Although rectal temperature is reliable, its measurement requires manual handling and causes stress to animals. IRT provides a non-contact alternative but often ignores bilateral eye temperature differences. This study presents an E-S-YOLO11n model for the automated detection of the binocular regions of sheep, which achieves remarkable performance with a precision of 98.2%, recall of 98.5%, mAP@0.5 of 99.40%, F₁ score of 98.35%, FPS of 322.58 frame/s, parameters of 7.27 M, model size of 3.97 MB, and GFLOPs of 1.38. Right and left eye temperatures exhibit a strong correlation (r = 0.8076, p < 0.0001), However, the eye temperatures show only very weak correlation with rectal temperature (right eye: r = 0.0852; left eye: r = −0.0359), and neither figure reaches statistical significance. Rectal temperature is 7.37% and 7.69% higher than the right and left eye temperatures, respectively. Additionally, the right eye temperature is slightly higher than the left eye (p < 0.01). The study demonstrates the feasibility of combining IRT and deep learning for non-invasive eye temperature monitoring, although environmental factors may limit it as a proxy for rectal temperature. These results support the development of efficient thermal monitoring tools for precision animal husbandry.

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.