A New Approach to Evidence Combination and Its Application to Targets Recognition in Image Sequence
Chen Liang-zhou · 上海交通大学学报：英文版 · 2007
The classical Dempster's combination rule is the most popular rule of combinations,but it is a poor solution for the management of the evidence conflict at the normalization step.When deal with high conflict information it can even involve counter-intuitive results.Based on evidence distance,some inherent characters of evidences are extracted,and discount method to combine conflicting evidence was proposed.The discount method can be also used to fuse image sequences to recognize targets.Examples show that the proposed method can provide reasonable results with good convergence efficiency.