Object detection algorithm based on moving background in MPEG-4 video

被引：0

作者：

Research Institute of Peripherals, Xidian University, Xi'an 710071, China ^{[1
]}

机构：

[1] Research Institute of Peripherals, Xidian University

来源：

Guangxue Xuebao | 2009年 / 5卷 / 1227-1231期

关键词：

DC coefficient; Global motion estimation; Motion vector; MPEG-4; Object detection;

D O I：

10.3788/AOS20092905.1227

中图分类号：

学科分类号：

摘要：

Focusing on the problem of moving object detection in moving camera, a new method for the estimation of global motion from compressed image sequences is proposed. With the global motion estimation as basis, utilizing the similarity of the background micro blocks, the algorithm can build background micro blocks sets speedily. Adopting the common four-parameter global motion estimation model, the motion parameters are estimated. By computing and filtering the motion vectors residual, the moving object is detected. The algorithm can utilize the motion information contained in the MPEG-4 video coded stream without decoding the coded stream completely, so it can improve the detection efficiency and effect dramatically. Testing results validate its advantages in global motion estimation.

引用

页码：1227 / 1231

页数：4

共 12 条

[1]

Kuhn P.M., Sony C., Camera motion estimation using feature points in mpeg compressed domain, IEEE, Internat. Conf. on Image Processing, pp. 596-599, (2000)

[2]

Rath G.B., Makur A., Iterative least squares and compression based estimation for a four-parameter linear global motion model and global motion compensation, IEEE Trans Circuits and System for Video Technology, 9, 7, pp. 1075-1099, (1999)

[3]

Xu G., Cai J., Su D., Detection method for moving target in complex environment, Infrared and Laser Engineering, 36, 6, pp. 992-995, (2007)

[4]

Ren C., Zhang T., New method for detecting of moving targets based on Kalman filter theory, Opto-Electronic Engineering, 34, 4, pp. 7-11, (2007)

[5]

Zha C., Wang C., Kong X., Et al., Moving target detection based on adaptive background model, Opto-Electronic Engineering, 35, 1, pp. 26-30, (2008)

[6]

Wang K., Zhang X., Li L., Et al., New method for moving target detection based on positive and negative difference images, J. Appl. Opt., 28, 5, pp. 521-525, (2007)

[7]

Jiang H., Visual motion analysis and feature extraction, (2004)

[8]

Lin C., Ling Z., Chang Y., Compressed domain fall incident detection for intelligent home surveillance, IEEE, Circuits and Systems, 4, pp. 3781-3784, (2005)

[9]

Chen H., Qi F., Double-iteration algorithm for motion field based global motion estimation, J. China Institute of Communications, 25, 6, pp. 126-131, (2004)

[10]

Chen Z., Nie Z., Gu X., Et al., Fast global motion estimation based on iteration least-square estimation with sustained symmetrical structure, Proc. IEEE International Symposium on Circuits and Systems, pp. 4695-4698, (2006)

← 1 2 →