With the rapid development of autonomous vehicles, traffic sign detection has become a prominent problem. Traffic sign detection is the basic premise of automatic driving environment perception. Aiming at the low accuracy of traditional traffic sign detection, an enhanced YOLOv7 algorithm incorporating the Simple Attention Mechanism and SPPCSPC-C module has been proposed. SimAM is introduced to improve the recognition ability of the original algorithm in complex dynamic scenes, and SPPCSPC-C module is introduced to enhance the detection ability of the model for small targets. The model is trained based on Speed Limit Detection data. The experimental results show that the mAP, Precision and Recall of the improved YOLOv7 reach 97.09%, 97.85% and 93.84%. Compared with YOLOv7, the mAP is increased by 1.19%, the Precision is increased by 2.90%, and the Recall is increased by 2.83%. It is an algorithm worthy of consideration in traffic sign detection.
YOLOv7-SC:A Traffic Sign Detection Algorithm Based On SimAM and improved SPPCSPC-C
2024-12-13
1072000 byte
Conference paper
Electronic Resource
English
YOLOv7-SIMAM: An effective method for SAR ship detection
IEEE | 2024
|YOLOv7-SPD3: A Small Target Detection Algorithm for Multi-Rotor UAV Based on Improved YOLOv7
Springer Verlag | 2025
|