基于ShuffleNetv2-YOLOv3模型的静态手势实时识别方法

辛文斌,郝惠敏,卜明龙,兰媛,黄家海,熊晓燕

Static gesture real-time recognition method based on ShuffleNetv2-YOLOv3 model

Wen-bin XIN,Hui-min HAO,Ming-long BU,Yuan LAN,Jia-hai HUANG,Xiao-yan XIONG

表 5 不同Anchors对模型精度的测试结果

Tab.5 Test results of model accuracy by different Anchors

网络模型 主干网络 mAP TT/h Ws /MB v /(帧·s−1) YOLOv3+6Anchors ShuffleNetv2-1.0× 0.966 1.481 14.6 45 YOLOv3+9Anchors ShuffleNetv2-1.0× 0.968 1.724 33.7 42 YOLOv3+CBAM+6Anchors ShuffleNetv2-1.0× 0.992 1.594 15.1 44 YOLOv3+CBAM+9Anchors ShuffleNetv2-1.0× 0.982 1.745 34.2 41