基于HRM-YOLO的交通标志检测算法OA

Traffic sign detection technology is an important application in autonomous driving and intelligent traffic management.However,missed detections and false detections are prone to occur in complex environments.In view of the above,this paper proposes an HRM-YOLO traffic sign detection algorithm based on improved YOLOv10.A hybrid pooling enhancement module HPE-SPPF is designed in order to improve the perception ability of the model for different scales of the object.A receptive field information fusion module RFIF is designed,and the multi-granularity information capture ability is enhanced by the interaction mechanism of cross-scale receptive fields.A lightweight feature aggregation module C2f-OMSA is designed to provide cross-level multi-view object clues while effectively retaining original information.The loss function Wise-IoU v3 is introduced to replace the loss function CIoU to improve the accuracy of bounding box positioning,so as to improve the robustness and detection accuracy of the model.Experiments on the traffic sign datasets CCTSDB 2021 and TT100K show that the precision,recall rate and mAP@0.5 of the HRM-YOLO are improved in comparison with those of the basic model,which verifies the effectiveness of the algorithm in practical applications.