基于DPM的高鲁棒性目标检测方法

With the arrival of the era of car networking, vision-based auxiliary driving system has attracted more and more attention. However, due to the complex outdoor environment, occlusion and other problems, the target detection accuracy is low. In this paper, a robust target detection method based on DPM model is proposed. Based on the DPM model, the complementary feature fusion method is used to improve the detection precision of target detection. The experimental results show that this method can improve the detection accuracy, improve the detection results effectively, and can effectively solve the detection of the targets that are blocked.