运动目标的自动分割与跟踪

刘明刚; 侯朝焕

运动目标的自动分割与跟踪

计量
- 文章访问数: 2375
- HTML全文浏览量: 104
- PDF下载量: 1006
- 被引次数: 0
出版历程
- 收稿日期: 2001-03-02
- 修回日期: 2001-08-24
- 刊出日期: 2002-08-19

Automatic segmentation and tracking of moving object

摘要

摘要: 该文提出了一种对视频序列中的运动目标进行自动分割的算法。该算法分析图像在L U V空间中的局部变化,同时使用运动信息来把目标从背景中分离出来。首先根据图像的局部变化,使用基于图论的方法把图像分割成不同的区域。然后,通过度量合成的全局运动与估计的局部运动之间的偏差来检测出运动的区域,运动的区域通过基于区域的仿射运动模型来跟踪到下一帧。为了提高提取的目标的时空连续性,使用Hausdorff跟踪器对目标的二值模型进行跟踪。对一些典型的MPEG-4测试序列所进行的评估显示了该算法的优良性能。
- 基于内容的功能; MPEG-4; 视频序列分割; 目标跟踪; 视频目标平面; 运动检测
Abstract: A new automatic video sequence segmentation algorithm that extracts moving objects is presented in this paper. The algorithm exploits the local variation in the L~*u~*v~* space, and combines it with motion information to separate foreground objects from the background. A new image segmentation algorithm based on graphic-theoretic approach is first employed to generate various regions according to local variation. Next, moving regions are identified by a new filter criterion, which measures the deviation of the estimated local motion from the synthesized global motion. In order to increase the temporal and spatial consistency of extracted objects, moving regions are tracked by a region-based affine motion model. A two-dimensional binary model is derived for the objects and tracked throughout the sequence by a Hausdorff object tracker. The proposed algorithm is evaluated for several typical MPEG-4 test sequences. Experimental results demonstrate the performance of the proposed algorithm.

HTML全文

参考文献(1)

MPEG-4 visual fixed draft international standard, ISO/IEC 14496-2, Oct.1998.[2]P. Salembier,et al., Antiextensive connected operations for image and sequence processing, IEEE Trans. on Image Processing, 1998, IP-7(4), 555-570.[3]L. Garrido,et al., Motion analysis of image sequences using connected operators.[J]. SPIE.1997,Vol.3024:546-[4]T. Meier, K. N. Ngan, Segmentation and tracking of moving objects for content-based video coding, IEE Proc. Visual Image Signal Processing, 1999, 146 (3), 144-150.[5]J. Guo,et al., Fast and accurate moving object extraction technique for MPEG-4 object-based video coding, in SPIE Visual Communication and Image Processing, VCIP99, San Jose, CA,1999, Vol.3653, 1210-1221.[6]T. Merier, K. N. Ngan, Automatic segmentation of moving objects for video object plane generation, IEEE Trans. on Circuits and Systems, Video Technology, 1998, CASVT-8(5), 525-537.[7]T. Meier, K. N. Ngan, Extraction of moving objects for content-based video coding, in SPIE Visual Communication and Image Processing, VCIP99, San Jose, CA, 1999, Vol.3653, 1178-1189.[8]R. Mech, M. Wollborn, A noise robust method for 2D shape estimation of moving objects in video sequences considering a moving camera, Signal Processing, 1998, 66(2), 203-217.[9]A. Neri, et al., Automatic moving object and background separation, Signal Processing, 1998,66(2), 219-232.[10]D. P. Huttenlocher, et al, Comparing images using the Hausdorff distance, IEEE Trans. on Pattern Anal. Machine Intell., 1993, PAMI-15(9), 850-863.[11]P.F. Felzenszwalb.[J].D. P. Huttenlocher, Image segmentation using local variation, Proc. IEEE Conf. Computer Vision Pattern Recognition, CVPR98, Santa Barbara, CA.1998,:-[12]B.K.P. Horn, B. G. Schunck, Determining optical flow, Artificial Intell., 1981, 17, 185-203.[13]M.R. Luettgen, et al., Efficient multiscale regularization with application to the computation of optical flow, IEEE Trans. on Image Processing, 1994, IP-3(1), 41-63.[14]M.J. Black, P. Anandan, A framework for the robust estimation of optical flow, Fourth International Conf. on Computer Vision, ICCV-93, Berlin, Germany, May 1993, 231-236.[15]J.D. Kim, S. K. Mitra, A local relaxation method for optical flow estimation, Signal Processing:Image Communication, 1997, 11(1), 21-38.[16]M. Bierling, Displacement estimation by hierarchical block-matching, in SPIE Visual Communication and Image Processing, VCIP88, Cambridge, MA, 1988, Vol. 1001, 942-951.[17]J. Canny, A computational approach to edge detection, IEEE Trans. on Pattern Anal. Machine Intell., 1986, PAMI-8(6), 679-698.

施引文献

资源附件(0)

访问统计