4 papers
Illumination Invariant Foreground Object Segmentation using ForeGANs
Maryam Sultana, Soon Ki Jung
The foreground segmentation algorithms suffer performance degradation in the presence of various challenges such as dynamic backgrounds, and various illumination conditions. To han…
Deep Neural Network Concepts for Background Subtraction: A Systematic Review and Comparative Evaluation
Thierry Bouwmans, Sajid Javed, Maryam Sultana +1
Conventional neural networks show a powerful framework for background subtraction in video acquired by static cameras. Indeed, the well-known SOBS method and its variants based on…
Unsupervised RGBD Video Object Segmentation Using GANs
Maryam Sultana, Arif Mahmood, Sajid Javed +1
Video object segmentation is a fundamental step in many advanced vision applications. Most existing algorithms are based on handcrafted features such as HOG, super-pixel segmentati…
Unsupervised Deep Context Prediction for Background Foreground Separation
Maryam Sultana, Arif Mahmood, Sajid Javed +1
In many advanced video based applications background modeling is a pre-processing step to eliminate redundant data, for instance in tracking or video surveillance applications. Ove…