Scholarlink

<p>Wildlife safaris are unique, but vast terrains, unpredictable animal movements and poor communication reduce their effectiveness. This study proposes a real-time wildlife detection and tracking system using the YOLOv8 object detection model. The system was trained on a dataset of 9000 images to detect animals such as tigers, deer, elephants and delivers instant notifications with animal type, detection time and location. After 100 epochs the model achieved an 89.26% accuracy, 81.70% sensitivity, 83.60% precision and 91.50% specificity. YOLOv8’s anchor-free architecture combined with advanced data augmentation enables reliable detection even under dense vegetation and low-light conditions. This system enhances safari management, reduces unnecessary vehicle movement and contributes to sustainable tourism and conservation.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Automated approach for wildlife detection and tracking using YOLOv8 deep learning algorithm

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年12月16日

查看全文
  • Namratha Nagaraj,
  • R. Likhitha,
  • B. N. Indu,
  • R. V. Manjunath

摘要

Wildlife safaris are unique, but vast terrains, unpredictable animal movements and poor communication reduce their effectiveness. This study proposes a real-time wildlife detection and tracking system using the YOLOv8 object detection model. The system was trained on a dataset of 9000 images to detect animals such as tigers, deer, elephants and delivers instant notifications with animal type, detection time and location. After 100 epochs the model achieved an 89.26% accuracy, 81.70% sensitivity, 83.60% precision and 91.50% specificity. YOLOv8’s anchor-free architecture combined with advanced data augmentation enables reliable detection even under dense vegetation and low-light conditions. This system enhances safari management, reduces unnecessary vehicle movement and contributes to sustainable tourism and conservation.