Related Experiment Video
Updated: Jul 16, 2026
12:08
The Use of Traditional Fear Tests to Evaluate Different Emotional Circuits in Cattle
Published on: April 22, 2020
Recent Advances in Vision-Based Beef Cattle Body Measurement Technologies.
Xiaofan Deng1, Fuli Zhang1, Gang Jin1
1Tianjin Key Laboratory of High Performance Manufacturing Technology and Equipment, School of Mechanical Engineering, Tianjin University of Technology and Education, Tianjin 300222, China.
Animals : an Open Access Journal From MDPI
|July 15, 2026
Summary
Vision-based methods offer automated beef cattle body measurement, crucial for livestock farming. While 2D, 3D, and multi-view approaches show promise, challenges in data, validation, and application remain for precision livestock farming.
Area of Science:
- Agricultural Science
- Computer Vision
- Animal Science
Background:
- Accurate beef cattle body measurements are vital for growth assessment, breeding, and precision livestock farming.
- Traditional manual measurements are inefficient, stressful for animals, and unsuitable for large-scale operations.
Purpose of the Study:
- To systematically review and summarize research progress in vision-based beef cattle body measurement techniques.
- To analyze the strengths, weaknesses, and farm applicability of different visual measurement approaches.
Main Methods:
- Structured systematic literature review following PRISMA 2020 guidelines.
- Focused on 2D image-based, 3D (RGB-D, LiDAR), and multi-view fusion measurement techniques.
- Analyzed key technologies: image segmentation, keypoint detection, point cloud processing, 3D reconstruction, and geometric calculations.
Main Results:
- 2D methods are cost-effective but limited for 3D parameters.
- RGB-D and LiDAR offer spatial data but face noise, occlusion, and cost issues.
- Multi-view fusion enhances data completeness but requires complex calibration and integration.
Conclusions:
- Current vision-based methods face challenges including data scarcity, annotation inconsistencies, and limited real-world validation.
- Future research should prioritize standardized datasets, cross-scenario validation, multimodal perception, and edge computing for intelligent livestock monitoring.
