Intelligent recognition of rice pest images based on YOLOv8s
The distribution of pests during rice cultivation is characterized by small scale and high density,making identification challenging.This article was based on deep learning and the classic YOLOv8s lightweight model was used to train and recognize 14 types of rice pests,including rice leaf roller,rice leaf caterpillar,and rice stem maggot,etc.The model training and verification results were obtained.The training results showed that the model has good convergence speed and stability;the verification results indicated that the model has good performance,with the recognition accuracy of 0.788,the recall rate of 0.721,and the recognition accuracy of 0.809,mAP@0.5 of 0.772 for 14 rice pests.Overall,the model had good performance and can meet the requirements of rice pest detection.The research results provide references for the identification of rice pest.
万方数据
维普
