Towards Real-time Traffic Sign and Traffic Light Detection on Embedded Systems

Jayasinghe, Oshada; Hemachandra, Sahan; Anhettigama, Damith; Kariyawasam, Shenali; Wickremasinghe, Tharindu; Ekanayake, Chalani; Rodrigo, Ranga; Jayasekara, Peshala

doi:10.1109/iv51971.2022.9827355

Cited by 9 publications

(1 citation statement)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Jayasinghe et al [60] used a two-stage approach, where detection was performed either with Faster R-CNN with a ResNet-50 backbone or SSD with MobileNetv2 backbone, and the classification was done with ResNet-18.…”

Section: B Multi-stage Approachesmentioning

confidence: 99%

German Traffic Sign Recognition Using Convolutional Neural Network

Santosh¹,

Kumar²,

Sandeep³

et al. 2022

2022 6th International Conference on Electronics, Communication and Aerospace Technology

View full text Add to dashboard Cite

Real-time traffic light recognition is essential for autonomous driving. Yet, a cohesive overview of the underlying model architectures for this task is currently missing. In this work, we conduct a comprehensive survey and analysis of traffic light recognition methods that use convolutional neural networks (CNNs). We focus on two essential aspects: datasets and CNN architectures. Based on an underlying architecture, we cluster methods into three major groups: (1) modifications of generic object detectors which compensate for specific task characteristics, (2) multi-stage approaches involving both rulebased and CNN components, and (3) task-specific single-stage methods. We describe the most important works in each cluster, discuss the usage of the datasets, and identify research gaps.

show abstract

Section: B Multi-stage Approachesmentioning

confidence: 99%