TY - GEN
T1 - Background subtraction using Gaussian Mixture Model enhanced by Hole Filling Algorithm (GMMHF)
AU - Nurhadiyatna, Adi
AU - Jatmiko, Wisnu
AU - Hardjono, Benny
AU - Wibisono, Ari
AU - Sina, Ibnu
AU - Mursanto, Petrus
PY - 2013
Y1 - 2013
N2 - There is a necessity in traffic control system using camera to have the capability to discriminate between an object and non-object in the image. One of the procedure to discriminate between those two is usually performed by background subtraction. Gaussian Mixture Model (GMM) is popular method that has been employed to tackle the problem of background subtraction. However, the output of GMM is a rather noisy image which comes from false classification. This situation may arise because several conditions in the video input such as, waving trees, rippling water, and illumination changes. In this paper, an enhanced version of GMM technique which is combined with Hole Filling Algorithm (HF) is proposed to alleviate those problems. The experimental result shows that the proposed method improved the accuracy up to 97.9% and Kappa statistic up to 0.74. This result has outperformed many similar methods that is used for evaluation.
AB - There is a necessity in traffic control system using camera to have the capability to discriminate between an object and non-object in the image. One of the procedure to discriminate between those two is usually performed by background subtraction. Gaussian Mixture Model (GMM) is popular method that has been employed to tackle the problem of background subtraction. However, the output of GMM is a rather noisy image which comes from false classification. This situation may arise because several conditions in the video input such as, waving trees, rippling water, and illumination changes. In this paper, an enhanced version of GMM technique which is combined with Hole Filling Algorithm (HF) is proposed to alleviate those problems. The experimental result shows that the proposed method improved the accuracy up to 97.9% and Kappa statistic up to 0.74. This result has outperformed many similar methods that is used for evaluation.
KW - Background subtraction
KW - Gaussian Mixture Model
KW - Hole Filling Algorithm
UR - http://www.scopus.com/inward/record.url?scp=84893522250&partnerID=8YFLogxK
U2 - 10.1109/SMC.2013.684
DO - 10.1109/SMC.2013.684
M3 - Conference contribution
AN - SCOPUS:84893522250
SN - 9780769551548
T3 - Proceedings - 2013 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2013
SP - 4006
EP - 4011
BT - Proceedings - 2013 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2013
T2 - 2013 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2013
Y2 - 13 October 2013 through 16 October 2013
ER -