Comparison of Object Recognition Approaches using Traditional Machine Vision and Modern Deep Learning Techniques for Mobile Robot

摘要

In this paper, we consider the problem of object recognition for a mobile robot in an indoor environment using two different vision approaches. Our first approach uses HOG descriptor with SVM classifier as traditional machine vision model while the second approach uses Tiny-YOLOv3 as modern deep learning model. The purpose of this study is to gain intuitive insight of both approaches for understanding the principles behind these techniques through their practical implementation in real world. We train both approaches with our own dataset for doors. The proposed work is assessed through the real-world implementation of both approaches using mobile robot with Zed camera in real world indoor environment and the robustness has been evaluated by comparing and analyzing the experimental results of both models on same dataset.