Λεπτομέρειες βιβλιογραφικής εγγραφής
| Τίτλος: |
Low-Altitude UAV-Based Recognition of Porcine Facial Expressions for Early Health Monitoring. |
| Συγγραφείς: |
Wang, Zhijiang, Mi, Ruxue, Liu, Haoyuan, Yi, Mengyao, Fan, Yanjie, Hu, Guangying, Liu, Zhenyu |
| Πηγή: |
Animals (2076-2615); Dec2025, Vol. 15 Issue 23, p3426, 26p |
| Θεματικοί όροι: |
Emotion recognition, Swine, Early diagnosis, Animal welfare, Agricultural drones, Patient monitoring, Object recognition (Computer vision), Livestock productivity |
| Περίληψη: |
Simple Summary: This study targets the critical challenges of pig facial expression recognition in large-scale swine-herd environments and proposes a detection method that couples active-flight inspection with a refined YOLOv8 architecture. The aim is to improve the accuracy and efficiency of automated health monitoring in pigs, focusing on the identification of symptoms associated with common conditions such as cold, fever, and cough. To ensure clinical relevance, the labeling of health-related symptoms was verified using a combination of on-site veterinary assessment and auxiliary tools including infrared thermometry (for fever) and clinical observation protocols. By integrating the Detect_FASFF, PartialConv, and iEMA modules, the improved model attains mean average precision at a 50% IoU threshold (mAP50) of 95.5%/95.9%, 95.6%, and 96.4%, respectively, surpassing conventional models by a substantial margin. The results demonstrate that the lightweight, high-precision detector can trigger early disease alerts and support intelligent herd management. This advancement has important implications for improving animal welfare and fostering sustainable livestock production. 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. [ABSTRACT FROM AUTHOR] |
|
Copyright of Animals (2076-2615) is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| Βάση Δεδομένων: |
Complementary Index |