基于特征点的多运动目标跟踪

高韬; 刘正光; 张军; 岳士弘

doi:10.3724/SP.J.1146.2008.01755

基于特征点的多运动目标跟踪

doi: 10.3724/SP.J.1146.2008.01755

计量
- 文章访问数: 3776
- HTML全文浏览量: 94
- PDF下载量: 2051
- 被引次数: 0
出版历程
- 收稿日期: 2008-12-22
- 修回日期: 2010-03-04
- 刊出日期: 2010-05-19

Feature Points Based Multiple Moving Targets Tracking

摘要

摘要: 该文针对智能监控的需求，提出基于特征的多运动目标跟踪算法。通过自适应Marr小波核函数背景建模算法，在冗余离散小波域进行多运动目标识别。运动跟踪采用SIFT特征粒子滤波算法，并采用队列链表法记录多运动目标之间的数据关联，在提高识别准确率的同时降低了运算的复杂度。实际测试表明，该算法对于多运动目标识别跟踪具有更优越的实时性和抗遮挡性，在智能监控领域具有较广泛的应用前景。
- 多运动目标跟踪; 运动识别; 智能监控
Abstract: For the widely demanding of adaptive multiple moving targets tracking, a type of feature based multi-target tracking algorithm is presented. Background is adaptively modeled by Marr wavelet kernel function and a background subtraction technique based on redundant discrete wavelet transforms is used to detect multiple moving targets. A type of particle filtering combined with SIFT key points is used for tracking, and a queue chain method is used to record data association among different targets, which can improve the detection accuracy and reduce the complexity. Actual tests show that the algorithm can track multi-target with a better performance of real time and mutual occlusion robustness; it can be used in intelligent monitoring with extensive application prospect.

HTML全文

参考文献(1)

Betke M, Haritaoglu E, and Davis L S. Real-time multiple vehicle detection and tracking from a moving vehicle [J].Machine Vision and Applications.2000, 12(2):69-83[2]Lin Ming-xiu and Xu Xin-he. Multiple vehicle visual tracking from a moving vehicle [C][J].Proceedings of the Sixth International Conference on Intelligent Systems Design and Applications, Jinan, China.2006, 2:373-378[3]孙志海, 朱善安. 多视频运动对象实时分割及跟踪技术[J]. 浙江大学学报(工学版), 2008, 42(9): 1631-1635.Sun Zhi-hai and Zhu Shan-an. Real-time segmentation and tracking technique of multiple moving objects in video sequence [J]. Journal of Zhejiang University (Engineering Science), 2008, 42(9): 1631-1635.[4]Lin Shin-ping, Chen Yuan-hsin, and Wu Bing-fei. Real-time multiple vehicle detection and tracking system with prior occlusion detection and resolution, and prior queue detection and resolution [C]. Proceedings of 18th International Conference on Pattern Recognition(ICPR), Hong Kong, 2006, 1: 828-831.[5]Jin Yong-gang and Mokhtarian F. Variational particle filter for multi-object tracking [C]. Proceedings of IEEE 11th International Conference on Computer Vision (ICCV), Rio de Janeiro, Brazil, 2007: 1-8.[6]Pinkiewicz T, Williams R, and Purser J. Application of the particle filter to tracking of fish in aquaculture research [C]. Proceedings of Digital Image Computing: Techniques and Applications (DICTA), Canberra, 2008: 457-464.Gao Tao and Liu Zheng-guang. Moving video object segmentation based on redundant wavelet transform [C]. Proceedings of the IEEE International Conference on Information and Automation, Zhangjiajie, China, 2008: 156-160.[7]Lowe D G. Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision.2004, 60(2):91-110[8]Nummiaro K. An adaptive color-based particle filter[J].Image and Vision Computing.2003, 21(1):99-110[9]Reckleitis I. A particle filter tutorial for mobile robot localization [C]. Proceedings of the IEEE International Conference on Robotics and Automation, Taipei, Taiwan, 2003, 42: 1-36.

施引文献

资源附件(0)

访问统计