DENG Hao, LIU Gui-hua, YANG Kang, et al. Moving target tracking method based on double boundary limitation[J]. 2019, 38(1): 60-63+68. DOI: 10.13873/J.1000-9787(2019)01-0060-04.
Aiming at problems of target extraction in complex background
mutual occlusion between two targets
target and background
processing of shadow
real-time and robustness of target tracking
and so on
in target tracking field
a moving target tracking algorithm based on double boundary limitation is proposed. The pyramid optical flow method is used to track target key points for a long time without model
and it is fused with the detected foreground key points without repetition. The scale factor and twiddle factor are evaluated
according to the key points obtained by fusion
and the target center points are probabilistically voted by using all the foreground key points. The double boundary definition method is used to make the key points on the boundary reliably describe the target and improve the robustness of the system.
Greedy Function Approximation: A Gradient Boosting Machine [J] . Jerome H. Friedman. The Annals of Statistics . 2001 (5)
Development of an Endoscopic Navigation System Based on Digital Image Processing [J] . M. Scholz,W. Konen,S. Tombrock,B. Fricke,L. Adams,M. von Dü,ring,A. Hentsch,L. Heuser,A. G. Harders. Computer Aided Surgery . 1998 (3)