Aided Navigation System Research Based on Multi-Information Fusion

Abstract

This paper designed a multi-information fusion algorithm after analysis information from vision sensors and radar sensors. This algorithm used D-S evidence theory to fuse the information of vision sensors and radar sensors to judge the front obstacles, and a final decision is made by the distance information provided by radar to decide whether give the driver corresponding warning. It also designed a critical vehicle distance, which can change according to relative distance and relative velocity. The test results show that this algorithm can give warning information correctly and greatly decrease the uncertainty, thus satisfying the requirement of car aided navigation system. At a resolution of 320×480, the identifying speed of this algorithm can reach 62.5ms/F which satisfied the requirement of real-time of car navigation.