Abstract
Potato late blight is a common disease affecting crops worldwide. To help detect this disease in complex environments, an improved YOLOv5 algorithm is proposed. First, ShuffleNetV2 is used as the backbone network to reduce the number of parameters and computational load, making the model more lightweight. Second, the coordinate attention mechanism is added to reduce missed detection for leaves that are overlapping, damaged, or hidden, thereby increasing detection accuracy under challenging conditions. Lastly, a bidirectional feature pyramid network is employed to fuse feature information of different scales. The study results show a significant improvement in the model's performance. The number of parameters was reduced from 7.02 to 3.87 M, and the floating point operations dropped from 15.94 to 8.4 G. These reductions make the model lighter and more efficient. The detection speed increased by 16 %, enabling faster detection of potato late blight leaves. Additionally, the average precision improved by 3.22 %, indicating better detection accuracy. Overall, the improved model provides a robust solution for detecting potato late blight in complex environments. The study's findings can be useful for applications and further research in controlling potato late blight in similar environments.