自动化学报2005，Vol.31Issue(4)：625-630,6.
基于多传感融合的路面机动目标跟踪
Maneuvering Vehicle Tracking Based on Multi-sensor Fusion
摘要
Abstract
Maneuvering targets tracking is a fundamental task in intelligent vehicle research. This paper focuses on the problem of fusion between radar and image sensors in targets tracking. In order to improve positioning accuracy and narrow down the image working area, a novel method that integrates radar filter with image intensity is proposed to establish an adaptive vision window.A weighted Hausdorff distance is introduced to define the functional relationship between image and model projection, and a modified simulated annealing algorithm is used to find optimum orientation parameter. Furthermore, the global state is estimated, which refers to the distributed data fusion algorithm. Experiment results show that our method is accurate.关键词
Information fusion/three-dimensional model/vision window/model matching/ma-neuvering target trackingKey words
Information fusion/three-dimensional model/vision window/model matching/ma-neuvering target tracking分类
信息技术与安全科学引用本文复制引用
陈莹,韩崇昭..基于多传感融合的路面机动目标跟踪[J].自动化学报,2005,31(4):625-630,6.基金项目
Supported by the Special Funds for Major State Basic Research Program of P. R. China (2001CB309403) （2001CB309403）
