Open AccessBackground subtraction via colour coherence under varying illuminations
Author(s) -
Kim Wonjun
Publication year - 2018
Publication title -
electronics letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.375
H-Index - 146
ISSN - 1350-911X
DOI - 10.1049/el.2018.6066
Subject(s) - robustness (evolution) , subtraction , artificial intelligence , background subtraction , computer vision , computer science , exploit , coherence (philosophical gambling strategy) , benchmark (surveying) , invariant (physics) , mathematics , pattern recognition (psychology) , pixel , statistics , arithmetic , geography , biochemistry , chemistry , computer security , geodesy , mathematical physics , gene
An illumination‐invariant method for background subtraction is presented. Inspired by the observation that the degree of dispersion in the colour space, which is computed from the local region of each frame, is not severely changed even with varying illuminations, To exploit the colour coherence as the features for formulating the background model is proposed. Experimental results on various benchmark databases show the efficiency and robustness of the proposed method compared to the previous approaches introduced in the literature.