复杂交通场景中多运动目标分割算法

李俊韬; 张海; 范跃祖

复杂交通场景中多运动目标分割算法

北京航空航天大学自动化科学与电气工程学院, 北京 100083

基金项目: 北京市教委重点学科建设基金资助项目(BHBJZB-1-5)

详细信息

作者简介:
李俊韬(1978-),男,河南开封人,博士生, ljtletter@126.com.

中图分类号: TP 391
计量
- 文章访问数: 3489
- HTML全文浏览量: 220
- PDF下载量: 2480
- 被引次数: 0
出版历程
- 收稿日期: 2005-06-21
- 网络出版日期: 2006-03-31

Multiple moving objects segmentation algorithm in complex traffic scene

School of Automation Science and Electrical Engineering, Beijing University of Aeronautics and Astronautics, Beijing 100083, China

摘要

摘要: 针对室外复杂交通场景中多运动目标分割问题,提出了一种由变化检测和运动分割组成的算法,利用水平集算法对帧差图像进行变化检测得到运动窗口,在运动窗口范围内进行改进的k-均值聚类分割,利用运动相似性进行分割区域融合.算法避免了整个图像的分割,减少了运算量,完整的分割出运动目标.试验结果表明,算法不仅能从复杂交通场景图像序列中有效的检测和提取出运动目标并有很强的鲁棒性,而且能够解决运动目标的遮挡问题.
- 目标检测 /
- 水平集 /
- k-均值聚类 /
- 鲁棒性
Abstract: To solve multiple moving objects segmentation problem in complex traffic scene outdoors, a new segmentation algorithm of multiple moving objects segmentation in complex traffic scene of outdoors was developed. The presented method consists of two phases. In the motion detection phase, motion-changed regionwas determined using an improved level set algorithm based on Mumford-Shah model of two consecutive frames difference of image sequence, and an simplified clustering algorithm providing initialization evolution curves of level set algorithm. Motion window was generated through detecting motion-changed region. In themotion segmentation phase, regions segmentation using an improved weighted k-means clustering algorithm of moving windows area were merged based on region motion similarity criterion. Computation time was reduced because of avoiding processing of the whole image. Very promising experimental results indicates that the proposed algorithm is effective with strong robustness using real image sequences of complex traffic scene and can resolve occlusions among multiple moving objects.
- target detection /
- level sets /
- k-means clustering /
- robustness

HTML全文

参考文献(1)

[1] Kouthemy P,Fraancois E. Motion segmentation and dynamic scene analysis from an image sequence[J]. International Journal of Computer Vision, 1993,10(2):157~182 [2] Memin E, Dence P. Estimation and object-based segmentation of the optical flow with robust techniques[J]. IEEE Transactions on Image Procession, 1998, 7(5):703~719 [3] Lipton A, Fujiyoshi H, Patil R. Moving target classification and tracking from real-time video . IEEE Workshop on Applications of Computer Vision . Princeton NJ, 1998.8~14 [4] Foresti G,Murino V,Regazzoni C. Vehicle recognition and tracking from road image sequences[J].IEEE Transaction on Vehicular Technology, 1999,48(1):301~317 [5] 杨莉,李玉山,刘洋,等. 复杂背景下多运动目标轮廓检测[J]. 电子与信息学报,2005,27(2):306~309 Yang Li, Li Yushan, Liu Yang, %et al%. Detection contours of multiple moving objects with complex background[J].Journal of Electronics & Information Technology,2005,27(2):306~309(in Chinese) [6] 朱辉,李在铭,蔡毅. 基于运动窗生成的时空视频分割[J] 电子学报,2004,32(3):480~484 Zhu Hui,Li Zaiming, Cai yi. Spatio-temporal vido segmentation based on the generation of motion window[J]. Acta Electronica Sinica,2004,32(3):480~484(in Chinese) [7] Fan J, Yu J, Fu G, %et al%. Spatiotemporal segmentation for compact video representation[J]. Signal Processing,2001,16:553~566 [8] Geidenberg R,Kimmel R,Rivlin E, %et al%. Fast geodesic active contours[J]. IEEE Transactions on Image Processing,2001,10(10):1467~1475 [9] Chan F T, Vese L. Active contours without edges[J]. IEEE Trans Image Processing,2001,10(2):266~277 [10] 李俊, 杨新, 施鹏飞. 基于Mumford-Shah模型的快速水平集图像分割方法[J]. 计算机学报,2002,11(25):1175~1183 Li Jun, Yang Xin,Shi Pengfei. A fast level set approach to image segmentation based on Mumfor-Shah model[J]. Chinese Journal of Computers,2002 , 11(25):1175~1183(in Chinese) [11] Kottke D, Sun Y. Motion estimation via cluster matching[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1994,16:1128~1132

施引文献

资源附件(0)

访问统计