An Improved Adaptive Background Mixture Model for Real-time Tracking with Shadow Detection

By Pakorn KaewTrakulPong, Richard Bowden. 2001

Subfields: Computer Vision and Pattern Recognition, Model Architectures

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

In Model Architectures

Citations in the corpus

SOCRATES: Introducing Depth in Visual Wildlife Monitoring Using Stereo Vision (2022, methodology): “Therefore, we employ an approach based on background modeling using Gaussian mixture models (KaewTraKulPong and Bowden, 2002).”
Understanding Background Mixture Models for Foreground Segmentation (2002, background): “…from [Stauffer and Grimson 1999] in that (10) to (13) are implemented there with a fixed α for all time—which leads to problems with initialization [KaewTraKulPong and Bowden 2001]— and (13) differs by a factor of fX(Xt |k,θk)—which leads to impractical values for their ρk,t if implemented…”
Change Detection in a 3-d World (2007, methodology): “5 standard deviations of the mean is updated with the following equations: These equations are the same as the EM-algorithm derived result in [4] in the case where the weights are constant.”
Background segmentation with feedback: The Pixel-Based Adaptive Segmenter (2012, methodology): “GMM— KaewTraKulPong [4] 0.”
SuBSENSE: A Universal Change Detection Method With Local Adaptive Sensitivity (2015, background): “Color versions of one or more of the figures in this paper are available online at http://ieeexplore.ieee.org.”
A large-scale hierarchical multi-view RGB-D object dataset (2011, methodology): “[18] and used the implementation in the OpenCV library.”
Focus: Querying Large Video Datasets with Low Latency and Low Cost (2018, methodology): “We use OpenCV 3.2.0 [14] to decode the videos into frames, and then use the built-in background subtraction algorithm [43] in OpenCV to extract moving objects from video frames.”
Effective Gaussian mixture learning for video background subtraction (2005, background): “Index Terms—Adaptive Gaussian mixture, online EM, background subtraction.”
The COACH prompting system to assist older adults with dementia through handwashing: An efficacy study (2008, methodology): “A single subject research design (SSRD) was used in this study because of the difficulty in recruiting and maintaining an adequate sample size and the variability of the participants' health [27-31].”
Efficient adaptive density estimation per image pixel for the task of background subtraction (2006, background): “The standard GMM update equations are extended in (KaewTraKulPong and Bowden, 2001; Lee, 2005) to improve the speed of adaptation of the model.”
A texture-based method for modeling the background and detecting moving objects (2006, background): “To the authors’ knowledge, none of the earlier studies have utilized discriminative texture features in dealing with the problem.”
ViBe: A Universal Background Subtraction Algorithm for Video Sequences (2011, methodology): “The GMM of [70] and the Bayesian algorithm of [47] were tested using their implementations available in Intel’s IPP image processing library.”
A comprehensive review of background subtraction algorithms evaluated with synthetic and real videos (2014, methodology): “DPGrimsonGMMBGS Gaussian Mixture Model [38] MixtureOfGaussianV1BGS Gaussian Mixture Model [25] MixtureOfGaussianV2BGS Gaussian Mixture Model [49] DPZivkovicAGMMBGS Gaussian Mixture Model [49] LBMixtureOfGaussians Gaussian Mixture Model [6]”
Changedetection.net: A new change detection benchmark dataset (2012, methodology): “Two fairly old, but frequently-cited, methods: KDE-based estimation by Elgammal et al. [8] and GMM by Stauffer and Grimson [24], as well as 5 improved versions of these methods: self-adapting GMM by KaewTraKulPong [12], improved GMM by Zivkovic and van der Heijden [28], block-based GMM by Dora (RECT”
Recent Advanced Statistical Background Modeling for Foreground Detection - A Systematic Survey (2011, background): “For the maintenance, the learning rates are better set [66, 67] or adapt over time [60-62 , 68-78 68-78].”