Computer Vision in Dynamical Scenes

Image description

Traditional computer vision methods for Structure from Motion (SFM), 3D reconstruction and camera pose estimation are mostly designed for static scenes, in which there is no moving objects in the scenes. However, the static scene assumption of the methods severely limits the applications, because most of the real world scenes are dynamical scenes. In this project we have proposed a framework to deal with all kinds of computer vision applications in dynamical scenes. Details coming soon...