パーティクルフィルタと単眼視点固定カメラを用いた3 次元空間上での物体領域推定

概要

論文の詳細を見る
In recent years, demands for video surveillance system have increased. Usually, a multi-cameras systemis used to have some 3D information in video surveillance system. But such a system needs much cost andtime to be put in place. For a low-cost system, we prefer to use only one fixed-view point camera which iscalibrated using the projective geometry which projects 3D points onto 2D image. But using only onecamera, infinite points on 3D space correspond to a single point on 2D image. In this paper, we propose ahigh performance method for estimating areas of moving objects on 3D space using one fixed-viewpointcamera and particle filters. Using some constraints on 3D size and position of objects, our method restrictsthe generation of particles which represent the candidate area of the object. Therefore, the distribution of theparticles shows the appropriate estimation of the object.
2011-12-01