Auto Track: Smart Aerial Object Tracking with Deep Learning

This paper presents the design and implementation of an intelligent drone system using a DJI Tello quadcopter integrated with computer vision and AI-based algorithms for real-time object following, obstacle avoidance, and gesture control.Leveraging YOLO-based object detection [2] and reinforcement learning-driven gesture recognition [1], the proposed framework enhances the autonomous capabilities of low-cost drones.The study also introduces a lightweight ducted propellers design to ensure stability and safety without exceeding payload limits.Experimental results demonstrate the efficiency of the system in achieving accurate tracking, responsive obstacle avoidance, and intuitive gesture-based control, thereby showcasing its potential in surveillance, disaster response, and human-drone interaction.