Comparative Analysis of Deep Learning Models for Perception in Autonomous Vehicles
Jalal Khan
TL;DR
The paper evaluates two state-of-the-art deep-learning detectors, YOLOv8s and YOLO-NAS, for perception tasks in autonomous vehicles on a custom road dataset. It documents training/setup details and uses mAP and confusion matrices to compare performance. The results show YOLOv8s trains faster and achieves higher final accuracy, with more stable learning curves, while YOLO-NAS performs relatively better on some vulnerable road-user classes. The findings guide model selection and hint at beneficial ensemble strategies for robust AV perception.
Abstract
Recently, a plethora of machine learning (ML) and deep learning (DL) algorithms have been proposed to achieve the efficiency, safety, and reliability of autonomous vehicles (AVs). The AVs use a perception system to detect, localize, and identify other vehicles, pedestrians, and road signs to perform safe navigation and decision-making. In this paper, we compare the performance of DL models, including YOLO-NAS and YOLOv8, for a detection-based perception task. We capture a custom dataset and experiment with both DL models using our custom dataset. Our analysis reveals that the YOLOv8s model saves 75% of training time compared to the YOLO-NAS model. In addition, the YOLOv8s model (83%) outperforms the YOLO-NAS model (81%) when the target is to achieve the highest object detection accuracy. These comparative analyses of these new emerging DL models will allow the relevant research community to understand the models' performance under real-world use case scenarios.