采用投影轮廓特征的激光雷达快速目标识别

郭裕兰; 鲁敏; 谭志国; 万建伟

doi:doi:10.3788/cjl201239.0209003

中国激光, 2012, 39 (2): 0209003, 网络出版: 2012-01-12

采用投影轮廓特征的激光雷达快速目标识别

Fast Target Recognition in Ladar Using Projection Contour Features

论文大纲

郭裕兰 ^*鲁敏谭志国万建伟

作者单位

国防科学技术大学电子科学与工程学院，湖南长沙 410073

激光光学激光雷达目标识别投影轮廓特征迭代最近点 laser optics ladar target recognition projection contour feature iterative closest point

摘要

激光雷达可以获得目标的三维形状信息，已成为目标识别领域新的研究热点。针对传统匹配识别算法计算量大的问题，提出了一种快速的激光雷达目标识别方法。采用由粗到精的策略，提出了一种新的点云正交投影轮廓特征(PCF)实现模型的快速预选，在此基础上利用迭代最近点(ICP)算法将目标与模型点云精确匹配，并综合利用特征匹配和点云匹配信息构建相似性度量实现目标识别。采用25类地面装甲目标在96个不同视角下的点云数据进行实验，结果表明该算法的运算效率远优于逐一匹配法，且对目标姿态估计误差和目标遮挡具有很强的稳健性，具有较好的综合性能和应用推广价值。

Abstract

Ladar has became a hot research topic in target recognition community for its ability to capture the object′s explicit 3D shape. To avoid the heavy computation burden faced by the traditional recognition methods, a fast ladar target recognition method is proposed. Adopting the coarse-to-fine strategy, the models are quickly pre-screened by using the proposed orthogonal projection contour features (PCF). Then the target is registered with the hypothesis models precisely by using the iterative closest point (ICP) method. Finally, the similarities between the target and models are calculated by integrating the features matching and points matching results. Therefore, the target is recognized to the model who owes the highest similarity. The experiments are performed using the point-clouds of 25 ground targets under 96 different viewing angles. The results show that the proposed method outperforms the existing methods greatly in the term of computation efficiency, and it is very robust to orientation error and occlusion. Thus, this method is the state-of-the-art and have a high application potential.

参考文献

[1] 孟昭华, 洪光烈, 胡以法等. 啁啾调幅相干探测激光雷达关键技术研究［J］. 光学学报, 2010, 30(8): 2046～2050

Meng Zhaohua, Hong Guanglie, Hu Yifa et al.. Research on chirped amplitude modulation coherent lidar［J］. Acta Optica Sinica, 2010, 30(8): 2046～2050

[2] 李晓峰, 徐军, 张胜修等. 激光主动成像图像边缘检测技术［J］. 中国激光, 2010, 37(6): 1599～1601

Li Xiaofeng, Xu Jun, Zhang Shengxiu et al.. Edge detection algorithm of laser active imaging［J］. Chinese J. Lasers, 2010, 37(6): 1599～1601

[3] 孙剑锋, 魏靖松, 刘金波等. 条纹管激光成像雷达目标重构算法［J］. 中国激光, 2010, 37(2): 510～513

Sun Jianfeng, Wei Jingsong, Liu Jinbo et al.. Target reconstruction algorithm for streak tube imaging lidar［J］. Chinese J. Lasers, 2010, 37(2): 510～513

[4] E. Sobel, J. Douglas, G. Ettinger. 3D ladar ATR based on recognition by parts［C］. SPIE, 2003, 5094: 29～40

[5] H. Garten, Y. Tal, Y. Swirski et al.. Recognition of tanks using laser radar (LADAR) images［C］. SPIE, 2004, 5613: 166～176

[6] T. Chevalier, O. Steinvall, H. Larsson. Performance of laser penetration through forest vegetation［C］. SPIE, 2007, 6550: 1～11

[7] J. F. Sun, W. Lu, Q. Li et al.. Correlation target recognition for laser radar［C］. SPIE, 2006, 6027: 602731

[8] J. Neulista, W. Armbruster. Segmentation, classification, and pose estimation of military vehicles in low resolution laser radar images［C］. SPIE, 2005, 5791: 218～225

[9] A. Mahalanobis, A. J. Nevel. Performance of multidimensional algorithms for target detection in ladar imagery［C］. SPIE, 2002, 4789: 134～147

[10] A. N. Vasile, R. M. Marino. Pose-independent automatic target detection and recognition using 3D laser radar imagery［J］. Lincoln Laboratory J., 2005, 15(1): 61～78

[11] A. E. Johnson, M. Hebert. Using spin images for efficient object recognition in cluttered 3D scenes［J］. IEEE Trans. Pattern Anal., 1999, 21(5): 433～449

[12] P. Besl, N. Mckay. A method for registration of 3D shapes［J］. IEEE Trans. Pattern Anal., 1992, 14(2): 239～256

[13] C. Grnwall, F. Gustafsson, M. Millnert. Ground target recognition using rectangle estimation［J］. IEEE Trans. Image Process., 2006, 15(11): 3401～3409

[14] A. S. Mian. Representations and Matching Techniques for 3D Free-Form Object and Face Recognition［D］. Perth: University of Western Australia, 2006. 2～3

[15] 郭裕兰, 鲁敏, 谭志国等. 一种新的激光雷达目标姿态估计算法［J］. 中国激光, 2011, 38(4): 0414002

Guo Yulan, Lu Min, Tan Zhiguo et al.. A novel method for ladar target orientation estimation［J］. Chinese J. Lasers, 2011, 38(4): 0414002

郭裕兰, 鲁敏, 谭志国, 万建伟. 采用投影轮廓特征的激光雷达快速目标识别[J]. 中国激光, 2012, 39(2): 0209003. Guo Yulan, Lu Min, Tan Zhiguo, Wan Jianwei. Fast Target Recognition in Ladar Using Projection Contour Features[J]. Chinese Journal of Lasers, 2012, 39(2): 0209003.

采用投影轮廓特征的激光雷达快速目标识别

关于本站 Cookie 的使用提示

全站搜索

采用投影轮廓特征的激光雷达快速目标识别

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索