Abstract
The paper first discusses shortcomings of classical adjacent-frame difference. Secondly, based on the image energy and high order statistic(HOS) theory, background reconstruction constraints are setup. Under the help of block-processing technology, background is reconstructed quickly. Finally, background difference is used to detect motion regions instead of adjacent frame difference. The DSP based platform tests indicate the background can be recovered losslessly in about one second, and moving regions are not influenced by moving target speeds. The algorithm has important usage both in theory and applications.
Similar content being viewed by others
References
M. Thomas, Automatic segmentation of moving objects for video object plane generation, IEEE Trans. on Circuits and Systems for Video Technology, 8(1998)5, 525–538.
J. G. Jeon, K. T. Park, Multi-target tracking system using texture. SPIE, 3024, 1997, 229–236.
S. Gil, T. Pun, R. Milanese, Comparing features for target tracking in traffic scenes, Pattern Recognition, 29(1996)8, 1285–1296.
M. A. Jain, Vehicle segmentation and classification using deformable templates, IEEE Trans. on PAMI, 18(1996)3, 293–308.
Zhang Xianda, Modern signal processing. Peiking: Tsinghua university publishing house, 1996, 373–380(in Chinese).
Wang Hongyu, Modern Spectrum Estimation. Nanjing: Southeast university publishing house, 1991, 304–320(in Chinese).
Author information
Authors and Affiliations
About this article
Cite this article
Zhang, W., Li, X. & Li, Z. Accurate detection of high-speed multi-target video sequences motion regions based on reconstructed background difference. J. of Electron.(China) 18, 1–7 (2001). https://doi.org/10.1007/s11767-001-0001-z
Issue Date:
DOI: https://doi.org/10.1007/s11767-001-0001-z