Preceding Vehicle Detection Based on Optimized Faster R-CNN Algorithm

Abstract

Preceding vehicle detection is still a challenge for unmanned driving technology. Deep learning has achieved great success in target detection. Among them, the Faster R-CNN algorithm is a classic representative. However, the algorithm still has some room for improvement in detection accuracy. By analyzing the problems of Faster R-CNN in the detection of occluded vehicles, taking the target detection post-processing algorithm Soft-NMS as the research object, two new penalty coefficients, inverse proportional penalty coefficient and exponential penalty coefficient, were proposed. It further improves the algorithm’s detection accuracy of the blocked vehicle in front.