A novel background subtraction method based on color invariants and grayscale levels. Guachi, L., Cocorullo, G., Corsonello, P., Frustaci, F., & Perri, S. In 2014 International Carnahan Conference on Security Technology (ICCST), pages 1-5, 10, 2014. IEEE.
A novel background subtraction method based on color invariants and grayscale levels [link]Website  doi  abstract   bibtex   1 download  
This paper presents a new method for background subtraction which takes advantages of using the color invariants combined with gray color. The proposed method works robustly reducing misclassified foreground objects. Gaussian mixtures are exploited for each pixel through two channels: the color invariants, which are derived from a physical model, and the gray colors obtained as a descriptor of the image. The background models update is performed using a random process selected considering that in many practical situations it is not necessary to update each background pixel model for each new frame. The novel algorithm has been compared to three state-of-the-art methods. Experimental results demonstrate the proposed method achieves a higher robustness, is less sensitive to noise and increases the number of pixel correctly classified as foreground for both indoor and outdoor video sequences.
@inproceedings{
 title = {A novel background subtraction method based on color invariants and grayscale levels},
 type = {inproceedings},
 year = {2014},
 keywords = {Background subtraction,Video systems,automatic monitoring},
 pages = {1-5},
 websites = {http://ieeexplore.ieee.org/document/6987024/},
 month = {10},
 publisher = {IEEE},
 id = {1b339a2f-f544-3fb5-bbcf-d9558c254188},
 created = {2020-12-30T02:11:40.230Z},
 file_attached = {false},
 profile_id = {e5f1b339-ec56-313b-b123-fd0a1c527f0d},
 last_modified = {2020-12-30T02:11:40.230Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Guachi2014},
 source_type = {inproceedings},
 private_publication = {false},
 abstract = {This paper presents a new method for background subtraction which takes advantages of using the color invariants combined with gray color. The proposed method works robustly reducing misclassified foreground objects. Gaussian mixtures are exploited for each pixel through two channels: the color invariants, which are derived from a physical model, and the gray colors obtained as a descriptor of the image. The background models update is performed using a random process selected considering that in many practical situations it is not necessary to update each background pixel model for each new frame. The novel algorithm has been compared to three state-of-the-art methods. Experimental results demonstrate the proposed method achieves a higher robustness, is less sensitive to noise and increases the number of pixel correctly classified as foreground for both indoor and outdoor video sequences.},
 bibtype = {inproceedings},
 author = {Guachi, Lorena and Cocorullo, Giuseppe and Corsonello, Pasquale and Frustaci, Fabio and Perri, Stefania},
 doi = {10.1109/CCST.2014.6987024},
 booktitle = {2014 International Carnahan Conference on Security Technology (ICCST)}
}

Downloads: 1