Data Fusion Using Improved Dempster-Shafer Evidence Theory for Vehicle Detection

Abstract

Data fusion is an important tool for improving the performance of detecting system when various sensors are available. The Dempster-Shafer evidence theory for fusion has similar reasoning logic with human. So we apply the data fusion method which is based on Dempster-Shafer theory, in a vehicle detecting system to increase the detection accuracy. In this paper, the Dempster-Shafer evidence theory and its problem are discussed, and an improved reliability revaluated Dempster-Shafer fusion (RRDSF) algorithm is proposed and applied. The experiments show promising results and encourage us to do further work.