Automatic 3D model building from video sequences

We describe progress on automating the construction of 3D geometric models from video sequences. The system we are developing allows a person to walk around a room with a video camera, and from the video sequence alone extract a 3D model of the room. The room can then be graphically rendered together with possible arrangements of previously modelled objects, e.g. CAD models of furniture. The system is designed to ease model acquisition for virtual reality and telepresence applications, however the approach also has application in model based image coding. The approach is based on recent work in computer vision where image primitives are extracted and matched through an image sequence. For example, the simultaneous estimation of epipolar geometry and image corner correspondences. The matching techniques are both robust (detecting and discarding mismatches) and fully automatic. No knowledge of the camera (e.g. its focal length) or motion is required. 3D structure is computed from the matched image primitives (corners, lines and texture). The structure is then triangulated and texture is mapped onto the triangles from intensities in the images. Experimental results are provided for a variety of scenes, including isolated objects acquired with a standard CCD camera, and outdoor scenes acquired with a hand-held camcorder.