Research on Traffic Object Detection Algorithm Based on YOLOv7
Aiming at the factors of lighting,occlusion,small target and complex background in complex traffic scenes,it leads to low target detection accuracy and is prone to cause missed and false detections,a traffic target detection algorithm based on YOLOv7 is proposed.To better capture the internal correlation within the data and features,the algorithm incorporates the multi-head atten-tion mechanism into the backbone network to enhance the network feature learning ability.The coordinated attention(CA)module is introduced into the YOLOv7 neck network,and the position information is embedded into the attention mechanism,which can ignore the interference of irrelevant information and enhance the feature extraction ability of the network.A multi-scale detection network is added to enhance the detection capability of the model for different scale targets.The CIoU loss function is modified to the SIoU func-tion to reduce the convergence and instability of the model,and improve the robustness of the model.The expermental results show that the mean average precision(mAP)and dectection speed of the improved algorithm on the BDD100K public dataset reach up to 59.8％and 96.2 frames per second(FPS),respectively,with an increase of 2.5％compared to that of the original algorithm.It shows that the improved algorithm has a good detection accuracy while meeting the real-time requirements,which is suitable for traffic target detections in complex situations.
traffic object detectionYOLOv7 networkattention mechanismsshallow network detection layerSIoU loss function
万方数据
维普
