Real-time foreground-background segmentation using codebook model

By Kyungnam Kim, Thanarat Horprasert Chalidabhongse, David Harwood, Larry S. Davis. Real-time imaging, 2005

1,613 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Safety, Risk, Reliability and Quality

View Paper: https://www.semanticscholar.org/paper/278d7642d835fcd0c246d7ef536e369880d1bae0

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 Safety, Risk, Reliability and Quality

Citations in the corpus

“Double-DIP”: Unsupervised Image Decomposition via Coupled Deep-Image-Priors (2018, background): “tation, the task is to decompose the image into meaningful sub-regions, such as foreground and background [1, 5, 17, 24, 31].”
Fall Detection from Human Shape and Motion History Using Video Surveillance (2007, background): “An ellipse is defined by its center (x̄, ȳ), its orientation θ and the length a and b of its major and minor semi-axes.”
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.”
A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications (2008, background): “The need is strongly felt world-wide, not only by private companies, but also by governments and public institutions, with the aim of increasing people safety and services efficiency.”
Background Modeling using Mixture of Gaussians for Foreground Detection - A Survey (2008, methodology): “[144] instead of the spherical color model used by Stauffer and Grimson [1].”
Animal Detection From Highly Cluttered Natural Scenes Using Spatiotemporal Object Region Proposals and Patch Verification (2016, neutral): “In [21], for each pixel, it builds a codebook.”
Ensemble Video Object Cut in Highly Dynamic Scenes (2013, background): “Most of the existing background models are constructed at the pixel level [4, 26, 10, 11].”
A Deep Convolutional Neural Network for Background Subtraction (2017, methodology): “[15], where the background model for each pixel position is modeled by a codebook.”
ViBe: A Universal Background Subtraction Algorithm for Video Sequences (2011, methodology): “Many popular techniques described in the literature, such as [53], [62], and [65], need a sequence of several dozens of frames to initialize their models.”
Background-subtraction using contour-based fusion of thermal and visible imagery (2007, methodology): “Another non-parametric approach is the code-book based technique recently presented in [24].”
Traditional and recent approaches in background modeling for foreground detection: An overview (2014, methodology): “[143] presented a modified algorithm which a layered modeling/detection and adaptive codebook updating.”
Robust Video Surveillance for Fall Detection Based on Human Shape Deformation (2011, background): “[24] which takes into account shadows, highlights and high image compression.”
Moving Object Detection in Spatial Domain using Background Removal Techniques - State-of-Art (2008, background): “[61, 62] quantize sample background values at each pixel into codebooks which represent a compressed form of background model for a long image sequence.”
Movement Pattern Histogram for Action Recognition and Retrieval (2014, positive): “Shapeflow relies on successful extraction of silhouette of the foreground actor (we use [12] for computing silhouette), which is challenging in videos.”