Enhancing cotton seedling recognition: a method for high-resolution UAV remote sensing images

Abstract

ABSTRACT Timely and accurate acquisition of cotton seedling information is crucial for seedling replenishment, yield increase, and effective cotton field management. This study proposes a cotton seedling recognition model and weed removal method for high-resolution UAV (Unmanned Aerial Vehicle) remote sensing images. First, the image information of cotton seedlings is enhanced by calculating the remote sensing index and using threshold segmentation. Second, the recognition model is constructed based on the spatial morphological characteristics of cotton seedlings, with weed interference removed using the straight-line method. Finally, the growth condition of cotton seedlings in farmland is comprehensively evaluated by calculating the seedling emergence rate and coverage rate. The experimental results show that: (1) the combination of the GLI (Green Leaf Index) and Otsu threshold segmentation algorithm effectively distinguishes cotton seedlings from the soil background and accurately portrays cotton seedling contours, further enhancing image information; (2) the proposed recognition model achieves an average overall accuracy of 95.75%, making it a practical method for cotton seedling recognition; and (3) the overall growth condition of cotton seedlings in the study area is good, enabling farmers to apply appropriate seedling replenishment and fertilizer based on the comprehensive cotton evaluation map to further improve the final cotton yield. This study aims to provide new research ideas for crop seedling identification and serve as a reference for the practical application of UAVs in crop monitoring.