Target Detection Algorithm Based on MMW Radar and Camera Fusion

Abstract

With the increasing demand of consumers for car safety and comfort, intelligent driving technology has received extensive attention and research. A robust and reliable vehicle detection and tracking system is one of the key modules for intelligent vehicles to perceive the surrounding environment. At present, the mass-produced intelligent driving system mainly uses millimeter-wave radar and monocular camera to detect and track vehicles. Despite their advantages, the drawbacks of these two sensors make them insufficient when used separately. Therefore, in order to improve the target detection ability of the system, the research on multi-sensor information fusion is particularly important. This paper presents an information fusion approach based on a millimeter-wave radar and a monocular camera. Firstly, the millimeter-wave radar and monocular camera are used for target detection separately. Then the target data is extracted and recognized. Finally, the same target data detected by the two sensors are fused at the decision level. The proposed algorithm is tested on typical urban roads and urban expressways. Experiments show that the proposed algorithm can effectively improve the stability and reliability of target recognition and reduce the probability of missing target detection.