AI-Based Animal Repellent System for Agricultural Fields Using YOLOv5 and OpenCV for Farmer Safeguard
Year: 2025
Type: article
Abstract: Crop productivity and farmer livelihoods are seriously threatened by wildlife intrusions into agricultural fields, which can result in large financial losses. In order to effectively address this problem, this paper presents an AI-based animal repellent system that combines cutting-edge computer vision and machine learning techniques. The system employs the YOLOv5 object detection algorithm for accurate, real-time animal identification and a high- definition camera to continuously monitor fields. When detected, it triggers species-specific sound alarms to discourage animals and instantly notifies farmers through a Telegram bot, allowing for prompt action. The system is a viable option for farmers in rural regions because it is non-lethal, completely automated, and reasonably priced. Its Python-based framework, which includes PyTorch and OpenCV, guarantees scalability and deployment simplicity. Test findings demonstrate its great efficacy in minimizing crop damage, quick reaction time, and high detection accuracy. This creative strategy bridges the gap between conventional practices and cutting-edge technological solutions to reduce human-wildlife conflict while providing a sustainable and contemporary safeguard for agricultural fields.
DOI: 10.55041/ijsrem44232
Authors: Anusha N S, Chinmayi K N
Language: English
Topic: Smart Agriculture and AI
Subfield: Plant Science
Domain: Life Sciences
SDGs: Zero hunger, Life on land
Open Access status: bronze
OpenAlex ID: W4409397269