YOLO-PPA based Efficient Traffic Sign Detection for Cruise Control in Autonomous Driving

TL;DR

This paper introduces a YOLO-PPA based method for efficient and accurate traffic sign detection in autonomous driving, especially for small and distant signs, improving inference speed and detection accuracy on embedded devices.

Contribution

The paper proposes a novel YOLO-PPA architecture that enhances traffic sign detection performance and efficiency, addressing challenges of small object detection and embedded device limitations.

Findings

11.2% improvement in inference efficiency

93.2% increase in mAP 50 accuracy

Effective detection of small and distant traffic signs

Abstract

It is very important to detect traffic signs efficiently and accurately in autonomous driving systems. However, the farther the distance, the smaller the traffic signs. Existing object detection algorithms can hardly detect these small scaled signs.In addition, the performance of embedded devices on vehicles limits the scale of detection models.To address these challenges, a YOLO PPA based traffic sign detection algorithm is proposed in this paper.The experimental results on the GTSDB dataset show that compared to the original YOLO, the proposed method improves inference efficiency by 11.2%. The mAP 50 is also improved by 93.2%, which demonstrates the effectiveness of the proposed YOLO PPA.