Image object tracking based on temporal context and MOSSE

摘要

Designing an image target tracking algorithm which is suitable for all occasions is a hotspot in visual field. The MOSSE algorithm based on correlation filter achieves good tracking effect, but it has the disadvantage of poor anti-drift ability. Based on the MOSSE algorithm, multi-frame historical images are used as the input samples of AdaBoost, the classification effect of the weak classifier is measured by the response to the peak coordinate distance, the weights of the training samples are updated according to the classification effect, and multiple weak classifiers and then weighed the weak classifiers according to the accuracy of the tracking target, then we get the final strong filter. The algorithm makes full use of the historical appearance information of the target, which can improve the robustness of the system effectively, while still maintaining the real-time of the related filter algorithm.