A Moving Object Detection Algorithm Based on Joint Gradient

Abstract:

Intelligent video retrieval is a prominent problem in police video investigation. In this paperwe propose a moving object detection algorithm which is based on jointing the Time gradient and theSingle-frame gradient of a video. Firstly, the concept of the joint gradient was discussed. Secondly,the algorithm steps and related descriptions were listed. The algorithm has been tested in a typicalvideo database. Finally, the experimental results and discussions were given at the end of the article.The results showed that this algorithm has good performance both in accuracy and robustness. Also,it has a fast execution speed. It is expected to be further used in police video investigation.

• Periodical: Applied Mechanics and Materials (Volume 743)
• Pages: 373-378
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.743.373
• Online since: March 2015
• Authors: L.K. Ma, J.Y. Peng, X.Y. Fen
• Keywords: Detection Algorithm, Joint Gradient, Moving Object Detection, Video Retrieval

References

[1] ``Moving object detection by detecting contiguous outliers in the low-rank representation, Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 35, no. 3, pp.597-610, (2013).

DOI: 10.1109/tpami.2012.132

[2] C. Zhao, W. Liu, Y. Wang, Y. Cheng, and H. Zhang, ``A fast algorithm for moving objects detection based on model switching, in Audio, Language and Image Processing, 2008. ICALIP 2008. International Conference on, 2008, pp.143-146.

DOI: 10.1109/icalip.2008.4589955

[3] Z. Chaohui, D. Xiaohui, X. Shuoyu, S. Zheng, and L. Min, ``Improved moving object detection algorithm based on frame difference and edge detection, in Image and Graphics, 2007. ICIG 2007. Fourth International Conference on, 2007, pp.519-523.

DOI: 10.1109/icig.2007.153

[4] ``Multiresolution based gaussian mixture model for background suppression, Image Processing, IEEE Transactions on, vol. 22, no. 12, pp.5022-5035, (2013).

DOI: 10.1109/tip.2013.2281423

[5] Y. Yang and Y. Liu, ``An improved background and foreground modeling using kernel density estimation in moving object detection, in Computer Science and Network Technology (ICCSNT), 2011 International Conference on, 2011, pp.1050-1054.

DOI: 10.1109/iccsnt.2011.6182141

[6] R. C. Gonzalez, R. E. Woods, and Q. R. trans., Digital Image Processing(2nd edition). Publishing House of Electronics Industry, Beijing, China, (2005).

[7] Y. Wang, J. Ostermann, Y. Zhang, and Z. H. trans., Video Processing and Communications. Publishing House of Electronics Industry, Beijing, China, (2003).

[8] ``Fast-moving target tracking based on mean shift and frame-difference methods, Journal of Systems Engineering and Electronics, vol. 22, no. 4, pp.578-592, (2011).

DOI: 10.3969/j.issn.1004-4132.2011.04.006

[9] C. Zhao, ``Studies on moving objects analyses technology in intelligent video surveillance, ' Master's thesis, Northwestern Polytechnical University, Xi, an, China, (2008).

[10] ``A new scheme for robust gradient vector estimation in color images, Image Processing, IEEE Transactions on, vol. 20, no. 8, pp.2211-2220, (2011).

DOI: 10.1109/tip.2011.2118217

[11] D. A. Forsyth and J. Ponce, Computer Vision: A Modern Aproach(2nd edition). Publishing House of Electronics Industry, Beijing, China, (2012).

[12] P. Chen, ``Study on object tracking and background subtraction algorithms, ' Master's thesis, Zhejiang University, Xi, an, China, (2010).