PMDNet: An Improved Object Detection Model for Wheat Field Weed

Efficient and accurate weed detection in wheat fields is critical for precision agriculture to optimize crop yield and minimize herbicide usage. The dataset for weed detection in wheat fields was created, encompassing 5967 images across eight well-balanced weed categories, and it comprehensively covers the entire growth cycle of spring wheat as well as the associated weed species observed throughout this period. Based on this dataset, PMDNet, an improved object detection model built upon the YOLOv8 architecture, was introduced and optimized for wheat field weed detection tasks. PMDNet incorporates the Poly Kernel Inception Network (PKINet) as the backbone, the self-designed Multi-Scale Feature Pyramid Network (MSFPN) for multi-scale feature fusion, and Dynamic Head (DyHead) as the detection head, resulting in significant performance improvements. Compared to the baseline YOLOv8n model, PMDNet increased mAP@0.5 from 83.6% to 85.8% (+2.2%) and mAP@0.50:0.95 from 65.7% to 69.6% (+5.9%). Furthermore, PMDNet outperformed several classical single-stage and two-stage object detection models, achieving the highest precision (94.5%, 14.1% higher than Faster-RCNN) and mAP@0.5 (85.8%, 5.4% higher than RT-DETR-L). Under the stricter mAP@0.50:0.95 metric, PMDNet reached 69.6%, surpassing Faster-RCNN by 16.7% and RetinaNet by 13.1%. Real-world video detection tests further validated PMDNet’s practicality, achieving 87.7 FPS and demonstrating high precision in detecting weeds in complex backgrounds and small targets. These advancements highlight PMDNet’s potential for practical applications in precision agriculture, providing a robust solution for weed management and contributing to the development of sustainable farming practices.