Authors : Bheshaj Prajapati

Volume/Issue : Volume 10 - 2025, Issue 11 - November

Google Scholar : https://tinyurl.com/2rdx52c8

Scribd : https://tinyurl.com/42f66pje

DOI : https://doi.org/10.38124/ijisrt/25nov058

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Note : Google Scholar may take 30 to 40 days to display the article.

Abstract : Stray and domestic animals on roads cause many accidents and traffic issues in India and other developing countries. This paper introduces PawSense, an AI-based alert and detection system aimed at reducing road accidents and protecting animals. The system features a smart AI camera inside the vehicle that detects animals up to 500 meters away. It alerts the driver using built-in audio warnings or adjusts the speed with adaptive cruise control. A secondary subsystem attaches identification RFID or barcode systems to animals to identify ownership. The main results will be fewer animal accidents from vehicle collisions, improved animal safety, and better municipal management. By using computer vision and IoT cloud databases, PawSense can operate independently in terms of resources and finances, supporting the Aatmanirbhar Bharat vision. Research shows that integrated AI systems can decrease animal-related accidents, promote smart mobility, and enhance animal health and safety.

Keywords : AI Detection, Road Safety, Smart Vehicle, Animal Tracking, Computer Vision, IoT, Aatmanirbhar Bharat, RFID Tagging.

References :

1. Redmon, J., Farhadi, A. (2018). YOLOv3: An Incremental Improvement. arXiv preprint arXiv:1804.02767.
2. OpenCV Documentation. (2023). https://opencv.org/
3. TensorFlow. (2023). TensorFlow Open Source Machine Learning Framework. https://www.tensorflow.org/
4. Google Coral TPU Documentation. (2024). https://coral.ai/docs/
5. Indian Road Safety Annual Report. (2023). Ministry of Road Transport and Highways, Government of India.
6. Wu, Z., Zhao, W., Wang, Y., & Li, Y. (2022). Deep Learning–Based Animal Detection Framework for Highway Safety. IEEE Transactions on Intelligent Transportation Systems, 23(10), 18045–18056.
7. Seiler, A. (2005). Predicting locations of moose–vehicle collisions in Sweden. Journal of Applied Ecology, 42(2), 371–382.
8. Huijser, M. P., McGowen, P., Fuller, J., Hardy, A., & Kociolek, A. (2012). Animal–Vehicle Collision Reduction Handbook. U.S. Department of Transportation, FHWA.
9. Kumar, A., & Yadav, P. (2021). “YOLO-Based Animal Detection for Smart Vehicle Safety.” IEEE Access, 9, 8945–8957.
10. MoRTH (2023). Annual Road Safety Report, Ministry of Road Transport and Highways, India.