A Computer Vision-Based Attention Generator Using DQN

Jordan B. Chipka, Shuqing Zeng, Thanura R. Elvitigala, Priyantha Mudalige

ICCVW 2021 pp. 2942-2950

doi:10.1109/ICCVW54120.2021.00329 /iccvw/2021/chipka2021iccvw-computer/

Abstract

A significant obstacle to achieving autonomous driving (AD) and advanced driver-assistance systems (ADAS) functionality in passenger vehicles is high-fidelity perception at a sufficiently low cost of computation and sensors. An area of research that aims to address this challenge takes inspiration from human foveal vision by using attention-based sensing. This work presents an end-to-end computer vision-based Deep Q-Network (DQN) technique that intelligently selects a priority region of an image to place greater attention to achieve better perception performance. This method is evaluated on the Berkeley Deep Drive (BDD) dataset. Results demonstrate that a substantial improvement in perception performance can be attained – compared to a baseline method – at a minimal cost in terms of time and processing.

ICCVW Semantic Scholar

Cite

Text

Chipka et al. "A Computer Vision-Based Attention Generator Using DQN." IEEE/CVF International Conference on Computer Vision Workshops, 2021. doi:10.1109/ICCVW54120.2021.00329

Markdown

[Chipka et al. "A Computer Vision-Based Attention Generator Using DQN." IEEE/CVF International Conference on Computer Vision Workshops, 2021.](https://mlanthology.org/iccvw/2021/chipka2021iccvw-computer/) doi:10.1109/ICCVW54120.2021.00329

BibTeX

@inproceedings{chipka2021iccvw-computer,
  title     = {{A Computer Vision-Based Attention Generator Using DQN}},
  author    = {Chipka, Jordan B. and Zeng, Shuqing and Elvitigala, Thanura R. and Mudalige, Priyantha},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2021},
  pages     = {2942-2950},
  doi       = {10.1109/ICCVW54120.2021.00329},
  url       = {https://mlanthology.org/iccvw/2021/chipka2021iccvw-computer/}
}