This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Keypoint-Based Forest Musk Deer Behavioral Recognition Method
by
, ,
Dequan Guo
1
,
Chuankang Chen
1,
Chengli Zheng
2,
Zhenyu Wang
1,3,
Dapeng Zhang
1,3 and
Dening Luo
1,* 1
School of Automation, Chengdu University of Information Technology, Chengdu 610225, China
2
Sichuan Institute of Musk Deer Breeding (Sichuan Institute for Drug Control), Chengdu 611845, China
3
Sichuan Chuanrongda Technology Co., Ltd., Chengdu 610041, China
*
Author to whom correspondence should be addressed.
Animals 2026, 16(11), 1594; https://doi.org/10.3390/ani16111594 (registering DOI)
Submission received: 19 April 2026
/
Revised: 8 May 2026
/
Accepted: 11 May 2026
/
Published: 23 May 2026
(This article belongs to the Special Issue The Application of Artificial Intelligence (AI) in Animal Behavior, Emotion and Health)
Simple Summary
Traditional forest musk deer behavior monitoring relies on manual observation or video playback, which suffers from low efficiency, strong subjectivity, and difficulty in real-time warning, thus restricting breeding and conservation efforts. To address these problems, this study proposes a behavioral recognition method based on an improved YOLOv8-Pose. By constructing a keypoint dataset covering four behaviors and introducing optimized modules, the accuracy of object detection and pose estimation is enhanced, outperforming several existing models. A visual interface is also developed, providing an efficient, low-cost automated analysis tool for the artificial breeding and wild conservation of forest musk deer, thereby contributing to the intelligent protection of endangered species.
Abstract
The traditional monitoring of forest musk deer behavior primarily relies on direct human observation or the post hoc playback analysis of ordinary surveillance videos. This approach is not only time-consuming and labor-intensive but also highly subjective, easily leading to missing or misjudged critical behavioral information. Moreover, it is difficult to achieve real-time monitoring and anomaly warning. These limitations severely constrain the efficiency of the large-scale artificial breeding of forest musk deer and the effective advancement of wild population conservation. Thus, this study proposes a forest musk deer behavioral recognition method based on an improved YOLOv8-Pose. A forest musk deer behavior image dataset covering four typical behaviors was constructed, and 18 keypoints were systematically annotated. This study designs a Dilated Spatial Pyramid Pooling-Fast (DILATED-SPPF) module and a Multi-scale Depthwise Separable Context Mixer (MDSC-Mixer) module, and integrates them into YOLOv8-Pose. Experimental results show that the improved model outperforms the original YOLOv8-Pose and comparison models such as YOLOv11/v12-Pose on key metrics of object detection (Box-mAP50 0.929, Box-mAP50-95 0.814) and pose estimation (Pose-mAP50 0.879, Pose-mAP50-95 0.565). This study further develops a visual interactive interface that intuitively presents detection results and skeleton structures. This work provides a high-precision, low-cost automated behavior analysis tool for the artificial breeding and wild conservation of forest musk deer with significant application value for enhancing the intelligence level of endangered species protection.
