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

Non-contact body weight (BW) estimation provides a low-stress and low-cost approach for precision beef cattle management, but single-view RGB images may not fully capture body-shape information. This study proposed a practical dual-view RGB framework for cattle BW estimation. A total of 3210 paired top-view and side-view RGB images were collected from 107 Simmental beef cattle with BW ranging from 169 to 980 kg. An EMA-enhanced YOLO11n-seg model was adopted to improve cattle foreground extraction, and a two-stream CBAM-ResNet50-SE network was constructed to learn dorsal and lateral morphological features for BW regression. The EMA-YOLO11n-seg model achieved mAP@0.5 values of 99.18% and 98.35% for top-view and side-view images, respectively. On the test set, the proposed BW estimation model achieved an MAE of 14.96 kg, an RMSE of 17.86 kg, and an R2 of 0.85. The model also showed stable performance across different growth stages and posture conditions. Adaptation experiments using a Sanhe cattle dataset further demonstrated the adaptability of the proposed framework. These results suggest that the practical dual-view RGB framework developed in this study provides an effective solution for non-contact beef cattle BW estimation under fixed image-acquisition conditions.