TSTTC: A Large-Scale Dataset for Time-to-Contact Estimation in Driving Scenarios

TL;DR

This paper introduces a large-scale, real-world dataset for Time-to-Contact estimation in driving scenarios, supporting the development of monocular camera-based collision risk assessment methods.

Contribution

It provides a comprehensive, balanced dataset with over 200K sequences, including augmented data, and baseline evaluations to advance TTC estimation research.

Findings

The dataset contains over 200,000 sequences with diverse TTC values.

Baseline models show promising results on the new dataset.

Data augmentation improves small TTC case representation.

Abstract

Time-to-Contact (TTC) estimation is a critical task for assessing collision risk and is widely used in various driver assistance and autonomous driving systems. The past few decades have witnessed development of related theories and algorithms. The prevalent learning-based methods call for a large-scale TTC dataset in real-world scenarios. In this work, we present a large-scale object oriented TTC dataset in the driving scene for promoting the TTC estimation by a monocular camera. To collect valuable samples and make data with different TTC values relatively balanced, we go through thousands of hours of driving data and select over 200K sequences with a preset data distribution. To augment the quantity of small TTC cases, we also generate clips using the latest Neural rendering methods. Additionally, we provide several simple yet effective TTC estimation baselines and evaluate them extensively on the proposed dataset to demonstrate their effectiveness. The proposed dataset is publicly available at https://open-dataset.tusen.ai/TSTTC.