YOLO-ORE: A Deep Learning-Aided Object Recognition Approach for Radar Systems
Tai-Yuan Huang, Ming‐Chun Lee, Chia-Hsing Yang, Ta-Sung Lee
Abstract
To enable intelligent vehicles and transportation systems, the vehicles and relevant systems need to have the ability to sense environment and recognize objects. In order to benefit from the robustness of radar for sensing, knowing how to use the radar system for effective object recognition is critical. Observing this, we in this paper propose a novel deep learning-aided object recognition system for radar systems by combining the You only look once (YOLO) system with a proposed object recheck system. Our proposed system is able to benefit from conventional YOLO and also mitigate the overlap errors and misclassification errors induced by using YOLO. We conduct extensive real-world experiments in realistic scenarios to evaluate our proposed object recognition system. Results validate that our system can provide good performance in complicated real-world scenarios. The results also show that our proposed object recognition system can outperform the state-of-the-art learning-based object recognition systems.