Search papers, labs, and topics across Lattice.
This paper introduces Cotton-SF YOLO, a novel framework for detecting cotton squares in complex field environments, addressing challenges such as occlusion and low contrast. By integrating Dynamic Snake Convolution for adaptive edge feature extraction and a frequency-domain feature modulation module for enhanced texture discrimination, the model significantly improves detection accuracy. The proposed approach outperforms the baseline YOLO26m, achieving mAP values of 0.8196 and 0.4942, demonstrating the effectiveness of combining structural and frequency cues in agricultural monitoring.
Achieving over 80% mAP in detecting small, occluded cotton squares could revolutionize precision agriculture practices.
Cotton squares are important phenotypic indicators of the early reproductive growth of cotton, and automatic field detection of cotton squares provides an important basis for cotton growth monitoring and precision cultivation management. However, early cotton square detection in complex field environments remains insufficiently explored, as cotton squares are small, frequently occluded, easily blurred, subject to illumination variations, and exhibit low contrast against surrounding cotton leaves. To address these challenges, we propose a task-oriented framework based on YOLO26m, named Cotton-SF YOLO, for cotton square detection under natural field conditions. To improve the perception of small and irregular cotton square boundaries, we introduce Dynamic Snake Convolution into the detector, enabling adaptive extraction of deformable edge features. Furthermore, a frequency-domain feature modulation module is designed by incorporating spectral enhancement into the C2f structure, which recalibrate frequency-domain representations and strengthen discriminative edge and texture cues while reducing interference from complex cotton leaf backgrounds. Trained and evaluated on our newly constructed and annotated field dataset with manually annotated cotton squares, the proposed model achieves mAP$_{50}$, mAP$_{50:95}$, and recall values of 0.8196, 0.4942, and 0.7939, improving over the baseline YOLO26m by 1.25%, 3.45%, and 2.96%, respectively. Ablation experiments and visualization demonstrate that the best performance is achieved with the complementary effects of structural and frequency cues.
