摘要 |
<P>PROBLEM TO BE SOLVED: To improve the accuracy of subject three-dimensional position estimation by handling a plurality of synchronously-captured camera videos in an integrated manner. <P>SOLUTION: Based on a three-dimensional world coordinate of a subject in an initial frame and camera images of a plurality of frames captured by a plurality of cameras, the three-dimensional world coordinate of the subject in the initial frame is projected on an XY coordinate on a specific plane, the XY coordinate of the subject on the specific plane is estimated based on temporal axis information, and the XY coordinate of the subject on the specific plane is evaluated based on inter-camera information, thereby estimating a three-dimensional world coordinate of the subject in a subsequent frame. <P>COPYRIGHT: (C)2013,JPO&INPIT |