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

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.

[1]  Hongwei Zhu,et al.  Data fusion for pattern classification via the Dempster-Shafer evidence theory , 2002, IEEE International Conference on Systems, Man and Cybernetics.

[2]  Hong Huo,et al.  Traffic Video Segmentation Using Adaptive-K Gaussian Mixture Model , 2006, IWICPAS.

[3]  Subhash Challa,et al.  An Introduction to Bayesian and Dempster-Shafer Data Fusion , 2003 .

[4]  Kari Sentz,et al.  Combination of Evidence in Dempster-Shafer Theory , 2002 .

[5]  P. Varaiya,et al.  Signal processing of sensor node data for vehicle detection , 2004, Proceedings. The 7th International IEEE Conference on Intelligent Transportation Systems (IEEE Cat. No.04TH8749).

[6]  Soraia Raupp Musse,et al.  Background Subtraction and Shadow Detection in Grayscale Video Sequences , 2005, XVIII Brazilian Symposium on Computer Graphics and Image Processing (SIBGRAPI'05).

[7]  Makeshwar Kothandaraman,et al.  Application of Douglas-Peucker algorithm to generate compact but accurate IBIS models , 2005, 18th International Conference on VLSI Design held jointly with 4th International Conference on Embedded Systems Design.

[8]  P. G. Michalopoulos,et al.  Vehicle detection video through image processing: the Autoscope system , 1991 .

[9]  Jie Yang,et al.  Sensor Fusion Using Dempster-Shafer Theory , 2002 .