Deep background subtraction with scene-specific convolutional neural networks

By Marc Braham, Marc Van Droogenbroeck. International Conference on Systems, Signals, and Image Processing, 2016

299 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Background Subtraction in Real Applications: Challenges, Current Models and Future Directions (2019, methodology): “Prospective solutions to handle the unsolved challenges can be the use of recent background subtraction methods based on fuzzy models [25][22][24][74], RPCA models [164][165][168][166] and deep learning models [51][221][219][252][253][310].”
A Deep Convolutional Neural Network for Background Subtraction (2017, methodology): “The robustness of the system is always dependent and limited by the performance of each individual St- Charles et al. [19] Stauffer and Grimson [3] Elgammal et al. [5] Hofman et al. [15] Oliver et al. [8]Kim et al. [7] Barnich et al. [6] Braham and Droogenbroeck [20] Codebookbased Probabilistic Samp”
Deep Neural Network Concepts for Background Subtraction: A Systematic Review and Comparative Evaluation (2018, methodology): “Experimental results [114] show that TCNN outperforms both ConvNet [22] and Cascaded CNN [204], and practically outperformed all the reported methods by an overall F-Measure of 0.”
Online Adaptation of Convolutional Neural Networks for Video Object Segmentation (2017, background): “Recently, deep learning based approaches, which often utilize large classification datasets for pretraining, have shown extremely good performance for VOS [7, 20, 24, 35] and the related tasks of single-object tracking [5, 18, 31] and background modeling [2, 6, 44].”