TY - GEN
T1 - Dictionary learning for robust background modeling
AU - Sivalingam, Ravishankar
AU - D'Souza, Alden
AU - Morellas, Vassilios
AU - Papanikolopoulos, Nikolaos P
AU - Bazakos, Mike E
AU - Miezianko, Roland
PY - 2011
Y1 - 2011
N2 - Background subtraction is a fundamental task in many computer vision applications, such as robotics and automated surveillance systems. The performance of high-level visions tasks such as object detection and tracking is dependent on effective foreground detection techniques. In this paper, we propose a novel background modeling algorithm that represents the background as a linear combination of dictionary atoms and the foreground as a sparse error, when one uses the respective set of dictionary atoms as basis elements to linearly approximate/reconstruct a new image. The dictionary atoms represent variations of the background model, and are learned from the training frames. The sparse foreground estimation during the training and performance phases is formulated as a Lasso [1] problem, while the dictionary update step in the training phase is motivated from the K-SVD algorithm [2]. Our proposed method works well in the presence of foreground in the training frames, and also gives the foreground masks for the training frames as a by-product of the batch training phase. Experimental validation is provided on standard datasets with ground truth information, and the receiver operating characteristic (ROC) curves are shown.
AB - Background subtraction is a fundamental task in many computer vision applications, such as robotics and automated surveillance systems. The performance of high-level visions tasks such as object detection and tracking is dependent on effective foreground detection techniques. In this paper, we propose a novel background modeling algorithm that represents the background as a linear combination of dictionary atoms and the foreground as a sparse error, when one uses the respective set of dictionary atoms as basis elements to linearly approximate/reconstruct a new image. The dictionary atoms represent variations of the background model, and are learned from the training frames. The sparse foreground estimation during the training and performance phases is formulated as a Lasso [1] problem, while the dictionary update step in the training phase is motivated from the K-SVD algorithm [2]. Our proposed method works well in the presence of foreground in the training frames, and also gives the foreground masks for the training frames as a by-product of the batch training phase. Experimental validation is provided on standard datasets with ground truth information, and the receiver operating characteristic (ROC) curves are shown.
UR - http://www.scopus.com/inward/record.url?scp=84864438578&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84864438578&partnerID=8YFLogxK
U2 - 10.1109/ICRA.2011.5979981
DO - 10.1109/ICRA.2011.5979981
M3 - Conference contribution
AN - SCOPUS:84864438578
SN - 9781612843865
T3 - Proceedings - IEEE International Conference on Robotics and Automation
SP - 4234
EP - 4239
BT - 2011 IEEE International Conference on Robotics and Automation, ICRA 2011
T2 - 2011 IEEE International Conference on Robotics and Automation, ICRA 2011
Y2 - 9 May 2011 through 13 May 2011
ER -