# Detecting Traffic Lights by Single Shot Detection

arXiv: https://arxiv.org/abs/1805.02523 · HTML: https://mlsanity.com/paper/1805.02523/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 May 2018.

## Built on by (most cited first, 8 of 8)

- [Radar-Camera Fusion for Object Detection and Semantic Segmentation in Autonomous Driving: A Comprehensive Review](https://mlsanity.com/paper/2304.10410/) (2023)
- [TLD-READY: Traffic Light Detection -- Relevance Estimation and Deployment Analysis](https://mlsanity.com/paper/2409.07284/) (2024)
- [Traffic Light Recognition using Convolutional Neural Networks: A Survey](https://mlsanity.com/paper/2309.02158/) (2023)
- [DualCam: A Novel Benchmark Dataset for Fine-grained Real-time Traffic Light Detection](https://mlsanity.com/paper/2209.01357/) (2022)
- [Small, but important: Traffic light proposals for detecting small traffic lights and beyond](https://mlsanity.com/paper/2307.15191/) (2023)
- [Fool the Stoplight: Realistic Adversarial Patch Attacks on Traffic Light Detectors](https://mlsanity.com/paper/2506.04823/) (2025)
- [Exploring Self-Attention for Visual Intersection Classification](https://mlsanity.com/paper/2203.13977/) (2022)
- [TigAug: Data Augmentation for Testing Traffic Light Detection in Autonomous Driving Systems](https://mlsanity.com/paper/2507.05932/) (2025)

## Abstract (arXiv)

Recent improvements in object detection are driven by the success of convolutional neural networks (CNN). They are able to learn rich features outperforming hand-crafted features. So far, research in traffic light detection mainly focused on hand-crafted features, such as color, shape or brightness of the traffic light bulb. This paper presents a deep learning approach for accurate traffic light detection in adapting a single shot detection (SSD) approach. SSD performs object proposals creation and classification using a single CNN. The original SSD struggles in detecting very small objects, which is essential for traffic light detection. By our adaptations it is possible to detect objects much smaller than ten pixels without increasing the input image size. We present an extensive evaluation on the DriveU Traffic Light Dataset (DTLD). We reach both, high accuracy and low false positive rates. The trained model is real-time capable with ten frames per second on a Nvidia Titan Xp. Code has been made available at https://github.com/julimueller/tl_ssd.