Abstract

This project proposes an intelligent wildlife protection system designed to detect poachers using thermal imaging, drones, and machine learning. By integrating IoT enabled sensors and CNN based recognition models, the system identifies suspicious human presence in protected reserves, enabling faster response and conservation monitoring.

Research Context

Poaching threatens biodiversity and ecological balance worldwide. Traditional monitoring methods are limited in coverage and response time. This research addresses the problem by leveraging automated detection technologies capable of day and night surveillance using infrared imaging and AI-based classification.

Contribution

Role: Team (4-Member group)

Responsibilities included:

• Participating in system concept development

• Researching ML/CNN applications for detection

• Supporting design and experimentation workflow

• Testing and documentation

• Collaboration in technical reporting and presentation

Methodology

• Surveillance via UAVs (drones)

• Infrared/thermal imaging cameras

• IoT-based monitoring infrastructure

• Image classification using CNN

• Detection pipeline distinguishes human/poacher presence

• Technologies involved: Machine Learning, Computer Vision, IoT Integration and Thermal Imaging

Key Findings

• Demonstrated feasibility of automated poacher detection

• Thermal imaging enabled night time surveillance

• Combined IoT + ML improved monitoring coverage

• Validated interdisciplinary approach for conservation tech

Impact

• Exposure to large scale system thinking

• Understanding integration of hardware + AI models

• Improved research and collaboration discipline

• Experience presenting technical solutions for real-world issues

• Reinforced interest in designing impactful technology solutions