基于改进YOLOv5s的护帮板异常检测方法研究

张旭辉,闫建星,麻兵,鞠佳杉,沈奇峰,吴雨佳

Research on abnormal detection method of side guard based on improved YOLOv5s

Xu-hui ZHANG,Jian-xing YAN,Bing MA,Jia-shan JU,Qi-feng SHEN,Yu-jia WU

表5 不同模型对hb_data2021的训练结果

Table 5 Training results of different models on hb_data2021

模型 T/% C/M v/(ms/帧) R/% Faster R-CNN 91.5 28.33 150.8 91.7 SSD 91.9 26.74 25.7 92.3 YOLOv3 92.1 62.57 28.2 92.5 YOLOv5s 94.2 7.09 19.8 93.6 A-YOLOv5s 95.0 4.72 13.2 94.6