Background segmentation with feedback: The Pixel-Based Adaptive Segmenter

By Martin Hofmann, Philipp Tiefenbacher, Gerhard Rigoll. IEEE Computer Society Conference on Computer Vision and Pattern Recognition workshops, 2012

586 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/333c1563d72a75f8d3ff3830350555380dc54ebc

How researchers see this paper

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

In Computer Vision and Pattern Recognition

Citations in the corpus

SuBSENSE: A Universal Change Detection Method With Local Adaptive Sensitivity (2015, methodology): “A notable exception is the Pixel-Based Adaptive Segmenter (PBAS) [7], which exploits “background dynamics” (i.e. the study of background motion patterns and model fidelity) to control local decision thresholds and update rates.”
A Deep Convolutional Neural Network for Background Subtraction (2017, methodology): “The fourth column is the output of the SuBSENSE [21], the fifth column represents the output of the PBAS [13] and the last column shows the output of the GMM [22] segmentation.”
Decomposition into Low-rank plus Additive Matrices for Background/Foreground Separation: A Review for a Comparative Evaluation with a Large-Scale Dataset (2015, methodology): “Experimental results on i-LIDS and Change Detection (CDnet) 2014 datasets show that OR-PCA with ARF outperforms by integrating the original MOG with ARF, PBAS with ARF, and Codebook model with ARF.”
Background Subtraction in Real Applications: Challenges, Current Models and Future Directions (2019, methodology): “(2015) [119] MOG [283], ViBe [28], PBAS [142] Idem MOG/PBAS/ViBe Idem MOG/PBAS/ViBe RGB Morphological Processing”
Changedetection.net: A new change detection benchmark dataset (2012, methodology): “The methods ranked number 1 [10] and number 3 [7] are closely related.”
Deep Neural Network Concepts for Background Subtraction: A Systematic Review and Comparative Evaluation (2018, methodology): “Experimental results [222] on the CDnet 2012 dataset [62] demonstrate that SDAE gives better performance than traditional methods (MOG [180], KDE [49], LBP [77]), and recent state-of-art model (PBAS [81]).”
A comprehensive review of background subtraction algorithms evaluated with synthetic and real videos (2014, methodology): “Method ID Settings Basic methods, mean and variance over time StaticFrameDifferenceBGS T ¼ 15 FrameDifferenceBGS T ¼ 15 WeightedMovingMeanBGS T ¼ 10 WeightedMovingVarianceBGS T ¼ 15 AdaptiveBackgroundLearning T ¼ 15; a ¼ 0:5 DPMeanBGS T ¼ 2700; a ¼ 10 7; LF ¼ 30 DPAdaptiveMedianBGS T ¼ 20; LF ¼ 30; ”
Traditional and recent approaches in background modeling for foreground detection: An overview (2014, methodology): “[124] and called Pixel-Based Adaptive Segmenter (PBAS) models the background by a history of recently observed pixel”
Ensemble Video Object Cut in Highly Dynamic Scenes (2013, methodology): “In this work, we include the top 7 methods for performance comparison: (a) CP, the Chebyshev probability approach [17]; (b) Feedback, the feedback approach [9]; (c) the ViBe+ method [3]; (d) PSP-MRF, the probabilistic superpixel Markov random fields approach [22]; (e) KDE, the integrated spatiotempo”