<![CDATA[The Asian palm civet (Paradoxurus hermaphroditus) plays a crucial role in the ecosystem as a seed disperser and has economic value in the civet coffee industry. However, monitoring civet activity in captivity is still conducted manually, which is time-consuming and prone to human error. This study aims to develop an automatic monitoring system based on Computer Vision using the YOLOv8 method with the Python programming language. The system can detect civet activities such as eating, drinking, moving, and sleeping through surveillance cameras in real time. The model was trained using a specialized dataset collected from civet enclosures under various lighting conditions and camera angles. Evaluation results show that the model achieved a mean Average Precision (mAP) of 99.5%, precision of 100%, and recall of 99.3%, indicating excellent detection capability. The implementation of this system is expected to assist captive management in monitoring efficiently, reducing reliance on manual supervision, and improving animal welfare through more accurate observation. Furthermore, this system has the potential to be further developed for real-time video-based monitoring and applied to other animal species. Thus, this study not only contributes to the efficiency of Asian palm civet monitoring but also opens opportunities for the application of Computer Vision technology in conservation and wildlife-based industries.]]>
Copyrights © 2025
