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.

This study presents a lightweight visual perception and decision-making method for online apple defect sorting under a “single-camera, three-lane” imaging scenario. Challenges of detecting apple surface defects under long-range imaging and false rejections from single-frame detection are addressed through a combination of approach focusing on defect detection, target association, and trajectory level decision-making. An apple defect dataset was created for the sorting scenario, and an enhanced defect detection model, MOD-DETR was developed by integrating a FasterNet lightweight backbone, an optimization‑stage enhancement network (OSENet), with an adaptive multi‑scale fusion module (AMSF), and a dynamic balanced reparameterization structure (DBRC3) into RT‑DETR, thereby improving defect representation under long‑range conditions. Furthermore, to address the high visual similarity among fruits and kinematically constrained motion trajectories in sorting scenarios, a lightweight tracking method ASORT is proposed. The integration of a trajectory-level multi-frame defect-confirmation strategy effectively reduces instantaneous false positives. Experiments on the custom apple defect dataset showed that MOD-DETR achieved a mAP@50 of 86.7%, 1.5 percentage points higher than that of the baseline model, while reducing GFLOPs by 29.4 and increasing inference speed by 23.8fps. In sorting scenario, the ASORT tracker achieved a MOTA of 97.8% and an IDF1 of 98.9% whereas the system’s overall grading accuracy reached 92.5%, in continuous sorting tests. The results indicate that the proposed method integrates visual perception, target association and rejection control, providing practical solution for apple sorting in small and medium-sized orchards.