M
Maryam Sultana
Researcher at Kyungpook National University
Publications - 16
Citations - 451
Maryam Sultana is an academic researcher from Kyungpook National University. The author has contributed to research in topics: Background subtraction & Object detection. The author has an hindex of 6, co-authored 13 publications receiving 265 citations.
Papers
More filters
Journal ArticleDOI
Deep neural network concepts for background subtraction:A systematic review and comparative evaluation
TL;DR: In this article, the authors provide a review of deep neural network concepts in background subtraction for novices and experts in order to analyze this success and to provide further directions.
Journal ArticleDOI
Unsupervised deep context prediction for background estimation and foreground segmentation
TL;DR: A unified method based on Generative Adversarial Network (GAN) and image inpainting and a context prediction network, which is an unsupervised visual feature learning hybrid GAN model for texture enhancement.
Book ChapterDOI
Moving Object Detection on RGB-D Videos Using Graph Regularized Spatiotemporal RPCA
TL;DR: This work investigates the performance of online Spatiotemporal RPCA (SRPCA) algorithm for moving object detection using RGB-D videos and shows competitive results as compared to four state-of-the-art subspace learning methods.
Journal ArticleDOI
Unsupervised Moving Object Detection in Complex Scenes Using Adversarial Regularizations
TL;DR: A Generative Adversarial Network (GAN) based on a moving object detection algorithm, called MOD_GAN, is proposed, enabling the algorithm to learn generating background sequences using input from uniformly distributed random noise samples.
Proceedings ArticleDOI
Dynamic Background Subtraction Using Least Square Adversarial Learning
TL;DR: The proposed method consisting of three loss-terms including least squares adversarial loss, L1-L Loss and Perceptual-Loss is evaluated on two benchmark datasets CDnet2014 and BMC and shows improved performance on both datasets compared with 10 existing state-of-the-art methods.