基于分段建模的肉牛体尺关键点检测轻量化策略

打开文本图片集

中图分类号：TP391.4;S823 文献标志码：A 文章编号：1001-411X（2026）01-0139-11

A lightweight strategy for cattle body size key point detection based on segmented modeling

CAO Zizhuo， GUO Xiaoyan， LI Yanmei， CHEN Xiangxue （College of Information Science and Technology， Gansu Agricultural University，Lanzhou 73oo70， China）

Abstract： 【Objective】 To quickly， efficiently and accurately measure beef catte body size，and design a lightweight automatic measurement strategy for catte body size. 【Method】 Based ona self-built dataset of cattle side-view images and using YOLOl1n-pose as the baseline model， the RepGhost （reparameterization）， CoT （context information fusion） and SaE modules were introduced. We proposed RepGhost-CoT-SaE-YOLO （RCS-YOLO），a lightweight strategy for catle body size keypoint detection. Based on RCS-YOLO， we obtained 11 key body size points， including the highest point of the withers，ground contact point of the front hoof， sternum base point， posterior edge point of the withers，the lowest point of the abdomen，lumbar vertebrae point， dorsal crosspoint，posterior edge point ofthe ischial tuberosity，anterior edge point ofthe shoulder，endpoints of the left front cannon bone.Using coordinate transformation algorithms between keypoint pixel values and actual values，along with specific body size formulas， we realized the automated measurement of seven body size parameters of body height，body slanting length，chest depth，abdominal depth， withers height，rump length and cannon circumference. 【Result】 Experiments on the self-built dataset showed that compared to the original baseline model， RCS-YOLO achieved 45.8% reduction in parameter size， 53.6% in computational cost， and 43.1% in model size while maintaining model accuracy. The average eror between predicted and manually annotated keypoints was 8.2 pixels，and the overallaverage relative error of the model measurement and manual measurement for various parameters was 3.7% 【Conclusion】 The RCS-YOLO model can rapidly， efficiently， and cost-effectively automate cattle body size data measurement.It meets the data requirements for cattle breeding and is well-suited for practical deployment in local beef cattle farm setings.

Key words： Cattle; Segmented modeling; Key point; Body size measurement; YOLO11n-pose

肉牛在我国农业经济中占据重要地位，肉牛养殖不仅创造经济价值，还带动了饲料、兽药、屠宰加工、物流等多个相关产业的发展。（剩余16545字）