Real-Time Detection of Mango Based on Improved YOLOv4

Agricultural mechanization occupies a key position in modern agriculture. Aiming at the fruit recognition target detection part of picking robot, mango method based on an improved YOLOv4 network structure is proposed, which can quickly and accurately identify locate mangoes. The improves accuracy width adjustment network, then reduces ResNet (Residual Networks) module to adjust neck improve prediction speed, finally adds CBAM (Convolutional Block Attention Module) network. newly model YOLOv4-LightC-CBAM. training results show that mAP (mean Average Precision) obtained by YOLOV4-LightC-CBAM 95.12%, 3.93% higher than YOLOv4. Regarding up 45.4 frames, 85.3% modified recognize mangoes better, faster, more accurately.