公开(公告)号：GB2503621B

公开(公告)日：2014-03-12

申请号：GB201318426

申请日：2012-05-02

Applicant: IBM

Inventor： BROWN LISA MARIE ,  FERIS ROGERIO SCHMIDT ,  PANKANTI SHARATHCHANDRA UMAPATHIRAO ,  DATTA ANKUR

IPC: H04N5/232 ,  G06T13/20 ,  G06T17/00

Abstract: A moving object tracked within a field of view environment of a two-dimensional data feed of a calibrated video camera is represented by a three-dimensional model. An appropriate three-dimensional mesh-based volumetric model for the object is initialized by using a back-projection of a corresponding two-dimensional image. A texture of the object is projected onto the three-dimensional model, and two-dimensional tracks of the object are upgraded to three-dimensional motion to drive a three-dimensional model.

公开(公告)号：GB2496547A

公开(公告)日：2013-05-15

申请号：GB201302244

申请日：2011-07-06

Applicant: IBM

Inventor： DING LEI ,  FAN QUANFU ,  PANKANTI SHARATHCHANDRA UMAPATHIRAO

IPC: G06K9/00 ,  G08B13/196

Abstract: In an embodiment, automated analysis of video data for determination of human behavior includes providing a programmable device that segments a video stream into a plurality of discrete individual frame image primitives which are combined into a visual event that may encompass an activity of concern as a function of a hypothesis. The visual event is optimized by setting a binary variable to true or false as a function of one or more constraints. The optimized visual event is processed in view of associated non-video transaction data and the binary variable by associating the optimized visual event with a logged transaction if associable, issuing an alert if the binary variable is true and the optimized visual event is not associable with the logged transaction, and dropping the optimized visual event if the binary variable is false and the optimized visual event is not associable.