面向挤奶机器人的轻量化奶牛乳头检测算法OA

Aiming at the adaptability of the traditional detection model in the environment of limited computing resources,a lightweight object detection algorithm based on enhanced YOLOv8n was proposed for the accurate detection of cow nipple by intelligent milking robot.Firstly,the structure of YOLOv8n is optimized,and context guidance module is introduced to reduce parameter redundancy and improve feature extrac-tion capability.At the same time,a large separable kernel attention module is used to expand the receptive field and enhance the ability of the model to express key features.In addition,the simple attention module is combined to strengthen the model's attention to important features,and the integrated separated and enhancement attention module in the detection head can further improve the ability of feature extraction and information fusion.The experimental results show that the improved model is superior to the original YOLOv8n in both detection accuracy and computational efficiency.Compared with the benchmark model,the accuracy,recall rate and average accuracy are improved by 2.6%,1.5%and 1.4%,respectively,while the computational complexity and the number of parameters are reduced by 39.3%and 27.8%,respectively,achieving a better lightweight effect.In comparison experiments,the improved model outperforms mainstream target detection algorithms such as YOLOv5,YOLOv6,YOLOv7 and YOLOv11 in several key indicators,showing better detection performance and model efficiency.