Sustainable Wildlife Movement Detection and Crop Protection System

Abstract

Wildlife intrusion into farmlands poses a major threat to agricultural productivity and farmer safety, particularly in regions bordering forest areas. Traditional preventive measures such as fencing, ultrasonic repellents, and surveillance cameras are often costly, energy-intensive, and unreliable under low-light or complex environmental conditions. To address these limitations, this project proposes a Sustainable Wildlife Movement Detection and Crop Protection System that integrates IoT and AI for intelligent, eco-friendly, and automated crop protection. The proposed system employs a YOLO-based object detection algorithm for real-time identification and classification of animals from live camera feeds. The detected animal behavior and movement patterns are analyzed to assess threat levels. Based on this analysis, appropriate eco-friendly deterrents including sound, light, or eco-friendly fog/spray mechanisms are automatically activated to drive away the animals without causing harm. An offline alert mechanism ensures that nearby farmers receive notifications even in areas with limited or no internet connectivity. Additionally, a farmer-friendly dashboard provides live intrusion alerts, detection history, and manual control options. By integrating YOLO-based AI detection, IoT-based automation, and sustainable deterrent mechanisms, the proposed system offers a low-cost, scalable, and intelligent solution that minimizes crop losses, enhances farmer safety, and fosters coexistence between humans and wildlife.