研究基于视频图像分析与定位的飞机翼尖跟踪技术,为飞机地面移动提供安全保障。现有图像特征进行翼尖跟踪经常失效且计算效率低下,本文结合纹理和轮廓信息,提出以梯度方向二值模式(OG_LBP)为特征的粒子滤波跟踪算法,降低特征维数的同时建立局部和全局的翼尖特征直方图描述,提高识别效果。同时,该算法在粒子滤波基本框架之下,结合当前观测信息,通过粒子传播半径的自适应更新建立系统状态模型,降低粒子集的衰减程度,提高算法效率。实验结果表明,该算法有效降低计算复杂度,在各种复杂背景下均可实现各种翼尖实时、有效的跟踪,并更具鲁棒性。
[1] 田穆. FAA继续推进机场地面安全技术[J]. 国际航空, 2006(3): 31-32. Tian Mu. FAA aims to improve runway safety[J]. International Aviation, 2006(3): 31-32. (in Chinese)
[2] 郭晓静. 多传感器数据融合在飞机地面防撞中的应用[J]. 测控技术, 2008, 27(6): 15-17. Guo Xiaojing. Multi-sensor data fusion application in aircraft ground collision avoidance[J]. Measurement & Control Technology, 2008, 27(6): 15-17. (in Chinese)
[3] 万卫兵, 霍宏, 赵宇民. 智能视频监控中目标检测与识别[M]. 上海: 上海交通大学出版社, 2010. Wan Weibing, Huo Hong, Zhao Yuming. Object detection and recognition in intelligent visual surveillance. Shanghai: Shanghai Jiao Tong University Press, 2010. (in Chinese)
[4] 李培华. 一种新颖的基于颜色信息的粒子滤波器跟踪算法[J] .计算机学报, 2009, 32(12): 2455-2463. Li Peihua. A novel color based particle filter algorithm for object tracking[J]. Chinese Journal of Computer, 2009, 32(12): 2455-2463. (in Chinese)
[5] Katja N E, Esther K, Luc V G. An adaptive color-based particle filter[J]. Image and Vision Computing, 2002, 21(1): 99-110.
[6] Pérez P, Hue C, Vermaak J, et al. Color-based probabilistic tracking//Proceedings of the European Conference on Computer Vision. 2002:661-675.
[7] Isard M, Blake A. CONDENSATION—conditional density propagation for visual tracking [J]. International Journal on Computer Vision, 1998, 29(1): 5-28.
[8] 庄严, 战洪斌, 王伟, 等. 基于加权颜色直方图和粒子滤波的彩色物体跟踪[J]. 控制与决策, 2006, 21(8): 867-872. Zhuang Yan, Zhan Hongbin, Wang Wei, et al. Weighted color histogram based particle filter for visual target tracking[J]. Control and Decision, 2006, 21(8): 867-872. (in Chinese)
[9] 卢晓鹏, 殷学民, 邹谋炎. 一种基于颜色分布的混合视频跟踪方法[J]. 电子与信息学报, 2008, 30(2): 259-262. Lu Xiaopeng, Yin Xuemin, Zou Mouyan. A hybrid algorithm of object tracking based on color distribution[J]. Journal of Electronics & Information Technology, 2008, 30(2): 259-262. (in Chinese)
[10] Yogesh R, Namrata V, Allen T, et al. Tracking deforming objects using particle filtering for geometric active contours[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(8):1470-1475.
[11] 牛长锋, 陈登峰, 刘玉树. 基于SIFT特征和粒子滤波的目标跟踪方法[J]. 机器人, 2010, 32(2): 241-247. Niu Changfeng, Chen Dengfeng, Liu Yushu. Tacking object based on SIFT features and particle filter[J]. Robot, 2010, 32(2): 241-247. (in Chinese)
[12] 郑永斌, 黄新生, 丰松江. SIFT和旋转不变LBP相结合的图像匹配算法[J]. 计算机辅助设计与图形学学报, 2010, 22(2): 286-292. Zheng Yongbin, Huang Xinsheng, Feng Songjiang. An image matching algorithm based on combination of SIFT and the rotation invariant LBP[J]. Journal of Computer-Aided Design & Computer Graphics, 2010, 22(2): 286-292. (in Chinese)
[13] Shen C, Anton V d H, Dick A. Probabilistic multiple cue integration for particle filter based tracking//Proceedings of Digital Image Computing: Techniques and Applications. 2003, 1: 399-408.
[14] 李远征, 卢朝阳, 高全学, 等. 基于多特征融合的均值迁移粒子滤波跟踪算法[J].电子与信息学报, 2010, 32(2): 411-415. Li Yuanzheng, Lu Chaoyang, Gao Quanxue, et al. Particle filter and mean shift tracking method based on multi-feature fusion[J]. Journal of Electronics & Information Technology, 2010, 32(2): 411-415. (in Chinese)
[15] 高建坡, 王煜坚, 杨浩, 等. 以颜色和形状直方图为线索的粒子滤波人脸跟踪[J]. 中国图象图形学报, 2007, 12(3): 466-473. Gao Jianpo, Wang Yujian, Yang Hao, et al. Particle filter face tracking using color and shape histogram as clues[J]. Journal of Image and Graphics, 2007, 12(3): 466-473. (in Chinese)
[16] 高涛, 何明一, 戴玉超, 等. 多级LBP直方图序列特征的人脸识别[J]. 中国图象图形学报, 2009, 14(2): 202-207. Gao Tao, He Mingyi, Dai Yuchao, et al. Face recognition using multi-level histogram sequence local binary pattern[J]. Journal of Image and Graphics, 2009, 14(2): 202-207. (in Chinese)
[17] Timo O, Matti P, David H. A comparative study of texture measures with classification based on featured distributions [J]. Pattern Recognition, 1996, 29(1):51-59.
[18] Timo O, Matti P, Top M. Multiresolution gray scale and rotation invariant texture classification with local binary patterns[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(7): 971-987.
[19] Navneet D, Bill T. Histograms of oriented gradients for human detection//Proceedings of Conference on Computer Vision and Pattern Recognition. 2005: 886-893.
[20] 孙瑾, 顾宏斌, 郑吉平. 一种基于梯度方向信息的运动目标检测算法[J]. 中国图象图形学报, 2008, 13(3): 571-579. Sun Jin, Gu Hongbin, Zheng Jiping. A gradient direction based moving object detection[J]. Journal of Image and Graphics, 2008, 13(3): 571-579. (in Chinese)
[21] Marko H, Matti P, Cordelia S. Description of interest regions with center-symmetric local binary patterns [J]. Pattern Recognition, 2009, 42(3): 58-69.
[22] 吴成茂, 田小平, 谭铁牛. 二维Otsu阈值法的快速迭代算法[J]. 模式识别与人工智能, 2008, 21(6): 746-757. Wu Chengmao, Tian Xiaoping, Tan Tieniu. Fast iterative algorithm for two-dimensional otsu thresholding method[J]. Pattern Recognition and Artificial Intelligence, 2008, 21(6): 746-757. (in Chinese)
[23] Sanjeev A, Simon M, Neil G, et al. A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking [J]. IEEE Transactions on Signal Processing, 2002, 50(2): 174-188.
[24] 胡士强, 敬忠良. 粒子滤波原理及其应用[M]. 北京:科学出版社, 2010:21-27. Hu Shiqiang, Jin Zhongliang. The theory and application of particle filter[M]. Beijing: Science Press, 2010:21-27. (in Chinese)
[25] 朱志宇. 粒子滤波算法及其应用原理[M]. 北京: 科学出版社, 2010. Zhu Zhiyu. Particle filtering and its application[M]. Beijing: Science Press, 2010. (in Chinese)
[26] 姚剑敏. 粒子滤波跟踪方法研究. 北京: 中国科学院研究生院, 2004. Yao Jianmin. Study on particle filtering based visual tracking method. Beijing: Graduate University of Chinese Academy of Science, 2004. (in Chinese)
[27] 胡昭华. 基于粒子滤波的视频目标跟踪技术研究. 南京: 南京理工大学, 2008: 16-19. Hu Shaohua. Visual target tracking based on particle filter[M]. Nanjing: Nanjing University of Science & Technology, 2008: 16-19. (in Chinese)
[28] 魏海坤. 神经网络结构设计的理论与方法[M]. 北京:国防工业出版社, 2005: 8-11. Wei Haikun. Theory and method of neural network structure design[M]. Beijing: National Defense Industry Press, 2005: 8-11. (in Chinese)
CJA