# TLD: A Vehicle Tail Light signal Dataset and Benchmark

arXiv: https://arxiv.org/abs/2409.02508 · HTML: https://mlsanity.com/paper/2409.02508/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 50 references that are in the map.
- First posted on arXiv 4 Sep 2024.

## Builds on (most cited first, 15 of 15)

- [Two-Stream Convolutional Networks for Action Recognition in Videos](https://mlsanity.com/paper/1406.2199/) (2014)
- [Bidirectional LSTM-CRF Models for Sequence Tagging](https://mlsanity.com/paper/1508.01991/) (2015)
- [YOLOv10: Real-Time End-to-End Object Detection](https://mlsanity.com/paper/2405.14458/) (2024)
- [Long-term Recurrent Convolutional Networks for Visual Recognition and Description](https://mlsanity.com/paper/1411.4389/) (2014)
- [TNT: Target-driveN Trajectory Prediction](https://mlsanity.com/paper/2008.08294/) (2020)
- [From Goals, Waypoints & Paths To Long Term Human Trajectory Forecasting](https://mlsanity.com/paper/2012.01526/) (2020)
- [IntentNet: Learning to Predict Intention from Raw Sensor Data](https://mlsanity.com/paper/2101.07907/) (2021)
- [GenAD: Generalized Predictive Model for Autonomous Driving](https://mlsanity.com/paper/2403.09630/) (2024)
- [Spatiotemporal Residual Networks for Video Action Recognition](https://mlsanity.com/paper/1611.02155/) (2016)
- [Spatiotemporal Relationship Reasoning for Pedestrian Intent Prediction](https://mlsanity.com/paper/2002.08945/) (2020)
- [LOKI: Long Term and Key Intentions for Trajectory Prediction](https://mlsanity.com/paper/2108.08236/) (2021)
- [Action Recognition using Visual Attention](https://mlsanity.com/paper/1511.04119/) (2015)
- [Temporal 3D ConvNets: New Architecture and Transfer Learning for Video Classification](https://mlsanity.com/paper/1711.08200/) (2017)
- [An Attention-based Recurrent Convolutional Network for Vehicle Taillight Recognition](https://mlsanity.com/paper/1906.03683/) (2019)
- [Nighttime Driver Behavior Prediction Using Taillight Signal Recognition via CNN-SVM Classifier](https://mlsanity.com/paper/2310.16706/) (2023)

## Built on by (most cited first, 1 of 1)

- [Thinking in Video: Can Video Generators Really Reason About the Real World?](https://mlsanity.com/paper/2607.17523/) (2026)

## Abstract (arXiv)

Understanding other drivers' intentions is crucial for safe driving. The role of taillights in conveying these intentions is underemphasized in current autonomous driving systems. Accurately identifying taillight signals is essential for predicting vehicle behavior and preventing collisions. Open-source taillight datasets are scarce, often small and inconsistently annotated. To address this gap, we introduce a new large-scale taillight dataset called TLD. Sourced globally, our dataset covers diverse traffic scenarios. To our knowledge, TLD is the first dataset to separately annotate brake lights and turn signals in real driving scenarios. We collected 17.78 hours of driving videos from the internet. This dataset consists of 152k labeled image frames sampled at a rate of 2 Hz, along with 1.5 million unlabeled frames interspersed throughout. Additionally, we have developed a two-stage vehicle light detection model consisting of two primary modules: a vehicle detector and a taillight classifier. Initially, YOLOv10 and DeepSORT captured consecutive vehicle images over time. Subsequently, the two classifiers work simultaneously to determine the states of the brake lights and turn signals. A post-processing procedure is then used to eliminate noise caused by misidentifications and provide the taillight states of the vehicle within a given time frame. Our method shows exceptional performance on our dataset, establishing a benchmark for vehicle taillight detection. The dataset is available at https://huggingface.co/datasets/ChaiJohn/TLD/tree/main