Related Experiment Video
Updated: Jul 21, 2026
14:14
Quantification of Strain in a Porcine Model of Skin Expansion Using Multi-View Stereo and Isogeometric Kinematics
Published on: April 16, 2017
11.6K
Multi-View Fusion-Based Automated Full-Posture Cattle Body Size Measurement
Zhihua Wu1, Jikai Zhang1, Jie Li1
1School of Automation and Electrical Engineering, Inner Mongolia University of Science and Technology, Baotou 014017, China.
Animals : an Open Access Journal From MDPI
|November 27, 2024
Summary
This study introduces an automatic system using multi-view cameras to measure cattle body sizes accurately. The system overcomes limitations of manual methods and environmental challenges, showing high feasibility and accuracy for livestock growth monitoring.
Area of Science:
- Agricultural Engineering
- Computer Vision
- Livestock Management
Background:
- Cattle body size is crucial for monitoring livestock growth in the global industry.
- Traditional manual measurements are time-consuming, labor-intensive, and costly.
- Existing automatic methods are susceptible to environmental conditions and animal posture.
Purpose of the Study:
- To develop a multi-view fusion-driven automatic measurement system for full-attitude cattle body dimensions.
- To overcome the limitations of traditional and current automatic measurement techniques.
- To provide an accurate and efficient method for assessing cattle growth.
Main Methods:
- Utilized three Zed2 cameras for multi-view image acquisition (RGB, depth, point clouds) using YOLOv8n.
- Processed point clouds through denoising and alignment to create a complete 3D model.
- Mapped 2D key points (YOLOv8x-pose) to 3D using camera parameters and depth data for size measurement; employed SVM and Bézier curves for data correction.
Main Results:
- The system automatically measured height, length, abdominal circumference, and chest circumference in Huaxi Beef Cattle.
- Achieved average relative errors of 2.32% (height), 2.27% (length), 3.67% (abdominal circumference), and 5.22% (chest circumference) compared to manual measurements.
- Demonstrated high feasibility and accuracy in measuring cattle body sizes across various poses.
Conclusions:
- The proposed multi-view fusion system offers a viable and accurate solution for automatic cattle body size measurement.
- This technology can significantly improve efficiency and reduce costs in livestock farming and growth monitoring.
- The system's robustness to environmental factors and animal posture enhances its practical applicability.
