YOLO11-DML: A Lightweight Object Detection Method for Cattle

Reliable cow detection in barn environments remains challenging due to visual occlusion,overlapping animals,and cluttered backgrounds.To improve accuracy and real-time performance under such conditions,this study presents YOLO11-DML,an enhanced detection framework built upon YOLO11.The proposed model introduces targeted improvements in feature extraction,attention design,and lightweight head architecture.First,an upgraded C3K2-DIMB module replaces the original C3K2 block,using dynamically weighted convolution branches to strengthen multi-scale representation.Second,a Mixed Local Channel Attention (MLCA) mechanism is added to the end of the backbone,improving robustness against illumination variation and partial occlusion.Finally,a Lightweight Shared Convolution Detection Head (LSCDH) is designed to reduce parameter redundancy and computation costs while maintaining detection accuracy.Experiments on the CBVD-5 and Dairy Cow datasets show that YOLO11-DML achieves stable improvements,reaching a precision of 92.57% and an F1-score of 89.07%,with only 2.16M parameters,5.1 GFLOPs,and a model size of 4.5 MB.These results indicate that the model provides an efficient and lightweight solution for real-time multi-object cow monitoring in intelligent dairy production.