Visual Understanding of a Scene by Automatic Movement of a Camera
暂无分享,去创建一个
A method for visual understanding of a scene by efficient automatic movement of a camera is presented in this paper. The purpose of this method is to choose a trajectory for a virtual camera, allowing the user to have a good knowledge of the scene at the end of a minimal flying over. The method is based on techniques for computing a good point of view, used together with various heuristics, in order to have smooth movement of the camera and to avoid fast returns to the starting point, due to local maxima. So, starting from a good view point, the virtual camera moves on the surface of a sphere surrounding the scene, combining good view, smooth camera movement and distance from the starting point based heuristics.
[1] Frank Jardillier,et al. Screen‐Space Constraints for Camera Movements: the Virtual Cameraman , 1998, Comput. Graph. Forum.
[2] Satoru Kawai,et al. A simple method for computing general position in displaying three-dimensional objects , 1988, Comput. Vis. Graph. Image Process..