Non-contact measurement based on the 3D reconstruction of sheep bodies can alleviate the stress response in sheep during manual measurement of body dimensions. However, data collection is easily affected by environmental factors and noise, which is not conducive to practical production needs. To address this issue, this study proposes a non-contact data acquisition system and a 3D point cloud reconstruction method for sheep bodies. The collected sheep body data can provide reference data for sheep breeding and fattening. The acquisition system consists of a Kinect v2 depth camera group, a sheep passage, and a restraining pen, synchronously collecting data from three perspectives. The 3D point cloud reconstruction method for sheep bodies is implemented based on C++ language and the Point Cloud Library (PCL). It processes noise through pass-through filtering, statistical filtering, and random sample consensus (RANSAC). A conditional voxel filtering box is proposed to downsample and simplify the point cloud data. Combined with the RANSAC and Iterative Closest Point (ICP) algorithms, coarse and fine registration are performed to improve registration accuracy and robustness, achieving 3D reconstruction of sheep bodies. In the base, 135 sets of point cloud data were collected from 20 sheep. After 3D reconstruction, the reconstruction error of body length compared to the actual values was 0.79%, indicating that this method can provide reliable reference data for 3D point cloud reconstruction research of sheep bodies.

Liaoning Cashmere Goats are a high-quality dual-purpose breed valued for both their cashmere and meat. They are also a key national genetic resource for the protection of livestock and poultry in China, with their intensive farming model currently taking shape. Leveraging new productivity advantages and reducing labor costs are urgent issues for intensive breeding. Recognizing goatbehavior in large-scale intelligent breeding not only improves health monitoring and saves labor, but also improves welfare standards by providing management insights. Traditional methods of goat behavior detection are inefficient and prone to cause stress in goats. Therefore, the development of a convenient and rapid detection method is crucial for the efficiency and quality improvement of the industry. This study introduces a deep learning-based behavior recognition and online detection system for Liaoning Cashmere Goats. We compared the convergence speed and detection accuracy of the two-stage algorithm Faster R-CNN and the one-stage algorithm YOLO in behavior recognition tasks. YOLOv8n demonstrated superior performance, converging within 50 epochs with an average accuracy of 95.31%, making it a baseline for further improvements. We improved YOLOv8n through dataset expansion, algorithm lightweighting, attention mechanism integration, and loss function optimization. Our improved model achieved the highest detection accuracy of 98.11% compared to other state-of-the-art (SOTA) target detection algorithms. The Liaoning Cashmere Goat Online Behavior Detection System demonstrated real-time detection capabilities, with a relatively low error rate compared to manual video review, and can effectively replace manual labor for online behavior detection. This study introduces detection algorithms and develops the Liaoning Cashmere Goat Online Behavior Detection System, offering an effective solution for intelligent goat management.

In the real pasture environment, the non-contact estimation of sheep live weight and carcass weight faces challenges such as hair interference, incomplete modal information and difficulty in edge deployment. In this paper, a top-view multi-modal perception and lightweight fusion modeling framework is proposed. The synchronously collected back RGB images, depth maps and point clouds are used as inputs. After unified calibration, time synchronization and standardization of the region of interest, they are sent to the lightweight multi-modal fusion network LMF-Net. The network uses modal-specific coding, multi-scale feature integration and low-rank multi-modal fusion, and introduces a wool thickness adaptive correction module to suppress the geometric deviation caused by thick wool quilts. A total of 3757 valid samples of 148 Hu sheep, including 46 real pasture data sets with carcass weight labels, LMF-Net achieved MAE = 1.03 kg, RMSE = 1.28 kg, R2 = 0.890 for LW task, and MAE = 1.03 kg, RMSE = 1.18 kg, R2 = 0.801 for CW task. WTAC reduces the prediction errors of LW and CW by about 20 % and 17 %, respectively, on high wool index and high surface roughness samples. The number of model parameters is only 5.4 M, and the single-frame inference delay is 28.3 ms, which is significantly better than a variety of single-mode, dual-mode and representative multi-mode methods. The system further integrates the front end of the small program to realize the result display and historical record management, forming a closed loop of ' acquisition-reasoning-output ' application. This framework achieves a good balance between accuracy, robustness and lightweight deployment, and provides a technical solution for non-contact measurement of sheep production performance in intelligent animal husbandry scenarios.