Traffic Light Recognition using Convolutional Neural Networks: A Survey
Not on the map. Why?
Abstract (arXiv)
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 rule-based 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.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 30 of its 87 references that are in the map. First posted on arXiv 5 Sep 2023.
Builds on
30 of 87 references.
References · 30
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
- 2014Microsoft COCO: Common Objects in Contextcited by 17,498
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
- 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
- 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
- 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
- 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
- 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
- 2022A ConvNet for the 2020scited by 3,545
- 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
- 2015SSD: Single Shot MultiBox Detectorcited by 3,125
18 more
- 2018YOLOv3: An Incremental Improvementcited by 2,652
- 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,624
- 2016YOLO9000: Better, Faster, Strongercited by 1,429
- 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,282
- 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,194
- 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,054
- 2016Training Region-based Object Detectors with Online Hard Example Miningcited by 577
- 2016R-FCN: Object Detection via Region-based Fully Convolutional Networkscited by 414
- 2020U2-Net: Going Deeper with Nested U-Structure for Salient Object Detectioncited by 410
- 2016ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentationcited by 291
- 2013OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networkscited by 224
- 2020SCRDet++: Detecting Small, Cluttered and Rotated Objects via Instance-Level Feature Denoising and Rotation Loss Smoothingcited by 62
- 2023Salient Sign Detection In Safe Autonomous Driving: AI Which Reasons Over Full Visual Contextcited by 14
- 2023Robust Traffic Light Detection Using Salience-Sensitive Loss: Computational Framework and Evaluationscited by 11
- 2018Detecting Traffic Lights by Single Shot Detectioncited by 8
- 2019Traffic Light Recognition Using Deep Learning and Prior Maps for Autonomous Carscited by 8
- 2018A Hierarchical Deep Architecture and Mini-Batch Selection Method For Joint Traffic Sign and Light Detectioncited by 6
- 2022Towards Real-time Traffic Sign and Traffic Light Detection on Embedded Systemscited by 3
Built on by
Citing papers per year: 2024: 1; 2025: 2.
3 papers.