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.

At present, preceding vehicle detection remains a challenging problem for autonomous vehicle technologies. In recent years, deep learning has been shown to be successful for vehicle detection, such as the faster region with a convolutional neural network (Faster R-CNN). However, when the host vehicle speed increases or there is an occlusion in front, the performance of the Faster R-CNN algorithm usually degrades. To obtain better performance on preceding vehicle detection when the speed of the host vehicle changes, a speed classification random anchor (SCRA) method is proposed. The reasons for degraded detection accuracy when the host vehicle speed increases are analyzed, and the factor of vehicle speed is introduced to redesign the anchors. Redesigned anchors can adapt to changes of the preceding vehicle size rule when the host vehicle speed increases. Furthermore, to achieve better performance on occluded vehicles, a Q-square penalty coefficient (Q-SPC) method is proposed to optimize the Faster R-CNN algorithm. The experimental validation results show that compared with the Faster R-CNN algorithm, the SCRA and Q-SPC methods have certain significance for improving preceding vehicle detection accuracy.

No abstract

No abstract

No abstract