EUVIMEDEUVIMED entdecken
Crossref

AI-Based Wild Animal Detection and Counting System using Deep Learning and Computer Vision

Dr . Deepak D Bage, Chetan Pustode, Sanjana Lohar, Tejaswini Motghare, Sahil Hase, Tejas More

International Journal of Science, Strategic Management and Technology · 21.04.2026 · 02 (04) · 1-9

DOI: 10.55041/ijsmt.v2i4.368 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Science, Strategic Management and Technology, online erschienen am 21.04.2026. Verfasst von Dr . Deepak D Bage und 5 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Wildlife monitoring and conservation represent critical priorities in the face of unprecedented biodiversity loss across the Indian subcontinent and globally. Traditional methods of manual animal census, camera trap analysis, and ranger patrols are labor-intensive, inconsistent, and limited in spatial coverage. This paper presents a comprehensive AI-based system for automated wild animal detection and counting using state-of-the-art deep learning and computer vision techniques. The proposed framework integrates a YOLOv8-based real-time object detection pipeline with a multi-object tracking module (DeepSORT) and a species classification backbone (EfficientNet-B4) to enable accurate identification and enumeration of wildlife from camera trap images, UAV footage, and live surveillance feeds. The system is specifically optimized for Indian wildlife including Bengal Tigers, Indian Leopards, Asian Elephants, Indian Gaurs, and Sloth Bears across forest habitats in Maharashtra, Madhya Pradesh, and Assam. Experiments conducted on the WildIndia-50K benchmark dataset and a novel dataset collected from Tadoba-Andhari and Pench Tiger Reserves demonstrate detection mAP@0.5 of 91.3% and counting accuracy of 94.7% under diverse environmental conditions. The proposed system introduces the Wildlife Monitoring Accuracy Score (WMAS) as a holistic evaluation metric. Results confirm that the system significantly outperforms existing baselines, offering a scalable, cost-effective tool for forest departments and conservation agencies.

Zitieren

APA

Bage, D. D. D., Pustode, C., Lohar, S., Motghare, T., Hase, S., & More, T. (2026). AI-Based Wild Animal Detection and Counting System using Deep Learning and Computer Vision. International Journal of Science, Strategic Management and Technology, 02(04), 1-9. https://doi.org/10.55041/ijsmt.v2i4.368

Vancouver

Bage DDD, Pustode C, Lohar S, Motghare T, Hase S, More T. AI-Based Wild Animal Detection and Counting System using Deep Learning and Computer Vision. International Journal of Science, Strategic Management and Technology. 2026;02(04):1-9. doi:10.55041/ijsmt.v2i4.368

BibTeX
@article{Bage2026,
  author = {Bage, Dr . Deepak D and Pustode, Chetan and Lohar, Sanjana and Motghare, Tejaswini and Hase, Sahil and More, Tejas},
  title = {AI-Based Wild Animal Detection and Counting System using Deep Learning and Computer Vision},
  journal = {International Journal of Science, Strategic Management and Technology},
  year = {2026},
  volume = {02},
  number = {04},
  pages = {1--9},
  doi = {10.55041/ijsmt.v2i4.368}
}
Kostenlos starten →