. The reason is not only the variety of complex object, but also the insufficiency of knowledge to human vision mechanism.
Presently, there are three methods of 3D object recognition: based on the theory of vision calculate, based on initiative vision and based on model. In this paper,
recognition aircraft is based on model--it is realized through matching the single
image with 2D model.
A new algorithm about adaptive data sampling based on vertical distance has been proposed, furthermore, a modeling method applying this algorithm for complex surface objects has been addressed in this paper. This process is as follows: firstly, the data of different section contour and of section line have been obtained by reverse-engineering; Secondly, Non-Uniform B-Spline approximation algorithm is used to fit the discrete data; Then the data have been optimized and reduced by adopting adaptive sampling of key points of the fitted curve based on vertical distance, sequently the adaptive sampling data is transformed into the format of the .ibl file of the famous 3-D design software Pro/E. therefore we reconstruct the surface and a model is generated; Lastly, The effectiveness of the adopted algorithm and modeling approach are demonstrated by the experiments.
In part of recognition, two problems are studied. First, shape descriptors, which are invariant under affine transformation, are proposed to describe the polygon. Second, a new algorithm for recognizing aircrafts from a single image is presented. The polygon is employed to present the aircraft contour approximately, and the aircraft can be recognized by recognizing the characteristic polygon. Then the shape descriptors are introduced to describe the polygon. The shape descriptors are the
number of the polygon's vertices, and the triangles areas ratio vector of the longest line hemline. The database of the aircraft's each pose is established to overcome the image differences which are produced by the occlusion of the aircraft's components in different pose. The aircraft is recognized by search for the database of the aircraft's each pose. The recognition method is a process from simple to complex, thus many redundancies calculation are avoided. The experiment results show the algorithm is efficient and feasible.
This thesis is supported by Graduation Seed Fund of Northwestern PoIytechnicalUniversity(Z20030060)
世界局势的局部动荡和经济与科技的发展使得飞机识别在当今国防军事以及民用领域的作用日益显著。从航拍及遥感图像中实现飞机的自动识别在近些年来取得了长足的发展，但仍有许多方面需要作更进一步的研究，其中的困难不仅表现在目标的复杂多样性，也有对人类视觉机制认识不足的原因。
目前对三维物体识别的研究方法大体可分为基于视觉计算理论、基于感知组织理论、主动视觉以及基于模型的视觉等类型。本文对飞机识别的研究应用了基于模型的视觉方法——将CAD模型转换为适合视觉应用的二维模型，通过目标的单幅灰度图像与二维模型的识别匹配达到对三维目标识别的目的。
建模型的过程中，首先运用逆向工程测量方法，获得曲面物体上不同截面轮廓线的测量数据点列，接着对测量数据点进行平滑处理，用最小二乘法求解基于数据点列的控制多边形，以非均匀三次B样条曲线拟合截面轮廓曲线；然后利用基于垂距的数据采样算法，对拟合曲线上的数据点进行重新采样，达到优化数据点的分布及减少描述曲线数据量的目的。将重新采样得到的曲线特征点列写成CAD造型软件Pro／E的接口文件格式，在Pro／E完成物体外形轮廓曲面重构和建模。仿真结果表明算法简便、有效。对飞机的识别还提出了一种利用仿射不变量——同底三角形的面积比，进行自动识别的新算法。该方法用多边形近似代替已提取出的飞机边缘轮廓，通过对该特征多边形的识别从而达到对飞机的识别。在对多边形进行识别时，用描述子即多边形的顶点个数以及以最长线段为底的同底三角形面积比向量，来描述多边形的形状。利用建立的三维CAD模型生成全方位姿态模型库来克服飞机姿态不同时飞机部件相互遮挡所造成的图像差异。进而建立姿态匹配特征模板库，通过搜索姿态模板库匹配多边形描述子来识别目标。整个识别过程逐层递进，由简到繁，从而避免了大量的冗余操作。实验表明该算法是高效可行的。
Today, aircraft recognizing become more important in field of national defence and civil aviation due to the development of economy and technology and local confliction. It has gained a great deal of achievement in identifying aircraft automatically from airphoto and remote sensing image. But the deeper study is necessary in many fields. The reason is not only the variety of complex object, but also the insufficiency of knowledge to human vision mechanism.
Presently, there are three methods of 3D object recognition: based on the theory of vision calculate, based on initiative vision and based on model. In this paper,
recognition aircraft is based on model--it is realized through matching the single
image with 2D model.
A new algorithm about adaptive data sampling based on vertical distance has been proposed, furthermore, a modeling method applying this algorithm for complex surface objects has been addressed in this paper. This process is as follows: firstly, the data of different section contour and of section line have been obtained by reverse-engineering; Secondly, Non-Uniform B-Spline approximation algorithm is used to fit the discrete data; Then the data have been optimized and reduced by adopting adaptive sampling of key points of the fitted curve based on vertical distance, sequently the adaptive sampling data is transformed into the format of the .ibl file of the famous 3-D design software Pro/E. therefore we reconstruct the surface and a model is generated; Lastly, The effectiveness of the adopted algorithm and modeling approach are demonstrated by the experiments.
In part of recognition, two problems are studied. First, shape descriptors, which are invariant under affine transformation, are proposed to describe the polygon. Second, a new algorithm for recognizing aircrafts from a single image is presented. The polygon is employed to present the aircraft contour approximately, and the aircraft can be recognized by recognizing the characteristic polygon. Then the shape descriptors are introduced to describe the polygon. The shape descriptors are the
number of the polygon's vertices, and the triangles areas ratio vector of the longest line hemline. The database of the aircraft's each pose is established to overcome the image differences which are produced by the occlusion of the aircraft's components in different pose. The aircraft is recognized by search for the database of the aircraft's each pose. The recognition method is a process from simple to complex, thus many redundancies calculation are avoided. The experiment results show the algorithm is efficient and feasible.
This thesis is supported by Graduation Seed Fund of Northwestern PoIytechnicalUniversity(Z20030060)
引文
[1] Armen F, Affarwal J K. Model-based object recognition in dense-range images——A review. ACM Computing Surveys, 25 (1), 1993, 5-43
[2] Chin R.T, and Dayer C.R. Model—Based Recognition in Robot Vision. ACM Computer Surveys, 18(1), 1986, 67-108
[3] Aloimons J., Weiss I. and Bandopadhay A. Active vision[J]. International Joumal of Computer Vision, 1988, 5(3); 333-356
[4] 马尔．视觉计算理论．刘磊，汪云九译．北京：科学出版社，1987
[5] Herman M. and Kanade T. Incremental reconstruction of 3D scenes from multiple, complex images. Artificial Intelligence, 1986, 30 (3), 289-341
[6] Collins R T. Automated site modeling from multiple aerial images. Computer Vision and Image Understanding, 72(2), 1998, 143-162
[7] Marouani S.; Huertas A. and Medioni G. Model-based aircraft recognition in perspective aerial imagery. IEEE Trans. International Conference on Computer Vision, Nov 21-23, 1995, 371-376
[8] S. Humberto and A. Palomino. Model-based recognition of planar objects using geometric invariants. IEEE Trans. International Conference on Image Processing, v 3, 1996, 603-606
[9] Schmidt J. and Suesse H. 3D-object recognition using model-based invariants. IECON Proceedings (Industrial Electronics Conference), v 4, 1998, 2034-2039
[10] Shariat H. A model-based method for object recognition. IEEE Trans. Int Conf Rob Autom, 1990, 1846-1851
[11] Lamdan Y., Schwartz J. T. and Wolfson H. J. Affine invariant model-based object recognition. IEEE Trans. Robotics and Automation, 6(5), 1990, 578-589
[12] Bose S.K., Biswas K.K and Gupta S.K. Model based object recognition-the role of affine invariants. Artificial Intelligence in Engineering, 10(3), 1996, 227-234
[13] 钟玉琢．机器人视觉技术．北京：国防工业出版社，1994
[14] 苏步青，刘鼎元．计算几何．上海：上海科学技术出版社，1981
[15] 袁奇荪．计算几何造型学基础．北京：航空工业出版社，1987
[16] 朱心雄 等，自由曲线曲面造型技术．北京：科学出版社，2000．
[17] 施法中．计算机辅助几何设计与非均匀有理B样条．北京：高等教育出版社，2001．
[18] 贾云得．机器视觉．北京：科学出版社，2000年．
[19] Hu M.K. Visual pattern recognition by moment invariant. IEEE Trans. Information Theory, 8(2) 1962, 179-187
[20] Teague M R. Image analysis via the general theory of moments. Optical Society of America, 70(8), 1980, 920-930
[21] Dudani S. A. Breeding K J. and McGhee R B. Aircraft identification by moment invariant. IEEE trans. Compute, C-26(1), 1977, 39-46
[22] Prokop R J, Teeves A P. A Survey of moment-based techniques for unconcluded object representation and recognition CVGIP, 9(2), 1992, 438-460
[23] 王国瑾等．计算机辅助几何设计．北京：高等教育出版社施普林格出版社，2000．
[24] K. Arbter and W. E. Synder. Application of affine invariant fourier descriptors to recognition of 3D objects, IEEE Trans. on Pattern Analysis and Machine Intelligence, 12(7), 1990
[25] Cohen. Fernand S, Huang zhaohui and zheng wei. Invariant matching and identification of curves using B-splines curve representation. IEEE Trans. Image Processing, 4(1), 1995, 1-10.
[26] Marouani S., Huertas A. and Medioni G. Model-based aircraft recognition in perspective aerial imagery. IEEE Trans. International Conference on Computer Vision, 1995, 371-376
[27] Somaie A.A, Badr. A. and Salah T. Aircraft image recognition using back-propagation. CIE International Conference of Radar Proceedings, 2001, 498-501
[28] Shen-Chi Tien, Tsomg-Lin Chia and Yibin Lu. Using cross-ratios to model curve data for aircraft recognition. Pattern Recognition Letters 24, 2003, 2047-2060.
[29] Hsu Y.N., Arsensult H.H., April G. Rotational Invariant Digital Pattern Recognition Using Circular Harmonic Expansion. Applied Optics, 21(7), 1982, 4012-4015
[30] Mokhtarian F. Silhouette-based occluded object recognition through curvature scale space. Machine Vision and Applications, 13(10), 1997, 87-97
[31] 徐树公，桑农．一种基于仿射不变特征的飞机识别方案．华中理工大学学报23(10)，1995，82-86
[32] 曲仕茹，史忠科．一种空中交通图象特征匹配方法．飞行力学，18(2)，2000，81-84
[33] 张艳宁，郑江滨．基于支撑矢量机的遥感图像目标识别．西北工业大学学报，20(4)，2002，536-539
[34] 杨华，肖志河．等以相关系数为特征量的飞机目标识别法．清华大学学报(自然科学版，) 041(007)，2001，29-31
[35] 杨华，肖志河．等基于径向基函数神经网络的飞机目标识别法．清华大学学报(自然科学版)，041(007)，2001，36-38
[36] 陈莹，邱锡钧．协同学理论方法在飞机识别中的应用．上海大学学报(自然科学版)8(5)，2002，103-106
[37] 陈昕，向健勇．不变性理论用于空中目标的识别．红外与毫米波学报．1997，16(1)．39-44
[38] 李江雄．复杂曲面反求工程CAD建模技术研究[D]．杭州：浙江大学，1998．
[39] 柯映林．反求工程CAD建模技术研究．计算机辅助设计与图形学学报，13(6)，2001，570-575．
[40] Chen Dong-Fan. Reconstruction Technique in Reverse Engineering. IEEE International Conference on Industrial Technology, 12 (3), 1996, 35-41
[41] 王英惠．逆向工程中自由曲面的自适应采样与建模．小型微型计算机系统，23(11)，2001，1406-1408．
[42] Les A. Piegl. Reducing control points in surface interpolation. IEEE Computer Graphics and Applications, 15 (9), 2000, 70-74
[43] 卡斯尔曼(Castleman, K. R.)著，朱志刚，林学阁，石定机等译．数字图像处理，北京：电子工业出版社，2002
[44] Z.W. Yang, F.S. Cohen. Image Registration and Object Recognition Using Affine Invariants and Convex Hulls. IEEE Trans. Image Processing, 8(7), 1999, 934-946
[45] Lowe D G. Three-dimensional object recognition from single two-dimensional images. Artificial Intelligence, 31(3), 1987, 355-395
[46] 成瑜．从一幅透视投影线图识别三维物体．电子学报，V23(4)，1995，65-69
[47] 郭雷．利用单个透视投影识别空间多变形．计算机学报，1991，858-864
[48] Jan Flusser. Affine Invariants of Convex Polygons. IEEE Trans. Image Processing, 11(9), 2002, 1117-1118
[49] 席学强，王润生．遥感图像三维目标多视点建模识别方法．计算机辅助设计与图形学学报，14(10)，2002，945-949
[50] Tiller W. Rational B-Splines for Curves and Surfaces Representation. IEEE Trans. CG&A, September 1983, 61-69
[51] 高满屯，曲仕茹，李西琴．计算机视觉研究中的投影理论和方法．西安：西北工业大学出版社，1998
[52] 周培德．计算几何——算法分析与设计．北京：清华大学出版社，2000
[53] 柳迎春．Pro／ENGINEER 2001曲面设计．北京：北京大学出版社，2002
[54] 张沛颀，裴建昌，黄圣杰．Pro／ENGINEER2001高级攻略．北京：人民邮电出版社，2002
[55] 柳迎春．Pro／ENGINEER 2001中文版自由曲面与行为建模．北京：清华大学出版社，2002
[56] 孙即详，王晓华．模式识别中的特征提取与计算机视觉不变量，北京：国防工业出版社，2001
[57] Hmam H., Kim J. Aircraft recognition and pose estimation. The Intemational Society for Optical Engineering, v 4067 (Ⅲ), 2000, 1198-1209
[2] Chin R.T, and Dayer C.R. Model—Based Recognition in Robot Vision. ACM Computer Surveys, 18(1), 1986, 67-108
[3] Aloimons J., Weiss I. and Bandopadhay A. Active vision[J]. International Joumal of Computer Vision, 1988, 5(3); 333-356
[4] 马尔．视觉计算理论．刘磊，汪云九译．北京：科学出版社，1987
[5] Herman M. and Kanade T. Incremental reconstruction of 3D scenes from multiple, complex images. Artificial Intelligence, 1986, 30 (3), 289-341
[6] Collins R T. Automated site modeling from multiple aerial images. Computer Vision and Image Understanding, 72(2), 1998, 143-162
[7] Marouani S.; Huertas A. and Medioni G. Model-based aircraft recognition in perspective aerial imagery. IEEE Trans. International Conference on Computer Vision, Nov 21-23, 1995, 371-376
[8] S. Humberto and A. Palomino. Model-based recognition of planar objects using geometric invariants. IEEE Trans. International Conference on Image Processing, v 3, 1996, 603-606
[9] Schmidt J. and Suesse H. 3D-object recognition using model-based invariants. IECON Proceedings (Industrial Electronics Conference), v 4, 1998, 2034-2039
[10] Shariat H. A model-based method for object recognition. IEEE Trans. Int Conf Rob Autom, 1990, 1846-1851
[11] Lamdan Y., Schwartz J. T. and Wolfson H. J. Affine invariant model-based object recognition. IEEE Trans. Robotics and Automation, 6(5), 1990, 578-589
[12] Bose S.K., Biswas K.K and Gupta S.K. Model based object recognition-the role of affine invariants. Artificial Intelligence in Engineering, 10(3), 1996, 227-234
[13] 钟玉琢．机器人视觉技术．北京：国防工业出版社，1994
[14] 苏步青，刘鼎元．计算几何．上海：上海科学技术出版社，1981
[15] 袁奇荪．计算几何造型学基础．北京：航空工业出版社，1987
[16] 朱心雄 等，自由曲线曲面造型技术．北京：科学出版社，2000．
[17] 施法中．计算机辅助几何设计与非均匀有理B样条．北京：高等教育出版社，2001．
[18] 贾云得．机器视觉．北京：科学出版社，2000年．
[19] Hu M.K. Visual pattern recognition by moment invariant. IEEE Trans. Information Theory, 8(2) 1962, 179-187
[20] Teague M R. Image analysis via the general theory of moments. Optical Society of America, 70(8), 1980, 920-930
[21] Dudani S. A. Breeding K J. and McGhee R B. Aircraft identification by moment invariant. IEEE trans. Compute, C-26(1), 1977, 39-46
[22] Prokop R J, Teeves A P. A Survey of moment-based techniques for unconcluded object representation and recognition CVGIP, 9(2), 1992, 438-460
[23] 王国瑾等．计算机辅助几何设计．北京：高等教育出版社施普林格出版社，2000．
[24] K. Arbter and W. E. Synder. Application of affine invariant fourier descriptors to recognition of 3D objects, IEEE Trans. on Pattern Analysis and Machine Intelligence, 12(7), 1990
[25] Cohen. Fernand S, Huang zhaohui and zheng wei. Invariant matching and identification of curves using B-splines curve representation. IEEE Trans. Image Processing, 4(1), 1995, 1-10.
[26] Marouani S., Huertas A. and Medioni G. Model-based aircraft recognition in perspective aerial imagery. IEEE Trans. International Conference on Computer Vision, 1995, 371-376
[27] Somaie A.A, Badr. A. and Salah T. Aircraft image recognition using back-propagation. CIE International Conference of Radar Proceedings, 2001, 498-501
[28] Shen-Chi Tien, Tsomg-Lin Chia and Yibin Lu. Using cross-ratios to model curve data for aircraft recognition. Pattern Recognition Letters 24, 2003, 2047-2060.
[29] Hsu Y.N., Arsensult H.H., April G. Rotational Invariant Digital Pattern Recognition Using Circular Harmonic Expansion. Applied Optics, 21(7), 1982, 4012-4015
[30] Mokhtarian F. Silhouette-based occluded object recognition through curvature scale space. Machine Vision and Applications, 13(10), 1997, 87-97
[31] 徐树公，桑农．一种基于仿射不变特征的飞机识别方案．华中理工大学学报23(10)，1995，82-86
[32] 曲仕茹，史忠科．一种空中交通图象特征匹配方法．飞行力学，18(2)，2000，81-84
[33] 张艳宁，郑江滨．基于支撑矢量机的遥感图像目标识别．西北工业大学学报，20(4)，2002，536-539
[34] 杨华，肖志河．等以相关系数为特征量的飞机目标识别法．清华大学学报(自然科学版，) 041(007)，2001，29-31
[35] 杨华，肖志河．等基于径向基函数神经网络的飞机目标识别法．清华大学学报(自然科学版)，041(007)，2001，36-38
[36] 陈莹，邱锡钧．协同学理论方法在飞机识别中的应用．上海大学学报(自然科学版)8(5)，2002，103-106
[37] 陈昕，向健勇．不变性理论用于空中目标的识别．红外与毫米波学报．1997，16(1)．39-44
[38] 李江雄．复杂曲面反求工程CAD建模技术研究[D]．杭州：浙江大学，1998．
[39] 柯映林．反求工程CAD建模技术研究．计算机辅助设计与图形学学报，13(6)，2001，570-575．
[40] Chen Dong-Fan. Reconstruction Technique in Reverse Engineering. IEEE International Conference on Industrial Technology, 12 (3), 1996, 35-41
[41] 王英惠．逆向工程中自由曲面的自适应采样与建模．小型微型计算机系统，23(11)，2001，1406-1408．
[42] Les A. Piegl. Reducing control points in surface interpolation. IEEE Computer Graphics and Applications, 15 (9), 2000, 70-74
[43] 卡斯尔曼(Castleman, K. R.)著，朱志刚，林学阁，石定机等译．数字图像处理，北京：电子工业出版社，2002
[44] Z.W. Yang, F.S. Cohen. Image Registration and Object Recognition Using Affine Invariants and Convex Hulls. IEEE Trans. Image Processing, 8(7), 1999, 934-946
[45] Lowe D G. Three-dimensional object recognition from single two-dimensional images. Artificial Intelligence, 31(3), 1987, 355-395
[46] 成瑜．从一幅透视投影线图识别三维物体．电子学报，V23(4)，1995，65-69
[47] 郭雷．利用单个透视投影识别空间多变形．计算机学报，1991，858-864
[48] Jan Flusser. Affine Invariants of Convex Polygons. IEEE Trans. Image Processing, 11(9), 2002, 1117-1118
[49] 席学强，王润生．遥感图像三维目标多视点建模识别方法．计算机辅助设计与图形学学报，14(10)，2002，945-949
[50] Tiller W. Rational B-Splines for Curves and Surfaces Representation. IEEE Trans. CG&A, September 1983, 61-69
[51] 高满屯，曲仕茹，李西琴．计算机视觉研究中的投影理论和方法．西安：西北工业大学出版社，1998
[52] 周培德．计算几何——算法分析与设计．北京：清华大学出版社，2000
[53] 柳迎春．Pro／ENGINEER 2001曲面设计．北京：北京大学出版社，2002
[54] 张沛颀，裴建昌，黄圣杰．Pro／ENGINEER2001高级攻略．北京：人民邮电出版社，2002
[55] 柳迎春．Pro／ENGINEER 2001中文版自由曲面与行为建模．北京：清华大学出版社，2002
[56] 孙即详，王晓华．模式识别中的特征提取与计算机视觉不变量，北京：国防工业出版社，2001
[57] Hmam H., Kim J. Aircraft recognition and pose estimation. The Intemational Society for Optical Engineering, v 4067 (Ⅲ), 2000, 1198-1209
© 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 |