Deformable part fuzzy decision algorithm for video pedestrian tracking

For the pedestrian tracking failure problems of the multiple concurrent particle filter with partial occlusion in active safety, this paper proposed a fuzzy decision algorithm to decrease the error probability when the multiple deformable parts are used to tracking an up-right person in the video frames. This algorithm applies the multiple adaptive color-based particle filter trackers to trace the different body parts of a pedestrian, and then introduces an elastic-based fuzzy decision in order to amend the incorrect particle filter results when part of the filters missing from pedestrian body. With the simulation results, the proposed algorithm increases the tracking efficiency and decreases the tracing failure or partial failure issues exploiting the combination of the two or more pedestrian parts.