EvTTC Benchmark

sensor

We present an event camera dataset, called EvTTC, for the task of time-to-collision estimation in autonomous driving:

A diverse set of sequences featuring various targets, such as real vehicles, inflatable vehicles, and dummies, across a wide range of relative speeds, including both routine and challenging situations.
A low-cost and small-scale TTC testbed that facilitates the generation of quasi-real data at different relative speeds. The design of the testbed is open-source.
A specific benchmark for the TTC task that can serve as an evaluation platform for the community to test and compare different TTC estimation methods.

News

Mar. 2, 2025	Updated annotations of bounding boxes and segmentation for objects/subjects.
Mar. 2, 2025	Updated ground-truth TTC.
Feb. 19, 2025	Updated detailed results of the TTC Benchmark.
Feb. 4, 2025	All parameters of the Prophesee EVK4 are now available.
Feb. 3, 2025	Depth maps for all sequences are now available.
Dec. 5, 2024	Watch our video on Youtube.
Nov. 5, 2024	EvTTC Benchmark goes live!

BibTeX

Please cite the following publication when using this benchmark in an academic context:

    
      @misc{sun2024aneventcameradatasetfortime-to-collisionestion,
        title         = {EvTTC: An Event Camera Dataset for Time-to-Collision Estimation},
        author        = {Kaizhen Sun and Jinghang Li and Kuan Dai and Bangyan Liao and Wei Xiong and Yi Zhou},
        year          = 2024,
        eprint        = {2412.05053},
        archiveprefix = {arXiv},
        primaryclass  = {cs.CV}
      }

Abs arXiv VIDEO

Time-to-Collision (TTC) estimation lies in the core of the forward collision warning (FCW) functionality, which is key to all Automatic Emergency Braking (AEB) systems. Although the success of solutions using frame-based cameras (e.g., Mobileye’s solutions) has been witnessed in normal situations, some extreme cases, such as the sudden variation in the relative speed of leading vehicles and the sudden appearance of pedestrians, still pose significant risks that cannot be handled. This is due to the inherent imaging principles of frame-based cameras, where the time interval between adjacent exposures introduces considerable system latency to AEB. Event cameras, as a novel bio-inspired sensor, offer ultra-high temporal resolution and can asynchronously report brightness changes at the microsecond level. To explore the potential of event cameras in the above-mentioned challenging cases, we propose EvTTC, which is, to the best of our knowledge, the first multi-sensor dataset focusing on TTC tasks under high-relative-speed scenarios. EvTTC consists of data collected using standard cameras and event cameras, covering various potential collision scenarios in daily driving and involving multiple collision objects. Additionally, LiDAR and GNSS/INS measurements are provided for the calculation of ground truth TTC. Considering the high cost of testing TTC algorithms on full-scale mobile platforms, we also provide a small-scale TTC testbed for experimental validation and data augmentation. All the data and the design of the testbed are open sourced, and they can serve as a benchmark that will facilitate the development of vision-based TTC techniques.

License

This datasets, along with documentation and toolbox, are released under the BSD 3-Clause Clear License.

Acknowledgement

This work was supported by the National Key Research and Development Project of China (grant number 2023YFB4706600), as well as the generous support provided by our industry partner Xidi Zhijia (Hunan) Co., Ltd..