基于Dempster-Shafer证据推理理论的ALV视觉信息融合

VISION INFORMATION FUSION BASED ON DEMPSTER SHAFER EVIDENCE INFERENCE THEORY IN ALV

本文针对Ｄｅｍｐｓｔｅｒ－Ｓｈａｆｅｒ（Ｄ－Ｓ）证据推理理论所存在的问题进行了新的推广，同时考虑证据的相关性与冲突性而修正了Ｄｅｍｐｓｔｅｒ组合规则，并将推广后的Ｄ－Ｓ理论应用于ＡＬＶ实际非结构化道路网环境中视觉信息的融合，研究并探索了信息融合实际应用中诸多具有较大难度的问题，取得了有意义的结果．

This paper generalizes the Dempster Shafer's(D S) theory of evidence inference. The Dempster combining rule is modified to the dependent and conflicting conditions. The generalized D S theory of evidence is implemented for the fusion of vision information of unstructured road network in ALV. Some problems concerning the implementation of fusion are discussed, and meaningful results are obtained.