Research on improved YOLOv5-based pest recognition

Previous means of controlling pests and diseases were relatively outdated and did not improve the yield and efficiency of farmland very much. In order to be able to monitor the degree of pests and diseases of planted crops such as wheat and corn in real time and to increase robustness, this paper proposes a pest detection model YOLOv5s-ECA based on the improved YOLOv5 algorithm, which introduces an attention mechanism, ECA, into the backbone network of YOLOv5s in order to achieve the enhancement of the network's capability of extracting image features while there is no increase in the model's parameters and volume. Thus, the purpose of improving the accuracy of detecting the target is achieved. In order to verify the performance of the model, we built a pest and disease dataset, and the training results show that YOLOv5-ECA improves the detection mAP by 3.1% and Precision by 4.1%, and the detection results are better than other detection algorithms.