In modern large-scale pig farming, accurately identifying sow estrus and ensuring timely breeding are crucial for maximizing economic benefits. However, the short duration of estrus and the reliance on subjective human judgment pose significant challenges for precise insemination timing. To enable non-contact, automated estrus detection, this study proposes an improved algorithm, Enhanced Context-Attention YOLO (ECA-YOLO), based on YOLOv11. The model utilizes ocular appearance features—eye’s spirit, color, shape, and morphology—across different estrus stages as key indicators. The MSCA module enhances small-object detection efficiency, while the PPA and GAM modules improve feature extraction capabilities. Additionally, the Adaptive Threshold Focal Loss (ATFL) function increases the model’s sensitivity to hard-to-classify samples, enabling accurate estrus stage classification. The model was trained and validated on a dataset comprising 4461 images of sow eyes during estrus and was benchmarked against YOLOv5n, YOLOv7tiny, YOLOv8n, YOLOv10n, YOLOv11n, and Faster R-CNN. Experimental results demonstrate that ECA-YOLO achieves a mean average precision (mAP) of 93.2%, an F1-score of 88.0%, with 5.31M parameters, and FPS reaches 75.53 frames per second, exhibiting superior overall performance. The findings confirm the feasibility of using ocular features for estrus detection and highlight the potential of ECA-YOLO for real-time, accurate monitoring of sow estrus under complex farming conditions. This study lays the groundwork for automated estrus detection in intensive pig farming.

Accurate estrus detection and optimal insemination timing are crucial for improving sow productivity and enhancing farm profitability in intensive pig farming. However, sows’ estrus typically lasts only 48.4 ± 1.0 h, and interference from false estrus further complicates detection. This study proposes an enhanced YOLOv8 model, Integrated Convolution and Attention Enhancement (ICAE), for vulvar detection to identify the estrus stages. This model innovatively divides estrus into three phases (pre-estrus, estrus, and post-estrus) and distinguishes five different estrus states, including pseudo-estrus. ICAE-YOLO integrates the Convolution and Attention Fusion Module (CAFM) and Dual Dynamic Token Mixing (DDTM) for improved feature extraction, Dilation-wise Residual (DWR) for expanding the receptive field, and Focaler-Intersection over Union (Focaler-IoU) for boosting the performance across various detection tasks. To validate the model, it was trained and tested on a dataset of 6402 sow estrus images and compared with YOLOv8n, YOLOv5n, YOLOv7tiny, YOLOv9t, YOLOv10n, YOLOv11n, and the Faster R-CNN. The results show that ICAE-YOLO achieves an mAP of 93.4%, an F1-Score of 92.0%, GFLOPs of 8.0, and a model size of 4.97 M, reaching the highest recognition accuracy among the compared models, while maintaining a good balance between model size and performance. This model enables accurate, real-time estrus monitoring in complex, all-weather farming environments, providing a foundation for automated estrus detection in intensive pig farming.

Addressing the carbon footprint in pig production is a fundamental technical basis for achieving carbon neutrality and peak carbon emissions. Only by systematically studying the carbon footprint can the goals of carbon neutrality and peak carbon emissions be effectively realized. This study aims to reduce the carbon footprint through optimized feeding strategies based on minimizing carbon emissions. To this end, this study conducted a full-lifecycle monitoring of the carbon footprint during pig growth from December 2024 to May 2025, optimizing feeding strategies using a real-time pig weight estimation model driven by deep learning to reduce resource consumption and the carbon footprint. We introduce EcoSegLite, a lightweight deep learning model designed for non-contact real-time pig weight estimation. By incorporating ShuffleNetV2, Linear Deformable Convolution (LDConv), and ACmix modules, it achieves high precision in resource-constrained environments with only 1.6 M parameters, attaining a 96.7% mAP50. Based on full-lifecycle weight monitoring of 63 pigs at the Pianguan farm from December 2024 to May 2025, the EcoSegLite model was integrated with a life cycle assessment (LCA) framework to optimize feeding management. This approach achieved a 7.8% reduction in feed intake, an 11.9% reduction in manure output, and a 5.1% reduction in carbon footprint. The resulting growth curves further validated the effectiveness of the optimized feeding strategy, while the reduction in feed and manure also potentially reduced water consumption and nitrogen runoff. This study offers a data-driven solution that enhances resource efficiency and reduces environmental impact, paving new pathways for precision agriculture and sustainable livestock production.

Timely and accurate detection of sow oestrus is crucial for enhancing reproductive efficiency and reducing non-productive days (NPDs) in large-scale pig farms. However, traditional manual observation is labour-intensive and subjective, while cloud-based deep learning solutions face challenges such as high latency and privacy risks when applied in intensive housing environments. This study developed an edge-intelligent monitoring system that integrates deep temporal modelling with sound source localisation technology. A three-stage hierarchical screening strategy was utilised to select and deploy a lightweight Stacked-LSTM model on the resource-constrained ESP32-S3 hardware platform. This model was trained and calibrated using a high-quality acoustic dataset validated against serum reproductive hormones, specifically follicle-stimulating hormone (FSH), luteinising hormone (LH), and progesterone ($P_4$). Experimental results demonstrate that the optimised model achieved a classification accuracy of 96.17%, with an inference latency of only 41 ms, thereby fully satisfying the stringent real-time monitoring requirements while maintaining a minimal memory footprint. Furthermore, the system integrates a localisation algorithm based on Generalised Cross-Correlation with Phase Transform (GCC-PHAT). Through spatial geometric modelling, the system successfully implements the functional mapping of vocalisation events to individual gestation stalls (Stall IDs). Laboratory pressure tests validated the robustness and low-cost deployment advantages of the “edge recognition–cloud synchronization” architecture, providing a reliable technical framework for the precision management of smart livestock farming.

Pigs’ facial regions encode a wealth of biological trait information; detecting their facial poses can provide robust support for individual identification and behavioral analysis. However, in large-scale swine-herd settings, variable lighting within pigsties and the close proximity of animals impose significant challenges on facial-pose detection. This study adopts an aerial-inspection approach—distinct from conventional ground or hoist inspections—leveraging the high-efficiency, panoramic coverage of unmanned aerial vehicles (UAVs). UAV-captured video frames from real herding environments, involving a total of 600 pigs across 50 pens, serve as the data source. The final dataset comprises 2800 original images, expanded to 5600 after augmentation, to dissect how different facial expressions reflect pig physiological states.ion. 1. The proposed Detect_FASFF detection head achieves mean average precision at 50% IoU (mAP₅₀) of 95.5% for large targets and 95.9% for small targets, effectively overcoming cross-scale feature loss and the accuracy shortcomings of the baseline YOLOv8s in detecting pig facial targets. 2. Addressing the excessive computation and sluggish inference of standard YOLOv8, we incorporate a Partial_Conv module that maintains mAP while substantially reducing Runtime. 3. We introduce an improved exponential moving-average scheme (iEMA) with second-order attention to improve small-target accuracy and mitigate interference from the piggery environment. This yields an mAP₅₀ of 96.4%. 4. Comprehensive comparison–The refined YOLOv8 is benchmarked against traditional YOLO variants (YOLOv5s, YOLOv8s, YOLOv11s, YOLOv12s, YOLOv13s), Rt-DeTR, and Faster-R-CNN. Relative to these models, the enhanced YOLOv8 shows a statistically significant increase in overall mAP. These results highlight the potential of the upgraded model to transform pig facial-expression recognition accuracy, advancing more humane and informed livestock-management practices.

Accidental crushing by sows is the primary cause of pre-weaning piglet mortality in intensive production, often due to the spatiotemporal lag of manual inspection. While Internet of Things (IoT) solutions exist, they frequently face challenges such as vision occlusion, high hardware costs, and latency. To address these, this study developed a low-cost multi-modal edge computing system based on TinyML. Using an ESP32-S3 microcontroller, the system employs a “Motion-Gated Acoustic Detection” strategy, activating a lightweight 1D-CNN model to identify piglet screams only when an IMU detects high-risk postural transitions of the sow. Results show the quantized model (5.1 KB) achieves 95.56% accuracy and 2 ms inference latency. The total end-to-end response latency is within 179 ms, ensuring intervention within the early “golden rescue window.” The low-power design enables the battery life to cover the entire lactation period. Field tests demonstrated that the system intercepted identified crushing risks within the monitored cohort, supporting its potential for significantly improving piglet survival probability. This research overcomes the limitations of single-modal monitoring and provides a scalable, cost-effective engineering intervention for enhancing animal welfare and achieving intelligent, unattended supervision in precision livestock farming.