Techniques are disclosed for learning and modeling a background for a complex and/or dynamic scene over a period of observations without supervision. A background/foreground component of a computer vision engine may be configured to model a scene using an array of ART networks. The ART networks learn the regularity and periodicity of the scene by observing the scene over a period of time. Thus, the ART networks allow the computer vision engine to model complex and dynamic scene backgrounds in video.
申请公布号
WO2011022279(A2)
申请公布日期
2011.02.24
申请号
WO2010US45227
申请日期
2010.08.11
申请人
BEHAVIORAL RECOGNITION SYSTEMS, INC.;COBB, WESLEY, KENNETH;SEOW, MING-JUNG;YANG, TAO