Advanced search
1 file | 3.78 MB Add to list

Low-complexity deep HDR fusion and tone mapping for urban traffic scenes

Ivana Shopovska (UGent) , Jan Aelterman (UGent) , David Van Hamme (UGent) and Wilfried Philips (UGent)
Author
Organization
Abstract
In this paper we propose a computationally efficient neural network for high dynamic range fusion and tone mapping, for application in perception systems of autonomous vehicles. The proposed approach fuses two consecutive, differently exposed images into a single output with good exposure in all regions, in a standard dynamic range. Motion is compensated based on fast optical flow estimation, and subsequently by including an error mask as an input to the network to indicate the remaining artifact-prone regions. This is an efficient way for the network to learn to reduce the ghosting artifacts without increasing computational complexity. Unlike the conventional approach, we train the network on versatile traffic data, and evaluate the performance based on object detection quality metrics, rather than for visual quality. The performance was compared to a similarly complex representative method from literature. We achieved improved performance in challenging light conditions due to the robustness of our method in variable traffic conditions.
Keywords
deep learning, high dynamic range imaging, fusion, traffic, EXPOSURE IMAGE FUSION, QUALITY ASSESSMENT

Downloads

  • m84009-shopovska paper.pdf
    • full text (Accepted manuscript)
    • |
    • open access
    • |
    • PDF
    • |
    • 3.78 MB

Citation

Please use this url to cite or link to this publication:

MLA
Shopovska, Ivana, et al. “Low-Complexity Deep HDR Fusion and Tone Mapping for Urban Traffic Scenes.” 2023 IEEE Intelligent Vehicles Symposium, IEEE, 2023, doi:10.1109/IV55152.2023.10186783.
APA
Shopovska, I., Aelterman, J., Van Hamme, D., & Philips, W. (2023). Low-complexity deep HDR fusion and tone mapping for urban traffic scenes. 2023 IEEE Intelligent Vehicles Symposium. Presented at the IEEE Intelligent Vehicles Symposium, Anchorage, Alaska. https://doi.org/10.1109/IV55152.2023.10186783
Chicago author-date
Shopovska, Ivana, Jan Aelterman, David Van Hamme, and Wilfried Philips. 2023. “Low-Complexity Deep HDR Fusion and Tone Mapping for Urban Traffic Scenes.” In 2023 IEEE Intelligent Vehicles Symposium. IEEE. https://doi.org/10.1109/IV55152.2023.10186783.
Chicago author-date (all authors)
Shopovska, Ivana, Jan Aelterman, David Van Hamme, and Wilfried Philips. 2023. “Low-Complexity Deep HDR Fusion and Tone Mapping for Urban Traffic Scenes.” In 2023 IEEE Intelligent Vehicles Symposium. IEEE. doi:10.1109/IV55152.2023.10186783.
Vancouver
1.
Shopovska I, Aelterman J, Van Hamme D, Philips W. Low-complexity deep HDR fusion and tone mapping for urban traffic scenes. In: 2023 IEEE Intelligent Vehicles Symposium. IEEE; 2023.
IEEE
[1]
I. Shopovska, J. Aelterman, D. Van Hamme, and W. Philips, “Low-complexity deep HDR fusion and tone mapping for urban traffic scenes,” in 2023 IEEE Intelligent Vehicles Symposium, Anchorage, Alaska, 2023.
@inproceedings{01GWVMTBQKT9YMV1RGX5ZB668A,
  abstract     = {{In this paper we propose a computationally efficient neural network for high dynamic range fusion and tone mapping, for application in perception systems of autonomous vehicles. The proposed approach fuses two consecutive, differently exposed images into a single output with good exposure in all regions, in a standard dynamic range. Motion is compensated based on fast optical flow estimation, and subsequently by including an error mask as an input to the network to indicate the remaining
artifact-prone regions. This is an efficient way for the network to learn to reduce the ghosting artifacts without increasing computational complexity. Unlike the conventional approach, we train the network on versatile traffic data, and evaluate the performance based on object detection quality metrics, rather than for visual quality. The performance was compared to a similarly complex representative method from literature. We achieved improved performance in challenging light conditions due to the robustness of our method in variable traffic conditions.}},
  author       = {{Shopovska, Ivana and Aelterman, Jan and Van Hamme, David and Philips, Wilfried}},
  booktitle    = {{2023 IEEE Intelligent Vehicles Symposium}},
  isbn         = {{9798350346916}},
  issn         = {{1931-0587}},
  keywords     = {{deep learning,high dynamic range imaging,fusion,traffic,EXPOSURE IMAGE FUSION,QUALITY ASSESSMENT}},
  language     = {{eng}},
  location     = {{Anchorage, Alaska}},
  pages        = {{6}},
  publisher    = {{IEEE}},
  title        = {{Low-complexity deep HDR fusion and tone mapping for urban traffic scenes}},
  url          = {{http://doi.org/10.1109/IV55152.2023.10186783}},
  year         = {{2023}},
}

Altmetric
View in Altmetric
Web of Science
Times cited: