ST126: Automated Animal Detection With Repellent System Using AI And Solar

DENISHA/LSEGAR UTEM

The presence of wild animals in urban environments is because they have been able to change their habits to adapt to people's habits. The coexistence of human populations with wildlife often leads to conflicts in which harmful animals cause damage to crops and property and threaten human welfare. Certain limitations influence the effectiveness and environmental impacts of traditional methods used to repel animals. Hence, this project introduces an AI-driven, solar-powered automated system for wildlife detection and humane deterrence inland areas. Addressing the limitations of traditional animal management techniques, the system leverages YOLOv8-based image classification for real-time monitoring and classification of animal species, integrated with IoT for instant notifications and remote control via a Telegram bot. Solar energy ensures sustainable and off-grid operations, reducing reliance on non-renewable resources. Field testing was carried out that demonstrated high detection accuracy (~90%) with buzzer as the deterrent mechanism for proof of concept which may minimise human-wildlife conflicts. This scalable solution not only enhances agricultural security but also aligns with global sustainability goals, offering transformative potential for ecological balance and commercial viability. Future enhancements include expanded species recognition and energy optimization for improved effectiveness.