Deep neural network concepts for background subtraction: A systematic review and comparative evaluation

T Bouwmans, S Javed, M Sultana, SK Jung - Neural Networks, 2019 - Elsevier
Conventional neural networks have been demonstrated to be a powerful framework for
background subtraction in video acquired by static cameras. Indeed, the well-known Self …

Unsupervised moving object segmentation using background subtraction and optimal adversarial noise sample search

M Sultana, A Mahmood, SK Jung - Pattern Recognition, 2022 - Elsevier
Abstract Moving Objects Segmentation (MOS) is a fundamental task in many computer
vision applications such as human activity analysis, visual object tracking, content based …

Learning Temporal Distribution and Spatial Correlation Towards Universal Moving Object Segmentation

G Dong, C Zhao, X Pan, A Basu - IEEE Transactions on Image …, 2024 - ieeexplore.ieee.org
The goal of moving object segmentation is separating moving objects from stationary
backgrounds in videos. One major challenge in this problem is how to develop a universal …

Dynamic mode decomposition via convolutional autoencoders for dynamics modeling in videos

IU Haq, T Iwata, Y Kawahara - Computer Vision and Image Understanding, 2022 - Elsevier
Extracting the underlying dynamics of objects in image sequences is one of the challenging
problems in computer vision. Besides, dynamic mode decomposition (DMD) has recently …

Tensor based completion meets adversarial learning: a win–win solution for change detection on unseen videos

I Kajo, M Kas, Y Ruichek, N Kamel - Computer Vision and Image …, 2023 - Elsevier
Foreground segmentation is an essential processing phase in several change detection-
based applications. Classical foreground segmentation is highly dependent on the accuracy …

Dynamic background subtraction by generative neural networks

F Bahri, N Ray - 2022 18th IEEE International Conference on …, 2022 - ieeexplore.ieee.org
Background subtraction is a significant task in computer vision and an essential step for
many real world applications. One of the challenges for background subtraction methods is …

Moving objects segmentation based on deepsphere in video surveillance

S Ammar, T Bouwmans, N Zaghden, M Neji - … NV, USA, October 7–9, 2019 …, 2019 - Springer
Segmentation of moving objects from video sequences plays an important role in many
computer vision applications. In this paper, we present a background subtraction approach …

Learning Temporal Distribution and Spatial Correlation Towards Universal Moving Object Segmentation

G Dong, C Zhao, X Pan, A Basu - arxiv preprint arxiv:2304.09949, 2023 - arxiv.org
The goal of moving object segmentation is separating moving objects from stationary
backgrounds in videos. One major challenge in this problem is how to develop a universal …

Deep learning based background subtraction: a systematic survey

JH Giraldo, HT Le, T Bouwmans - Handbook of Pattern Recognition …, 2020 - World Scientific
Machine learning has been widely applied for detection of moving objects from static
cameras. Recently, many methods using deep learning for background subtraction have …

Unsupervised deep learning for online foreground segmentation exploiting low-rank and sparse priors

K Takeda, K Fujiwara, T Sakai - 2022 International Conference …, 2022 - ieeexplore.ieee.org
This paper proposes a simple approach to unsupervised deep learning for foreground
object segmentation. Robust principal component analysis (RPCA) can achieve background …