A Quick Extraction Algorithm Using Window-Scanning for Moving Vehicles

Abstract:

Aiming at the particularity of traffic monitoring video sequences and the regularity of vehicle movement, a quick extraction algorithm using window-scanning for moving vehicles in traffic monitoring videos is proposed in this paper. This algorithm uses hypothesis testing to higher order statistics of frame differences to achieve the rough separation of moving vehicles and background. Then obtain the length of the vehicle and extract the vertical coordinates of the initial point of moving vehicle by setting a static window with a stationary location, combining with the velocity of the vehicle and the moving pixel distribution probability in the window. And obtain the width of the vehicle the horizontal coordinates of the initial point of moving vehicle by setting a dynamic window, combining with the distribution probability of moving pixels in the window. Finally this algorithm achieved the quick extraction of vehicles with the window obtained by length and width, combining with the coordinates of the initial point of moving vehicle. Experiments show the feasibility of the algorithm that the time and space efficiency is relatively high.

• Periodical: Advanced Materials Research (Volumes 756-759)
• Pages: 3879-3883
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.756-759.3879
• Online since: September 2013
• Authors: Ji Ze Yang, Tie Sheng Fan
• Keywords: Dynamic Window Scanning, Moving Pixel Distribution Probability, Moving Vehicle Extraction, Static Window Scanning

References

[1] Haskell B G, Howard P G, Lecun Y A. Image and video coding-emerging standards and beyond. IEEE Transaction On Circuits and Systems for Video Technology, 1998. 8(7): 814-836.

DOI: 10.1109/76.735379

[2] Takaya K. Detection and segmentation of moving objects in video. Proc of IEEE conference on Electrical and Computer Engineering, Canadian: 2006(5): 2069-(2073).

DOI: 10.1109/ccece.2006.277574

[3] Yang L, Zhang H, Li Y S. The automatic partitioning of video moving objects[J]. CAD&CG. 2004. 16（3）302~305.

[4] Stauffer C, Grimson W. Adaptive background mixture models for real-time tracking. In CVPR'99[C], FortColins, CO, June 1999, 2: 246-252.

[5] Ma Y F, Zhang H J. A new perceived motion based shot conten representation. Proceeding of IEEE International Conference on Image Processing. 2001(3): 426-429.

[6] Yu T L, Zhang Y J. A video retrieval method based on locac movement feature[J]. Journal of Tsinghua University, 2002, 42(7): 925~928.

[7] Zhang Y J. Visual information retrieval based on contents[M]. Beijing. Science Press.

[8] Zhang Y J, Lu H B. 1999. Hierarchical video organization based on compact representation of video units. Proc. Workshop on Very Low Bitrate Video'99, 67~70.

[9] Yang S, Zhong Y Z, A Unified Approach to Extraction of Key frames from MPEG Compressed Video [J]. Journal of image and graphics, 6A(3): 254~258.

[10] Neri A, Colonnese S, Russo G, et al. Automatic moving object and background separation [J]. Signal Processing, 1998, 66(2) : 219~ 232.

DOI: 10.1016/s0165-1684(98)00007-3

[11] Yu L T, Zhang Y J, Video Retrieval Based on the Global Motion Information[J]. ACTA electronica sinica2001, 29(12A): 1794~1798.

[12] Lu H B, Zhang Y J, Yang W P, Shot and Episode Based Nonlinear Organization of Video [J]. Chinese journal of computers2000, 25(5): 548~552.