TY - GEN
T1 - A fast algorithm for adaptive background model construction using Parzen density estimation
AU - Tanaka, Tatsuya
AU - Arita, Daisaku
AU - Shimada, Atsushi
AU - Taniguchi, Rin Ichiro
PY - 2007
Y1 - 2007
N2 - Non-parametric representation of pixel intensity distribution is quite effective to construct proper background model and to detect foreground objects accurately. However, from the viewpoint of practical application, the computation cost of the distribution estimation should be reduced. In this paper, we present fast estimation of the probability density function (PDF) of pixel value using Parzen density estimation and foreground object detection based on the estimated PDF. Here, the PDF is computed by partially updating the PDF estimated at the previous frame, and it greatly reduces the computation cost of the PDF estimation. Thus, the background model adapts quickly to changes in the scene and, therefore, foreground objects can be robustly detected. Several experiments show the effectiveness of our approach.
AB - Non-parametric representation of pixel intensity distribution is quite effective to construct proper background model and to detect foreground objects accurately. However, from the viewpoint of practical application, the computation cost of the distribution estimation should be reduced. In this paper, we present fast estimation of the probability density function (PDF) of pixel value using Parzen density estimation and foreground object detection based on the estimated PDF. Here, the PDF is computed by partially updating the PDF estimated at the previous frame, and it greatly reduces the computation cost of the PDF estimation. Thus, the background model adapts quickly to changes in the scene and, therefore, foreground objects can be robustly detected. Several experiments show the effectiveness of our approach.
UR - http://www.scopus.com/inward/record.url?scp=44849097817&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=44849097817&partnerID=8YFLogxK
U2 - 10.1109/AVSS.2007.4425366
DO - 10.1109/AVSS.2007.4425366
M3 - Conference contribution
AN - SCOPUS:44849097817
SN - 9781424416967
T3 - 2007 IEEE Conference on Advanced Video and Signal Based Surveillance, AVSS 2007 Proceedings
SP - 528
EP - 533
BT - 2007 IEEE Conference on Advanced Video and Signal Based Surveillance, AVSS 2007 Proceedings
T2 - 2007 IEEE Conference on Advanced Video and Signal Based Surveillance, AVSS 2007
Y2 - 5 September 2007 through 7 September 2007
ER -