A complex roadside object detection model based on multi-scale feature pyramid network

In response to the challenges of false positives and misses caused by dense occlusions and small targets in complex road environments, this paper proposes an enhanced YOLOv8-based network named YOLO-RC for advanced road traffic object detection. YOLO-RC utilizes MBConv modules to enhance feature extraction in the backbone network, improving the accurate localization capability for densely occluded targets. Additionally, a novel C3FB structure (Efficient Fusion of C3 modules and FocalNextBlock structure) is introduced to replace the C2f module in the neck network of YOLOv8, aiming to reduce the parameter count while enhancing model accuracy. Combining the weighted Bi-directional Feature Pyramid Network (BCFPN) for feature fusion incorporates deep, shallow, and original features, reinforces feature integration, minimizes information loss during convolution processes, and enhances target detection accuracy. Finally, introducing the CBAM module further enhances the algorithm's ability to capture target features, directing more attention to relevant information within the images. Experimental results demonstrate that the proposed algorithm achieves a mAP50 of 91.1% on the roadside target detection dataset DAIR-V2X-I, representing a 4.5% improvement compared to the originalalgorithm, with a recall rate of 81.8%. The generalization experiments are conducted on the challenging dataset UA-DETRAC. The experimental results show that mAP50 reaches 94.8%, and MAP50-95 reaches 77.9%. The algorithm exhibits outstanding detection accuracy performance. Comparative analysis against some mainstream target detection algorithms also reveals the superiority of the proposed approach.