no code implementations • 6 Mar 2023 • Fateme Bahri, Nilanjan Ray
In this work, we propose a weakly supervised framework that can perform background subtraction without requiring per-pixel ground-truth labels.
1 code implementation • 10 Feb 2022 • Fateme Bahri, Nilanjan Ray
One of the challenges for background subtraction methods is dynamic background, which constitute stochastic movements in some parts of the background.
no code implementations • 3 Aug 2018 • Fateme Bahri, Moein Shakeri, Nilanjan Ray
In this paper, we propose an extension of a state-of-the-art batch MOD method (ILISD) to an online/incremental MOD using unsupervised and generative neural networks, which use illumination invariant image representations.