Yangfan Bai

Accurate measurement of sheep body dimensions is fundamental for growth monitoring and breeding management. To address the limited segmentation accuracy and the trade-off between lightweight design and precision in existing non-contact measurement methods, this study proposes an improved model, YOLOv12n-Seg-SSM, for the automatic measurement of body height, body length, and chest circumference from side-view images of sheep. The model employs a synergistic strategy that combines semantic segmentation with 3D point cloud geometric fitting. It incorporates the SegLinearSimAM feature enhancement module, the SEAttention channel optimization module, and the ENMPDIoU loss function to improve measurement robustness under complex backgrounds and occlusions. After segmentation, valid RGB-D point clouds are generated through depth completion and point cloud filtering, enabling 3D computation of key body measurements. Experimental results demonstrate that the improved model outperforms the baseline YOLOv12n-Seg: the mAP@0.5 for segmentation reaches 94.20%, the mAP@0.5 for detection reaches 95.00% (improvements of 0.5 and 1.3 percentage points, respectively), and the recall increases to 99.00%. In validation tests on 43 Hu sheep, the R² values for chest circumference, body height, and body length were 0.925, 0.888 and 0.819, respectively, with measurement errors within 5%. The model requires only 10.71 MB of memory and 9.9 GFLOPs of computation, enabling real-time operation on edge devices. This study demonstrates that the proposed method achieves non-contact automatic measurement of sheep body dimensions, providing a practical solution for on-site growth monitoring and intelligent management in livestock farms.

This study, conducted in the Lifang Dryland Experimental Area in Jinzhong, Shanxi Province, China, aimed to develop a method to accurately predict maize yield by combining UAV multispectral data with meteorological information. A DJI Mavic 3M UAV was used to capture four-band imagery (red, green, red-edge, and near-infrared), from which 16 vegetation indices were calculated, along with daily meteorological data. Among eight machine learning algorithms tested, ensemble models, Random Forest and Gradient Boosting Trees performed best, with R² values of 0.8696 and 0.8163, respectively. SHAP analysis identified MSR and RVI as the most important features. The prediction accuracy varied across growth stages, with the jointing stage showing the highest performance (R² = 0.7161), followed by the flowering stage (R² = 0.6588). The yield exhibited a strip-like spatial distribution, ranging from 6450 to 9600 kg·ha⁻¹, influenced by field management, soil characteristics, and microtopography. K-means clustering revealed high-yield areas in the central-northern region and low-yield areas in the south, supported by a global Moran’s I index of 0.4290, indicating moderate positive spatial autocorrelation. This study demonstrates that integrating UAV multispectral data, meteorological information, and machine learning can achieve accurate yield prediction (with a relative RMSE of about 2.8%) and provides a quantitative analytical framework for spatial management in drought-prone areas.

Accurate and non-contact identification of individual sheep is important for intelligent livestock management, but remains challenging due to subtle inter-individual differences, breed-dependent facial morphology, and complex farm environments. This study proposes a lightweight sheep face detection and keypoint recognition framework based on an improved YOLO11 architecture, termed SAMS-KLA-YOLO11. The model incorporates a Sheep Adaptive Multi-Scale Convolution (SAMSConv) module to enhance feature extraction across breed-dependent facial scales, a Keypoint-Aware Lightweight Attention (KLAttention) mechanism to emphasize biologically discriminative facial landmarks, and the Efficient IoU (EIoU) loss to stabilize bounding box regression. A dataset of 3860 images from 68 individuals belonging to three breeds (Hu, Dorper, and Dorper × Hu crossbreeds) was collected under unconstrained farm conditions and annotated with five facial keypoints. On this dataset, the proposed model achieves higher precision, recall, and mAP than several mainstream YOLO-based baselines, while reducing FLOPs and parameter count compared with the original YOLO11. Additional ablation experiments confirm that each proposed module provides complementary benefits, and OKS-based evaluation shows accurate facial keypoint localization. All results are obtained on a single, site-specific dataset without external validation or on-device deployment benchmarks, so the findings should be viewed as an initial step toward practical sheep face recognition rather than definitive evidence of large-scale deployment readiness.

Near-infrared (NIR) spectroscopy is a rapid, non-destructive tool widely used in agriculture, but limited labeled spectra often constrain model robustness. To address this, we propose using denoising diffusion probabilistic models (DDPMs) for NIR data augmentation. Leveraging the SpectraFood leek dataset, a conditional MLP-DDPM was trained to generate realistic synthetic spectra guided by dry matter content. Incorporating 1000 generated spectra into the training set improved the predictive performance of PLSR, RF, and XGBoost models, demonstrating enhanced generalization and robustness. Compared with WGAN, DDPM offered higher stability and fidelity, effectively expanding the calibration space without introducing unrealistic patterns. Future work will explore conditional and hybrid diffusion frameworks, integrating environmental and physiological covariates, and cross-domain spectral transfer, extending the applicability of DDPMs for diverse crops and precision agriculture scenarios.