What question did this study set out to answer?

To develop and evaluate a practical, non-contact dual-view RGB image framework for accurate beef cattle body weight estimation.

August 15, 2026AnimalsOpen Access

Beef Cattle Body Weight Estimation Based on Dual-View RGB Images

View Full Paper

Ask AI

Bookmark

Authors

ZLZiruo LiMinistry of Agriculture and Rural Affairs YZYadan ZhangMinistry of Agriculture and Rural Affairs CYChong YaoMinistry of Agriculture and Rural Affairs

Discussion

Member takes

Overview

Machine learning study demonstrates non-contact body weight estimation in beef cattle via dual-view RGB images, indicating a viable method for precision livestock management.

Key Points

To develop and evaluate a practical, non-contact dual-view RGB image framework for accurate beef cattle body weight estimation.
Collected 3,210 paired top-view and side-view RGB images from 107 Simmental beef cattle with body weights ranging from 169 to 980 kg.
Used an EMA-enhanced YOLO11n-seg model for foreground cattle segmentation and a two-stream CBAM-ResNet50-SE network to extract dorsal and lateral features for weight regression.
Assessed performance across growth stages, postures, and an external adaptation dataset of Sanhe cattle.
The EMA-YOLO11n-seg model achieved mAP@0.5 scores of 99.18% for top-view images and 98.35% for side-view images.
The body weight estimation framework achieved an MAE of 14.96 kg, an RMSE of 17.86 kg, and an R² of 0.85 on the test set.

Cite This Study

Li et al. (2026) studied this question.

synapsesocial.com/papers/6a8019fe75c2e31742c8654f https://doi.org/10.3390/ani16162532

View Full Paper

Ask AI

Bookmark

August 15, 2026AnimalsOpen Access

Beef Cattle Body Weight Estimation Based on Dual-View RGB Images

View Full Paper

Ask AI

Bookmark

Authors

ZLZiruo LiMinistry of Agriculture and Rural Affairs YZYadan ZhangMinistry of Agriculture and Rural Affairs CYChong YaoMinistry of Agriculture and Rural Affairs

Discussion

Member takes

Overview

Machine learning study demonstrates non-contact body weight estimation in beef cattle via dual-view RGB images, indicating a viable method for precision livestock management.

Key Points

To develop and evaluate a practical, non-contact dual-view RGB image framework for accurate beef cattle body weight estimation.
Collected 3,210 paired top-view and side-view RGB images from 107 Simmental beef cattle with body weights ranging from 169 to 980 kg.
Used an EMA-enhanced YOLO11n-seg model for foreground cattle segmentation and a two-stream CBAM-ResNet50-SE network to extract dorsal and lateral features for weight regression.
Assessed performance across growth stages, postures, and an external adaptation dataset of Sanhe cattle.
The EMA-YOLO11n-seg model achieved mAP@0.5 scores of 99.18% for top-view images and 98.35% for side-view images.
The body weight estimation framework achieved an MAE of 14.96 kg, an RMSE of 17.86 kg, and an R² of 0.85 on the test set.

Cite This Study

Li et al. (2026) studied this question.

synapsesocial.com/papers/6a8019fe75c2e31742c8654f https://doi.org/10.3390/ani16162532

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark