Abstract. Visual tracking is one of the hot topics in the field of computer science. However, the effective use of context information can improve the robustness of video tracking due to factors such as illumination and rotation. The traditional spatio-temporal context algorithm does not detect the validity of the tracking result, so when the target is obscured for a long time, the tracking target is easily updated wrongly. Based on SURF feature point detection, an improved spatio-temporal context tracking algorithm is proposed. Using the SURF algorithm to extract the feature points from the initial model of the target as the evaluation criteria, the tracking target is evaluated and the target can be updated according to the standard when the target is blocked for a long time. Experiments show that the proposed algorithm can accurately update the target model when the target is obscured for a long time, and achieves reliable tracking.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.