Drive&Act: A Multi-Modal Dataset for Fine-Grained Driver Behavior Recognition in Autonomous Vehicles
Abstract
We introduce the novel domain-specific Drive&Act benchmark for fine-grained categorization of driver behavior. Our dataset features twelve hours and over 9.6 million frames of people engaged in distractive activities during both, manual and automated driving. We capture color, infrared, depth and 3D body pose information from six views and densely label the videos with a hierarchical annotation scheme, resulting in 83 categories. The key challenges of our dataset are: (1) recognition of fine-grained behavior inside the vehicle cabin; (2) multi-modal activity recognition, focusing on diverse data streams; and (3) a cross view recognition benchmark, where a model handles data from an unfamiliar domain, as sensor type and placement in the cabin can change between vehicles. Finally, we provide challenging benchmarks by adopting prominent methods for video- and body pose-based action recognition.
Cite
Text
Martin et al. "Drive&Act: A Multi-Modal Dataset for Fine-Grained Driver Behavior Recognition in Autonomous Vehicles." Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019.Markdown
[Martin et al. "Drive&Act: A Multi-Modal Dataset for Fine-Grained Driver Behavior Recognition in Autonomous Vehicles." Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019.](https://mlanthology.org/iccv/2019/martin2019iccv-drive/)BibTeX
@inproceedings{martin2019iccv-drive,
title = {{Drive&Act: A Multi-Modal Dataset for Fine-Grained Driver Behavior Recognition in Autonomous Vehicles}},
author = {Martin, Manuel and Roitberg, Alina and Haurilet, Monica and Horne, Matthias and Reiss, Simon and Voit, Michael and Stiefelhagen, Rainer},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
year = {2019},
url = {https://mlanthology.org/iccv/2019/martin2019iccv-drive/}
}