ADAPTIVE VISUAL TRACKING METHOD OF FUSING MULTIPLE INFORMATION

Abstract

The objective is to present an adaptive tracking approach of visual objects in the framework of particle filters (PF) and conflict redistribution strategy based on Dezert-Smarandache theory (DSmT). A combination rule of conflict redistribution was introduced into the researches on visual objects tracking, position and color information of moving objects were combined by modified combination strategy information, and the objects tracking model of fusing multiple information on the condition of occluded objects was established effectively. On the basis of building the execution panel of objects tracking simulation platform, many tracking experiments in complicated scene were carried out to validate the correctness and availability of the introduced method by comparing with other tracking method. Results showed that the introduced approach had excellent adaptive ability for dealing with high conflict among evidences under different occlusion condition, and could solve partly high-level vision tracking problems efficiently.