Road Scene Multi-Object Detection Algorithm Based on CMS-YOLO

Abstract

To address issues such as low detection accuracy and limited real-time performance in road scene detection, a novel road scene detection algorithm based on CMS-YOLO is proposed in this paper. In this algorithm, an efficient backbone called the cross-stage partial DWNeck is devised. By using large-scale depthwise separable convolutions and residual structures, it enables the acquisition of more comprehensive feature information, thereby increasing both the receptive field and the richness of extracted features. Meanwhile, a feature pyramid called the multi-scale fusion feature pyramid network is designed to strengthen the fusion of shallow and deep-level information, effectively preventing the loss of feature information in the transmission process. Besides, a new decoupled head structure called the special decoupled head is introduced, which effectively addresses the conflict between classification and regression tasks through a three-layer joint output structure. Finally, experiments were conducted on two publicly available datasets, namely Udacity Self-Driving and BDD100K. Experimental results indicate that the CMS-YOLO algorithm achieved an impressive detection accuracy of 90.3% and 59.1% in mAP@0.5, demonstrating a remarkable improvement of 4.2% and 7.2% over YOLOv5 respectively. Moreover, in real-world scenarios, the algorithm achieves an impressive real-time detection speed of 34.5 frames per second. These results demonstrate that CMS-YOLO not only meets but also surpasses the requirements for detection accuracy and real-time performance for object detection in autonomous driving scenarios.