Illumination-Aware Multi-Task GANs for Foreground Segmentation

Dimitrios Sakkos, Edmond S. L. Ho and Hubert P. H. Shum
IEEE Access, 2019

 Impact Factor: 3.9 Citation: 29#

Illumination-Aware Multi-Task GANs for Foreground Segmentation
# According to Google Scholar 2023"


Foreground-background segmentation has been an active research area over the years. However, conventional models fail to produce accurate results when challenged with videos of challenging illumination conditions. In this paper, we present a robust model that allows accurately extracting the foreground even in exceptionally dark or bright scenes, as well as continuously varying illumination in a video sequence. This is accomplished by a triple multi-task generative adversarial network (TMT-GAN) that effectively models the semantic relationship between dark and bright images, and performs binary segmentation end-to-end. Our contribution is two-fold: First, we show that by jointly optimising the GAN loss and the segmentation loss, our network simultaneously learns both tasks that mutually benefit each other. Secondly, fusing features of images with varying illumination into the segmentation branch vastly improves the performance of the network. Comparative evaluations on highly challenging real and synthetic benchmark datasets (ESI, SABS) demonstrate the robustness of TMT-GAN and its superiority over state-of-the-art approaches.





 author={Sakkos, Dimitrios and Ho, Edmond S. L. and Shum, Hubert P. H.},
 journal={IEEE Access},
 title={Illumination-Aware Multi-Task GANs for Foreground Segmentation},


AU  - Sakkos, Dimitrios
AU  - Ho, Edmond S. L.
AU  - Shum, Hubert P. H.
T2  - IEEE Access
TI  - Illumination-Aware Multi-Task GANs for Foreground Segmentation
PY  - 2019
VL  - 7
IS  - 1
SP  - 10976
EP  - 10986
DO  - 10.1109/ACCESS.2019.2891943
SN  - 2169-3536
ER  - 

Plain Text

Dimitrios Sakkos, Edmond S. L. Ho and Hubert P. H. Shum, "Illumination-Aware Multi-Task GANs for Foreground Segmentation," IEEE Access, vol. 7, no. 1, pp. 10976-10986, IEEE, 2019.

Supporting Grants

Similar Research

Dimitrios Sakkos, Edmond S. L. Ho, Hubert P. H. Shum and Garry Elvin, "Image Editing Based Data Augmentation for Illumination-Insensitive Background Subtraction", Journal of Enterprise Information Management (JEIM), 2020
Dimitrios Sakkos, Hubert P. H. Shum and Edmond S. L. Ho, "Illumination-Based Data Augmentation for Robust Background Subtraction", Proceedings of the 2019 International Conference on Software, Knowledge, Information Management and Applications (SKIMA), 2019



Last updated on 4 June 2024
RSS Feed