TY - GEN
T1 - Background/Foreground Separation
T2 - 18th IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021
AU - Sultana, Maryam
AU - Mahmood, Arif
AU - Bouwmans, Thierry
AU - Khan, Muhammad Haris
AU - Ki Jung, Soon
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - Background-Foreground separation and appearance generation is a fundamental step in many computer vision applications. Existing methods like Robust Subspace Learning (RSL) suffer performance degradation in the presence of challenges like bad weather, illumination variations, occlusion, dynamic backgrounds and intermittent object motion. In the current work we propose a more accurate deep neural network based model for background-foreground separation and complete appearance generation of the foreground objects. Our proposed model, Guided Attention based Adversarial Model (GAAM), can efficiently extract pixel-level boundaries of the foreground objects for improved appearance generation. Unlike RSL methods our model extracts the binary information of foreground objects labeled as attention map which guides our generator network to segment the foreground objects from the complex background information. Wide range of experiments performed on the benchmark CDnet2014 dataset demonstrate the excellent performance of our proposed model.
AB - Background-Foreground separation and appearance generation is a fundamental step in many computer vision applications. Existing methods like Robust Subspace Learning (RSL) suffer performance degradation in the presence of challenges like bad weather, illumination variations, occlusion, dynamic backgrounds and intermittent object motion. In the current work we propose a more accurate deep neural network based model for background-foreground separation and complete appearance generation of the foreground objects. Our proposed model, Guided Attention based Adversarial Model (GAAM), can efficiently extract pixel-level boundaries of the foreground objects for improved appearance generation. Unlike RSL methods our model extracts the binary information of foreground objects labeled as attention map which guides our generator network to segment the foreground objects from the complex background information. Wide range of experiments performed on the benchmark CDnet2014 dataset demonstrate the excellent performance of our proposed model.
UR - http://www.scopus.com/inward/record.url?scp=85123045223&partnerID=8YFLogxK
U2 - 10.1109/ICCVW54120.2021.00025
DO - 10.1109/ICCVW54120.2021.00025
M3 - Conference contribution
AN - SCOPUS:85123045223
T3 - Proceedings of the IEEE International Conference on Computer Vision
SP - 181
EP - 188
BT - Proceedings - 2021 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 11 October 2021 through 17 October 2021
ER -