Robot Real-time Pedestrian Tracking Algorithm based on Deep Learning

In recent years, deep learning models have greatly improved the performance of pedestrian detection and tracking. Although the accuracy of neural network-based modeling methods is high, they often require large computational and storage resource overheads, which makes them difficult to apply to robots with high resource requirements. Pedestrian tracking for robots still faces great challenges in the problems of occlusion, multi-target, and target loss. In this thesis, we focus on solving the problem of real-time pedestrian tracking by lightweight fusion of deep learning target detection models for robots, firstly, through the lightweight YOLO network, we perform pedestrian detection and feature extraction, and then we propose a Gaussian mixture model based feature matching method to construct the target pedestrian tracker, and finally, we use the PID-based control algorithm for real-time control of the robot's motion, and finally realize the real-time pedestrian Tracking. In this thesis, we validate the feature matching method based on the Gaussian mixture model on the ETH dataset, and at the same time, combined with the motion control algorithm, we carry out the actual validation, and the experimental results show that our proposed method can realize the real-time pedestrian tracking.