Lightweight YOLOv8 for Wheat Head Detection

Accurate real-time observations of wheat head growth are crucial for effective agricultural management. However, the dense distribution of wheat heads often leads to severe overlap in imagery. Existing target detection algorithms face challenges in overcoming this problem, rendering them ineffective for real-time field computations using portable devices. Therefore, this study proposes a lightweight you-only-look-once (YOLO) model with a simplified structure and a more powerful attention mechanism. A limitation of the traditional YOLO model is its complex structure, as it requires a substantial number of parameters and its accuracy is unsatisfactory. We remove the modules designed for large targets and reduce the number of detection heads from three to two. Moreover, we add an improved feature pyramid network to the neck, resulting in improved parameter count and accuracy over traditional YOLO methods. To improve inferencing, we replace the spatial pyramid pooling (SPP) module with a simplified SPP-fast type. Finally, a large separable kernel attention and wise intersection-over-union method are introduced to integrate the attention mechanisms, and we replace the loss function to improve the discriminative capabilities of the model. Experimental results on the Global Wheat Head Dataset demonstrate a 53% reduction in memory usage, 27% decrease in computational load, and 5.2 frames-per-second increase in detection speed over extant methods. The proposed model also achieves 3.9%, 2.1%, and 1.3% improvements in terms of precision, recall, and mean average precision, respectively, and it exhibits lightweight and portable characteristics. Overall, the proposed method has fast inference speed and effectively alleviates the problem of low recognition of dense wheat head.