CBLN-YOLO: An Improved YOLO11n-Seg Network for Cotton Topping in Fields

The positioning of the top bud by the topping machine in the cotton topping operation depends on the recognition algorithm. The detection results of the traditional target detection algorithm contain a lot of useless information, which is not conducive to the positioning of the top bud. In order to obtain a more efficient recognition algorithm, we propose a top bud segmentation algorithm CBLN-YOLO based on the YOLO11n-seg model. Firstly, the standard convolution and multihead self-attention (MHSA) mechanisms in YOLO11n-seg are replaced by linear deformable convolution (LDConv) and coordinate attention (CA) mechanisms to reduce the parameter growth rate of the original model and better mine detailed features of the top buds. In the neck, the feature pyramid network (FPN) is reconstructed using an enhanced interlayer feature correlation (EFC) module, and regression loss is calculated using the Inner CIoU loss function. When tested on a self-built dataset, the mAP@0.5 values of CBLN-YOLO for detection and segmentation are 98.3% and 95.8%, respectively, which are higher than traditional segmentation models. At the same time, CBLN-YOLO also shows strong robustness under different weather and time periods, and its recognition speed reaches 135 frames per second, which provides strong support for cotton top bud positioning in the field environment.