Adaptive background mixture models for real-time tracking

By Chris Stauffer, W. Grimson. 1999

Subfields: Computer Vision and Pattern Recognition

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

Segment Anything (2023, background): “Segmentation is a broad field: there’s interactive segmentation [57, 109], edge detection [3], super pixelization [85], object proposal generation [2], foreground segmentation [94], semantic segmentation [90], instance segmentation [66], panoptic segmentation [59], etc.”
Unsupervised label noise modeling and loss correction (2019, methodology): “Modern CNNs trained with stochastic gra-0 Mixture models are a widely used unsupervised modeling technique (Stauffer & Grimson, 1999; Permuter et al., 2006; Ma & Leijon, 2011), with the Gaussian Mixture Model (GMM) (Permuter et al., 2006) being the most popular.”
A Biologically Inspired System for Action Recognition (2007, methodology): “Preprocessing We preprocessed the datasets to speed-up our experiments: On the KTH human and UCSD mice datasets we used the openCV GMM background subtraction technique based on [30].”
A Review on Human Activity Recognition Using Vision-Based Method (2017, methodology): “Stauffer and Grimson [13] proposed to model the values of a particular background pixel as a mixture of Gaussians to replace the strategy of using only one Gaussian value in the previous approach.”
Tracking loose-limbed people (2004, methodology): “We exploit the fact that the background is static, model it using a mixture model at each pixel, and perform standard foreground detection [24].”
Visual Tracking: an Experimental Survey (2013, unknown): “For static scenes, background intensity representation is an old solution [84], [85] only suited for standardized circumstances, improved with background intensity prediction with simple statistics [86], [87], [88].”
Sparse reconstruction cost for abnormal event detection (2011, background): “Research in video surveillance has made great progresses in recent years, such as background model [22], object tracking [3], pedestrian detection [8], action recognition [27] and crowd counting [7].”
Modeling pixel process with scale invariant local patterns for background subtraction in complex scenes (2010, unknown): “[1] [2] [4] [8] [10].”
A background model initialization algorithm for video surveillance (2001, background): “Recently, there has been a large amount of work addressing the issues of background model representation and adaptation [5, 6, 7, 8, 9, 10, 11, 12].”
Bilayer Segmentation of Live Video (2006, background): “The background colour distribution is constructed from an initial extended observation of the background, rather as in [17, 18], to build in variability of appearance.”
Deep Neural Network Concepts for Background Subtraction: A Systematic Review and Comparative Evaluation (2018, methodology): “e that the representative conventional neural networks Coherence-based and Fuzzy SOBS (SOBS-CF) [125] and SOBS with Spatial Coherence (SC-SOBS) [126] outperforms the basic statistical models like MOG [180] (1999) even with improvements like in RMOG [192] (2013). However, SOBS and its variants were t”
Anomaly detection in crowded scenes (2010, methodology): “Temporal abnormality detection is inspired by the popular background subtraction method of [23].”
Automatic analysis of multimodal group actions in meetings (2005, unknown): “Adaptive background subtraction should improve robustness [60].”
Pedestrian detection in crowded scenes (2005, methodology): “Using the sequences as input, we computed a motion segmentation mask with a Grimson-Stauffer background model [ 21 ] and selected a set of frames for which a good segmentation could be obtained.”
Tracking Groups of People (2000, methodology): “used gray-level subtraction [10, 11], Pfinder modeled pixel color variation using multivariate Gaussians [31], and Gaussian mixtures have also been used in a similar manner [23, 29].”
Moving Object Detection by Detecting Contiguous Outliers in the Low-Rank Representation (2011, background): “We will discuss the scenarios with moving cameras in Section IV.”
Segmenting foreground objects from a dynamic textured background via a robust Kalman filter (2003, methodology): “In [4, 17] the color distribution of each background pixel is learned using a Gaussian mixture model, and these mixture models are continuously updated to adapt to slow background changes.”
Recent developments in human motion analysis (2003, methodology): “As an example of statistical methods, StauOer and Grimson [38] presented an adaptive background mixture model for real-time tracking.”