图象目标识别技术的研究与应用
|
摘要
目标识别在当今军事国防以及民用领域的作用日益显著，从航拍及遥感图象中实现目标的自动识别在近些年来取得了长足的发展，但是仍然没有一种可以普遍适用的方法。这其中的困难不仅体现在目标场景的复杂性本身，同时也是由于对人类视觉机制认识上的不足。
目前常用的目标识别算法有两种：一种是传统的由下而上的数据驱动型，另一种是由上而下的知识(假设)驱动型。前者常用于飞机、工件等团块目标的识别中；而后者是在复杂场景中将桥梁、道路、机场跑道等目标识别出来最为常用的识别方法。文章中对后一种方法做了较为详细的研究。
知识驱动的目标识别方法的实现有很多种，其中图象分割中所涉及到的区域分割和线状特征提取技术是我们的研究的基础，在文章中对这两种方法中的所涉及的具体知识做了详细的介绍。
知识的表示与利用在我们在自上而下的目标识别方式中起着十分关键的作用。文章中对知识的概念以及知识的表示方法给出了详细的介绍，并结合对国内外相关文献的研究，给出了一套目标识别的思路与流程。
在前面工作的基础上，文章针对常见的人工目标——桥梁、机场跑道，给出了实际的实现算法。机场跑道的实现算法主要结合了线状特征提取的思路，桥梁识别的算法则主要结合了区域特征分析的方法。这两种方法在结合前人研究的基础上，均有自己的独到之处。通过大量实验验证，算法的稳定性和实时性都非常好。其中根据机场跑道的识别算法文中还设计了一个简单的仿真目标跟踪系统。
Target recognition is valued in military affairs. Although the researches in automated target detection from aerial and remote sensing imagery have made great progress in recent years, there is still no commonly accepted method. The difficulties come not only from the complexity of scene itself, but also from the weak knowledge about the principle of human visual perception.
There are two basic target recognition algorithms. One of them is processed from bottom to top, which is called data-driving method. This traditional method is most often used in object as airplane, workpiece, etc. The other is processed from top to bottom, which is called knowledge-driving method. This one is always used in extracting road, bridge and runway from complex scene. This paper presents adequate research on the later one.
Image segmentation techniques involving region segmentation and line feature extraction which are the foundation of our research are introduced. And the other concerning methods have been referred and exemplified.
It has been well recognized that the expression and the application of knowledge play a key role in target recognition. The definition of the knowledge and several expression methods of the knowledge are introduced. On the basis of it, this paper gives a set of flow on how to extract target from complex scene based on the knowledge.
At the final of this paper, two algorithms on man-made object recognition are present. Algorithm on runway recognition is based on linear feature extraction and the algorithm on bridge recognition is focused on region character analysis. All of them are robust and realtime. And a simulation tracking system is designed based on runway recognition algorithm.
目前常用的目标识别算法有两种：一种是传统的由下而上的数据驱动型，另一种是由上而下的知识(假设)驱动型。前者常用于飞机、工件等团块目标的识别中；而后者是在复杂场景中将桥梁、道路、机场跑道等目标识别出来最为常用的识别方法。文章中对后一种方法做了较为详细的研究。
知识驱动的目标识别方法的实现有很多种，其中图象分割中所涉及到的区域分割和线状特征提取技术是我们的研究的基础，在文章中对这两种方法中的所涉及的具体知识做了详细的介绍。
知识的表示与利用在我们在自上而下的目标识别方式中起着十分关键的作用。文章中对知识的概念以及知识的表示方法给出了详细的介绍，并结合对国内外相关文献的研究，给出了一套目标识别的思路与流程。
在前面工作的基础上，文章针对常见的人工目标——桥梁、机场跑道，给出了实际的实现算法。机场跑道的实现算法主要结合了线状特征提取的思路，桥梁识别的算法则主要结合了区域特征分析的方法。这两种方法在结合前人研究的基础上，均有自己的独到之处。通过大量实验验证，算法的稳定性和实时性都非常好。其中根据机场跑道的识别算法文中还设计了一个简单的仿真目标跟踪系统。
Target recognition is valued in military affairs. Although the researches in automated target detection from aerial and remote sensing imagery have made great progress in recent years, there is still no commonly accepted method. The difficulties come not only from the complexity of scene itself, but also from the weak knowledge about the principle of human visual perception.
There are two basic target recognition algorithms. One of them is processed from bottom to top, which is called data-driving method. This traditional method is most often used in object as airplane, workpiece, etc. The other is processed from top to bottom, which is called knowledge-driving method. This one is always used in extracting road, bridge and runway from complex scene. This paper presents adequate research on the later one.
Image segmentation techniques involving region segmentation and line feature extraction which are the foundation of our research are introduced. And the other concerning methods have been referred and exemplified.
It has been well recognized that the expression and the application of knowledge play a key role in target recognition. The definition of the knowledge and several expression methods of the knowledge are introduced. On the basis of it, this paper gives a set of flow on how to extract target from complex scene based on the knowledge.
At the final of this paper, two algorithms on man-made object recognition are present. Algorithm on runway recognition is based on linear feature extraction and the algorithm on bridge recognition is focused on region character analysis. All of them are robust and realtime. And a simulation tracking system is designed based on runway recognition algorithm.
引文
[1] 石纯一，黄昌宁等，人工智能原理，清华大学出版社，1993
[2] 王永庆，人工智能 原理·方法·应用，西安交通大学出版社，1994
[3] 容观澳，计算机图象处理，清华大学出版社，2000
[4] 章毓晋，图象分割，科学出版社，2001
[5] 崔屹，图象处理与分析·数学形态学方法及应用，科学出版社，2000
[6] 文贡坚，航空图象中道路和建筑物的自动提取技术，国防科学技术大学博士论文，2000
[7] 韩军伟，景物边缘提取技术的研究与应用，西北工业大学硕士论文，2001
[8] 杨益军，单色遥感图象中建筑物检测方法研究，西北工业大学博士论文，2000
[9] R. Nevatia, K. Babu, Linear Feature Extraction and Description, Computer Graphics and Image Processing, 13, 1980, 257-269
[10] A. Huertas, W. Cole, and R. Nevatia, Detecting Runways in Complex Airport Scenes, CVGIP 51, 1990, 107-145
[11] Canny J F., A Computational Approach to Edge Detection, IEEE Trans on PAMI, 1986, 8(6):679-698
[12] 孙琪，曹治国，张天序，基于框架红外桥梁目标识别，华中科技大学学报，Vol．29，No．4，Apr．2001
[13] A. Mansouri, S. Malowany, and M. Levine, Line Detection in Digital Pictures: A Hypothesis Prediction/Verification Paradigm, CVGIP, 40, 1987, 95-114
[14] A. Huertas, R. Nevatia, Detecting Buildings in Aerial Images, CVGIP, 41, 1988,131-152
[15] Hevenor, et al., Automated Extraction of Airport Runway Patterns from Radar Imagery, United States Patent, 5335298, August 2, 1994
[16] A. Scher, M. Shneier, and A. Rosenfeld, A Method for Finding Pairs of Antiparallel Straight Lines, IEEE Trans on PAMI, Vol.4, No.3, May 1982, 316-323
[17] R. O. Duda, P. E. hart, Use of Hough Transformation to Detect Lines and Curves in Pictures, Communi ACM, 15, 1982, 11-15
[18] J. Sklansky, On the Hough Techniques for Curve Detection, IEEE Trans on Compute, 27, No.10, 1978, 923-926
[19] 叶斌，彭嘉雄，基于结构特征的军用机场识别与理解，华中科技大学学报，Vol．29，No．3，Mar．2001，39-42
[20] D. C. Baker, S. S. Hwang, and J. K. Aggarwal, Detection and Segmentation of Man-made Objects in Outdoor Scenes: Concrete Bridges, J. Opt. Soc. Am.A, Vol. 6, No.6, June 1989, 938-950
[21] Todd Law, Hidenori Itoh, and Hirohisa Seki, Image Filtering, Edge Detection, and Edge Tracing Using Fuzzy Reasoning, IEEE Trans on PAMI, Vol. 18, No.5, May 1996, 481-491
[22] 徐胜荣，徐凡等，基于知识的桥梁目标识别方法研究，模式识别与人工智能，Vol．5，No．2，June．1992，123-128
[23] 徐胜荣，李忠兴，自然景物中桥梁目标识别方法的研究，浙江大学学报(自然科学版发)，No．3，Vol．29，May 1995，275-281
[24] Meir Barzohar, David B. Cooper, Automatic Finding of Main Roads in Aerial Images by Using Geometric-Stochastic Models and Estimation, IEEE Trans on PAMI, Vol.18, No.7, July 1996, 707-720
[25] Sita. D., Target detection in SLAR images. Proc. SPIE, 1994, 2232:291-299
[26] K. S. Shanmugan, Craig Paul, A Fast Edge Thinning Operator, IEEE Trans on SMC, Vol.12, No.4, July/August 1982, 567-569
[27] Michael O. Shneier, Extracting Linear Features from Images Using Pyramids, IEEE Trans on SMC, Vol.12, No.4, July/August 1982, 569-572
[28] 袁在华，杨树谦，桥梁红外图象的自动识别跟踪方法探讨，红外与激光工程，Vol．27，No．1，Feb．1998，4-8
[29] 沈丽琴，胡国栋，戚飞虎，基于知识的线状目标边缘提取与识别定位，红外与毫米波学报，Vol．14，No．1，Feb．1995，59-66
[30] Sankar K. Pal, Nikhil R. Pal, Segmentation Based on Measures of Contrast, Homogeneity, and Region Size, IEEE Trans on SMC, Vol. 17, No.5, Sep/Oct 1987, 857-868
[31] David M. Mckeown, JR., Wilson A. Harvey, Rule-Based Interpretation of Aerial Imagery, 1EEE Trans on PAMI, Vol.7, No.5, Sep. 1985, 570-585
[32] John Canning, A Minimum Description Length Model for Recognizing Object with Variance Appearances, IEEE Trans on PAMI, Vol. 16, No. 10, 1994, 1032-
1036
[33] Y. T. Zhou, V. Venkateswar, and R. Chellappa, Edge Detection and Linear Feature Extraction Using a 2-D Random Field Model, IEEE Trans on PAMI, Vol. 11, No.l, Jan.1989
[34] 左震，张天序，汪国有，远距红外图象中桥梁目标识别方法研究，电子学报，Vol．26，No．11，Nov，1998，6-9
[35] 席学强，王润生，一个针对遥感图象特定目标的自动识别系统，遥感技术与应用，Vol．15，No．3，Sep．2000，179-183
[36] I. Pitas, A. N. Ventsanopoulos, Edge Detectors Based on Nonlinear Filters, IEEE Trans on PAMI, Vol.8, No.4, July 1986, 538-550
[37] V. Venkateswar, R. Chellappa, Extraction of Straight Lines in Aerial Images, IEEE Trans on PAMI, Vol.14, No.11, Nov 1992
[38] J. B. Burns, A. R. Hanson, and E. M. Roseman, Extraction Straight Lines, IEEE Trans on PAMI-8, 1986, 425-445
[39] 邢延，张天序，复杂背景下基于知识的目标识别算法研究，模式识别与人工智能，Vol．8，No．3，Sep．1995，237-242
[40] 王伟明，徐胜荣，姚庆栋等，一种使用黑板模型实观的图象分割策略及在桥梁目标识别中的应用，计算机学报，Vol．18，No．2，Feb．1995，127-134
[41] Randal C. Nelson, Finding Line Segments by Stick Growing, IEEE Trans on PAMI, Vol.16, No.5, May 1994, 519-523
[42] A. M. Nazif, Martin D. L, Low Level Image Segmentation: An Expert System, IEEE Trans on PAMI, Vol.6, No.5, Sep.1984, 555-577
[43] G. S. Zabele, J. Koplowitz, On Improving Line Detection in Noisy Images, Computer Graphics and Image Processing, 15, 1981, 130-135
[44] M. R. Rezaee, Pieter M. J. van der Zwet, et al., A Multiresolution Image Segmentation Technique Based on Pyramidal Segmentation and Fuzzy Clustering, IEEE Trans on Image Processing, Vol.9, No.7, July 2000, 1238-1247
[45] L. T. Watson, K. Arvind, R. W. Ehrich, R. M. Haralick, Extraction of Lines and Regions from Gray Tone Line Drawing Image, Pattern Recognition, 17(5), 1984, 493-507
[46] M. Mirmehdi, Phil L. Palmer, J. Kittler, and H. Dabis, Feedback Control Strategies for Object Recognition, IEEE Trans on Image Processing, Vol.8,
No.8, August 1999, 1084-1101
[47] B. Chanda, M. K. Kundu, and Y. Vani Padmaja, A Multi-Scale Morphologic Edge Detector, Pattern Recognition, Vol.31, No. 10, 1998, 1469-1478
[48] M. A. Brown, K. T. Blackwell, et al., Multi-Scale Edge Detection and Binding an Integrated Approach, Pattern Recognition, Vol.31, No.10, 1998, 1479-1490
[49] ZuWhan Kim, Andres Huertas, and Ramakant Nevatia, Automatic Description of Complex Buildings with Multiple Images, Proceedings of the 5th IEEE Workshop on Applications of Computer Vision, 2000, 155-162
[50] R. A. Mclaughlin, M. D. Alder, The Hough Transform Versus the Upwrite, IEEE Trans on PAMI, Vol.20, No.4, April 1998, 396-400
[51] M. A. Fischler, J. M Tenenbaum, and H. C. Wolf, Detection of Road and Linear Features in Low Resolution Aerial Imagery, CVGIP, Vol. 15, 1981,201-223
[52] A. Martelli, An Application of Heuristic Search Methods to Edge and Contour Detection, Comm ACM, Vol. 19, 1976, 73-83
[53] Narendra Ahujo, A Transform for Multiscale Image Segmentation by Integrated Edge and Region Detection, IEEE Trans on PAMI, Vol.18, No.12, Dec. 1996, 1211-1235
[54] 赵锋，赵荣椿，分裂——合并方法在图象分割、目标提取中的应用，西北工业大学学报，Vol．18，No．1，Feb．2000，116-120
[55] 汤志伟，王运锋等，合成孔径雷达图象中桥梁形状的目标识别，电波科学学报，Vol．15，No．1，Mar．2000，41-44
[56] 郑云慧，张桂林，吴光焰，一个基于知识的目标跟踪信息处理系统，华中理工大学学报，Vol．24，No．2，Feb．1996，46-48
[57] 周凌翔，顾伟康，最佳边缘检测的准则与算子，模式识别与人工智能，Vol．11，No．1，March 1998，54-61
[58] 孙斌，航空图片的自动识别，浙江大学学报(自然科学版)，Vol，32，No．4，July 1998，399-405
[2] 王永庆，人工智能 原理·方法·应用，西安交通大学出版社，1994
[3] 容观澳，计算机图象处理，清华大学出版社，2000
[4] 章毓晋，图象分割，科学出版社，2001
[5] 崔屹，图象处理与分析·数学形态学方法及应用，科学出版社，2000
[6] 文贡坚，航空图象中道路和建筑物的自动提取技术，国防科学技术大学博士论文，2000
[7] 韩军伟，景物边缘提取技术的研究与应用，西北工业大学硕士论文，2001
[8] 杨益军，单色遥感图象中建筑物检测方法研究，西北工业大学博士论文，2000
[9] R. Nevatia, K. Babu, Linear Feature Extraction and Description, Computer Graphics and Image Processing, 13, 1980, 257-269
[10] A. Huertas, W. Cole, and R. Nevatia, Detecting Runways in Complex Airport Scenes, CVGIP 51, 1990, 107-145
[11] Canny J F., A Computational Approach to Edge Detection, IEEE Trans on PAMI, 1986, 8(6):679-698
[12] 孙琪，曹治国，张天序，基于框架红外桥梁目标识别，华中科技大学学报，Vol．29，No．4，Apr．2001
[13] A. Mansouri, S. Malowany, and M. Levine, Line Detection in Digital Pictures: A Hypothesis Prediction/Verification Paradigm, CVGIP, 40, 1987, 95-114
[14] A. Huertas, R. Nevatia, Detecting Buildings in Aerial Images, CVGIP, 41, 1988,131-152
[15] Hevenor, et al., Automated Extraction of Airport Runway Patterns from Radar Imagery, United States Patent, 5335298, August 2, 1994
[16] A. Scher, M. Shneier, and A. Rosenfeld, A Method for Finding Pairs of Antiparallel Straight Lines, IEEE Trans on PAMI, Vol.4, No.3, May 1982, 316-323
[17] R. O. Duda, P. E. hart, Use of Hough Transformation to Detect Lines and Curves in Pictures, Communi ACM, 15, 1982, 11-15
[18] J. Sklansky, On the Hough Techniques for Curve Detection, IEEE Trans on Compute, 27, No.10, 1978, 923-926
[19] 叶斌，彭嘉雄，基于结构特征的军用机场识别与理解，华中科技大学学报，Vol．29，No．3，Mar．2001，39-42
[20] D. C. Baker, S. S. Hwang, and J. K. Aggarwal, Detection and Segmentation of Man-made Objects in Outdoor Scenes: Concrete Bridges, J. Opt. Soc. Am.A, Vol. 6, No.6, June 1989, 938-950
[21] Todd Law, Hidenori Itoh, and Hirohisa Seki, Image Filtering, Edge Detection, and Edge Tracing Using Fuzzy Reasoning, IEEE Trans on PAMI, Vol. 18, No.5, May 1996, 481-491
[22] 徐胜荣，徐凡等，基于知识的桥梁目标识别方法研究，模式识别与人工智能，Vol．5，No．2，June．1992，123-128
[23] 徐胜荣，李忠兴，自然景物中桥梁目标识别方法的研究，浙江大学学报(自然科学版发)，No．3，Vol．29，May 1995，275-281
[24] Meir Barzohar, David B. Cooper, Automatic Finding of Main Roads in Aerial Images by Using Geometric-Stochastic Models and Estimation, IEEE Trans on PAMI, Vol.18, No.7, July 1996, 707-720
[25] Sita. D., Target detection in SLAR images. Proc. SPIE, 1994, 2232:291-299
[26] K. S. Shanmugan, Craig Paul, A Fast Edge Thinning Operator, IEEE Trans on SMC, Vol.12, No.4, July/August 1982, 567-569
[27] Michael O. Shneier, Extracting Linear Features from Images Using Pyramids, IEEE Trans on SMC, Vol.12, No.4, July/August 1982, 569-572
[28] 袁在华，杨树谦，桥梁红外图象的自动识别跟踪方法探讨，红外与激光工程，Vol．27，No．1，Feb．1998，4-8
[29] 沈丽琴，胡国栋，戚飞虎，基于知识的线状目标边缘提取与识别定位，红外与毫米波学报，Vol．14，No．1，Feb．1995，59-66
[30] Sankar K. Pal, Nikhil R. Pal, Segmentation Based on Measures of Contrast, Homogeneity, and Region Size, IEEE Trans on SMC, Vol. 17, No.5, Sep/Oct 1987, 857-868
[31] David M. Mckeown, JR., Wilson A. Harvey, Rule-Based Interpretation of Aerial Imagery, 1EEE Trans on PAMI, Vol.7, No.5, Sep. 1985, 570-585
[32] John Canning, A Minimum Description Length Model for Recognizing Object with Variance Appearances, IEEE Trans on PAMI, Vol. 16, No. 10, 1994, 1032-
1036
[33] Y. T. Zhou, V. Venkateswar, and R. Chellappa, Edge Detection and Linear Feature Extraction Using a 2-D Random Field Model, IEEE Trans on PAMI, Vol. 11, No.l, Jan.1989
[34] 左震，张天序，汪国有，远距红外图象中桥梁目标识别方法研究，电子学报，Vol．26，No．11，Nov，1998，6-9
[35] 席学强，王润生，一个针对遥感图象特定目标的自动识别系统，遥感技术与应用，Vol．15，No．3，Sep．2000，179-183
[36] I. Pitas, A. N. Ventsanopoulos, Edge Detectors Based on Nonlinear Filters, IEEE Trans on PAMI, Vol.8, No.4, July 1986, 538-550
[37] V. Venkateswar, R. Chellappa, Extraction of Straight Lines in Aerial Images, IEEE Trans on PAMI, Vol.14, No.11, Nov 1992
[38] J. B. Burns, A. R. Hanson, and E. M. Roseman, Extraction Straight Lines, IEEE Trans on PAMI-8, 1986, 425-445
[39] 邢延，张天序，复杂背景下基于知识的目标识别算法研究，模式识别与人工智能，Vol．8，No．3，Sep．1995，237-242
[40] 王伟明，徐胜荣，姚庆栋等，一种使用黑板模型实观的图象分割策略及在桥梁目标识别中的应用，计算机学报，Vol．18，No．2，Feb．1995，127-134
[41] Randal C. Nelson, Finding Line Segments by Stick Growing, IEEE Trans on PAMI, Vol.16, No.5, May 1994, 519-523
[42] A. M. Nazif, Martin D. L, Low Level Image Segmentation: An Expert System, IEEE Trans on PAMI, Vol.6, No.5, Sep.1984, 555-577
[43] G. S. Zabele, J. Koplowitz, On Improving Line Detection in Noisy Images, Computer Graphics and Image Processing, 15, 1981, 130-135
[44] M. R. Rezaee, Pieter M. J. van der Zwet, et al., A Multiresolution Image Segmentation Technique Based on Pyramidal Segmentation and Fuzzy Clustering, IEEE Trans on Image Processing, Vol.9, No.7, July 2000, 1238-1247
[45] L. T. Watson, K. Arvind, R. W. Ehrich, R. M. Haralick, Extraction of Lines and Regions from Gray Tone Line Drawing Image, Pattern Recognition, 17(5), 1984, 493-507
[46] M. Mirmehdi, Phil L. Palmer, J. Kittler, and H. Dabis, Feedback Control Strategies for Object Recognition, IEEE Trans on Image Processing, Vol.8,
No.8, August 1999, 1084-1101
[47] B. Chanda, M. K. Kundu, and Y. Vani Padmaja, A Multi-Scale Morphologic Edge Detector, Pattern Recognition, Vol.31, No. 10, 1998, 1469-1478
[48] M. A. Brown, K. T. Blackwell, et al., Multi-Scale Edge Detection and Binding an Integrated Approach, Pattern Recognition, Vol.31, No.10, 1998, 1479-1490
[49] ZuWhan Kim, Andres Huertas, and Ramakant Nevatia, Automatic Description of Complex Buildings with Multiple Images, Proceedings of the 5th IEEE Workshop on Applications of Computer Vision, 2000, 155-162
[50] R. A. Mclaughlin, M. D. Alder, The Hough Transform Versus the Upwrite, IEEE Trans on PAMI, Vol.20, No.4, April 1998, 396-400
[51] M. A. Fischler, J. M Tenenbaum, and H. C. Wolf, Detection of Road and Linear Features in Low Resolution Aerial Imagery, CVGIP, Vol. 15, 1981,201-223
[52] A. Martelli, An Application of Heuristic Search Methods to Edge and Contour Detection, Comm ACM, Vol. 19, 1976, 73-83
[53] Narendra Ahujo, A Transform for Multiscale Image Segmentation by Integrated Edge and Region Detection, IEEE Trans on PAMI, Vol.18, No.12, Dec. 1996, 1211-1235
[54] 赵锋，赵荣椿，分裂——合并方法在图象分割、目标提取中的应用，西北工业大学学报，Vol．18，No．1，Feb．2000，116-120
[55] 汤志伟，王运锋等，合成孔径雷达图象中桥梁形状的目标识别，电波科学学报，Vol．15，No．1，Mar．2000，41-44
[56] 郑云慧，张桂林，吴光焰，一个基于知识的目标跟踪信息处理系统，华中理工大学学报，Vol．24，No．2，Feb．1996，46-48
[57] 周凌翔，顾伟康，最佳边缘检测的准则与算子，模式识别与人工智能，Vol．11，No．1，March 1998，54-61
[58] 孙斌，航空图片的自动识别，浙江大学学报(自然科学版)，Vol，32，No．4，July 1998，399-405