Background modeling and subtraction by codebook construction

By Kyungnam Kim, Thanarat Horprasert Chalidabhongse, David Harwood, Larry S. Davis. 2004 International Conference on Image Processing, 2004. ICIP '04., 2004

437 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/8ff8c59b6bd8f83d53479c7df32ca11d1c4234cb

How researchers see this paper

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

Citations in the corpus

SuBSENSE: A Universal Change Detection Method With Local Adaptive Sensitivity (2015, methodology): “The codebook methods of [18] and [19] present another alternative to solve this problem: they cluster observations into codewords and store them in local dictionaries, allowing for a wider range of representations to be kept in the background model.”
Evaluation of background subtraction techniques for video surveillance (2011, methodology): “McFarlane [20] 1995 unimodal (median) color pixel yes DM Stauffer [26] 1999 multimodal (Gaussian) color pixel yes DM Oliver [22] 2000 linear subspace pixel correlation (color) frame no DM McKenna [21] 2000 unimodal (Gaussian) chromaticity, gradient pixel yes DM Li2 [18] 2003 non-parametric (discreti”
ViBe: A Universal Background Subtraction Algorithm for Video Sequences (2011, methodology): “In the codebook algorithm [61], [62], each pixel is represented by a codebook, which is a compressed form of background model for a long image sequence.”
Video Processing From Electro-Optical Sensors for Object Detection and Tracking in a Maritime Environment: A Survey (2016, methodology): “Range model [132], [133] Multiple class model, each with a range of intensities Simple, pre-learnt ranges, may be made adaptive Not discriminative”
Background Subtraction in Real Applications: Challenges, Current Models and Future Directions (2019, methodology): “(2008) [210] Codebook [187] Idem Codebook Idem Codebook RGB Shadow/Highlight Detection [146]”
Traditional and recent approaches in background modeling for foreground detection: An overview (2014, methodology): “Bootstrapping Background Initialization: SVM [161], Consecutive Frames [126] Cluster Models: K-means [43], Codebook [142][224], BSC [291] Features: Blocks [126][1] Strategies: Markov Random Fields (MRF) [211]”
A texture-based method for modeling the background and detecting moving objects (2006, methodology): “Unlike most other approaches, the features in background modeling are”