Evaluation of background subtraction techniques for video surveillance

By Sebastian Brutzer, Benjamin Höferlin, Gunther Heidemann. Computer Vision and Pattern Recognition, 2011

684 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/1a4f64aa3c05b871b844a0ea2e299b92a3869123

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Changedetection.net: A new change detection benchmark dataset (2012, background): “, 2011 [6] use a synthetic (computergenerated) dataset produced from only one 3D scene representing a street corner.”
Video Segmentation by Non-Local Consensus voting (2014, background): “These were assumed to be either: (i) stationary backgrounds [5, 9, 12, 33] or backgrounds undergoing 2D parametric motion [16, 18, 30] (thus image registration can be used for background stabilization); or (ii) backgrounds undergoing 3D motions with 3D parallax [17, 34, 37].”
Fast Object Segmentation in Unconstrained Video (2013, methodology): “Our method does not require a static or slowly moving background (as opposed to classic background subtraction methods [9, 4, 7]).”
Camera-trap images segmentation using multi-layer robust principal component analysis (2017, background): “There is a significant body research of background subtraction focused in video surveillance [4].”
Traditional and recent approaches in background modeling for foreground detection: An overview (2014, methodology): “• SABS Dataset: The SABS31 (Stuttgart Artificial Background Subtraction) dataset [41] represents an artificial dataset for pixel-wise evaluation of background models.”
A Survey on Deep Learning Technique for Video Segmentation (2021, background): “These geometry-based methods fit well for specific application scenarios such as surveillance systems [9], [26], but they are sensitive to model selection (2D or 3D), and cannot handle non-rigid camera movements.”
Reducto: On-Camera Filtering for Resource-Efficient Real-Time Video Analytics (2020, background): “(C1) What low-level video features to use? The computer vision (CV) community [20, 24, 44, 46, 59, 60, 66, 68, 83, 84] has discovered a slew of low-level video features that extract frame differences [21], such as Edge and Pixel.”
A comprehensive review of background subtraction algorithms evaluated with synthetic and real videos (2014, background): “Recently, this lack of durable reference has lead to the emergence of several benchmarks, fully available on the Web, as ChangeDetection.net [20], SABS (Stuttgart Artificial Background Subtraction Dataset) [8], or BMC (Background Models Challenge) [42].”
CDnet 2014: An Expanded Change Detection Benchmark Dataset (2014, methodology): “We highlight strengths and weaknesses of these methods and identify remaining issues in change detection.”
Focus: Querying Large Video Datasets with Low Latency and Low Cost (2018, methodology): “Alternatively, objects can be detected separately using relatively inexpensive techniques like background subtraction [28], which are well-suited for static cameras, as in surveillance or traffic installations, and then the detected objects can be classified using object classification CNN architect”
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 [435] on the SABS dataset [40] show that MBRMF outperforms PCP solved via IALM [45], BRPCA [83], VBRPCA [18], DECOLOR [464] and PRMF [385].”