Citrus Diseases and Pests Detection Model Based on Self-Attention YOLOV8

To accurately detect citrus diseases and pests in real time, even in complex natural environments, this study proposes a Light-SA YOLOV8 (Lightweight Self-Attention YOLOV8) model. Based on YOLOV8, the model introduces the BRA self-attention mechanism module before the SPPF layer in the backbone to overcome challenges posed by complex backgrounds, such as uneven lighting and reflections on citrus leaves and fruits, and achieve flexible computation allocation and content awareness. And, the FasterNet Block is also introduced into the backbone to decrease the computational complexity. Moreover, to enhance precision and computational efficiency for citrus diseases and pests, a new feature fusion technique, known as the AFPN (asymptotic characteristic pyramid network) structure, is employed at the Neck. The constructed dataset includes five types of diseases: anthracnose, citrus canker, melanosis, scab, and bacterial brown spot-along with one type of insect pest, the citrus shallow leaf moth. Experimental results demonstrate that the Light-SA YOLOV8 model achieves an average detection accuracy of 92.6% for the six types of diseases and pests on test set. The mAP@0.5 reaches 92.5%, and it takes only 3.4ms to detect a single image. Moreover, the model's memory consumption is just 4.5MB. Compared with the original YOLOV8n, the Light-SA YOLOV8 model exhibits significant improvements in detection accuracy and computational efficiency. It achieves a 2.8% increase in precision(P), a 0.9% increase in mAP@0.5, and a 20.7% reduction in computational load. Furthermore, when compared to Faster RCNN, YOLOV3-tiny, YOLOV8n, and YOLOV5n, the Light-SA YOLOV8 model achieves an average increase in detection precision of 8.8%, 6%, 2.8%, and 1.8%, respectively. The proposed Light-SA YOLOV8 model effectively mitigates the challenges posed by complex backgrounds, ensuring accurate and fast detection of citrus pests and diseases in images. This research offers valuable insights for real-time plant pest and disease detection in natural environments with unstructured backgrounds.