Robust visual tracking based on selective attention shift

Abstract

Primates demonstrate an outstanding ability of gaining a continuous tracking of target in cluttered environments after target disappears in the scene for a long time while it is still a challenge for artificial visual system to do so. Research in psychology indicates that selective visual attention with two attention selection processes is crucial to visual tracking. This paper presents a novel visual attention shift tracking (VAST) algorithm to solve the difficult problems mentioned above by treating tracking as a kind of shifting visual attention to the target in consequent frames. In VAST, the early attentional selection process extracts a pool of salient objects or regions that have good localization properties from a salient map. Then, by the learned knowledge from historical data on the fly, the late attentional selection process generates a sequence of shifting between those objects and implements a detection of the target in them one by one. Experiments under various conditions show that this algorithm is general, robust and can gain better tracking results as compared to the existing tracking algorithms. Index Terms-Mean-shift tracker, Spatial information, Tunable kernels978-1-4244-4603-2/09/$25.00 ©2009 IEEE

Human Memory Update Strategy: A Multi-Layer Template Update Mechanism for Remote Visual Monitoring

“…This method used some characteristics of target intensity for modeling to make the monitor determine the true coordinates of one or more targets and thus monitor effectively. Lamberti et al [31] proposed a template matching strategy to improve the robustness of the FLIR image of the target monitoring algorithm. This method used motion prediction metrics to identify the occurrence of false alarms and control the activation based on the template matching phase.…”