Research on Multiple People Tracking Based on Temporal Color Feature and Fast Fuzzy C-means Clustering
基于时间颜色特征及快速模糊C-均值聚类的多人跟踪方法研究

First,detect people by subtraction from the background,and second,segment the foreground regions into sub-regions representing individual; and third,extract color feature by fast fuzzy C-means clustering,and in the end,track multiple people by spot feature and color feature and eliminate noise by temporal weight at the same time.The experiment shows that the method that use temporal color feature in spot-feature model can effectively solute the question of multiple people tracking, and improve the robustness of tracking.