A method, system and equipment for detecting and counting brown spot disease in rice.
By improving the YOLOv8 model and introducing the C2f-EFA module, ASFPN module, WSIoU loss function, and TADHead detection head, the problems of insufficient accuracy in multi-scale feature extraction and small target detection in rice brown spot disease detection and counting were solved, achieving efficient and accurate disease detection and counting.
CN121482047BActive Publication Date: 2026-06-30SANYA NATIONAL INSTITUTE OF SOUTHERN BREEDING CHINESE ACADEMY OF AGRICULTURAL SCIENCES +1
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SANYA NATIONAL INSTITUTE OF SOUTHERN BREEDING CHINESE ACADEMY OF AGRICULTURAL SCIENCES
- Filing Date
- 2026-01-08
- Publication Date
- 2026-06-30
Smart Images

Figure CN121482047B_ABST
Abstract
This invention relates to the field of crop breeding, and in particular to a method for detecting and counting brown spot disease in rice. The technical solution includes: improving the YOLOv8 model by introducing the C2f-EFA module, the ASFPN module, the WSIoU loss function, and the TADHead detection head to optimize model performance, achieving efficient and accurate detection and counting of brown spot disease in rice, improving the accuracy and efficiency of brown spot disease detection and counting, and providing technical support for rice disease analysis. Specifically, the C2f-EFA module enhances the ability to express the features of brown spot lesions and diseased leaves, significantly reducing the number of parameters and computational complexity, making it suitable for resource-constrained brown spot detection scenarios; the ASFPN module effectively improves the model's ability to detect brown spot lesions and diseased leaves, making it suitable for scenarios with large scale differences, complex backgrounds, and small lesions; the TADHead detection head enhances the model's generalization ability for brown spot detection, strengthens the detection accuracy of brown spot lesions and diseased leaves, and ensures robustness under complex backgrounds or low contrast conditions; the WSIoU loss function significantly improves the accuracy of lesion and diseased leaf localization.
Need to check novelty before this filing date? Find Prior Art