3D acquisition of archaeological heritage from images
Marc Pollefeys, Maarten Vergauwen, Kurt Cornelis, Luc Van Gool · 2001
In this contribution an approach is proposed that can capture the 3D shape and appearance of objects, monuments or sites from photographs or video. The flexibility of the approach allows us to deal with uncalibrated hand-held camera images. In addition, through the use of advanced computer vision algorithms the process is largely automated. Both these factors make the approach ideally suited to applications in archaeology. Not only does it become feasible to obtain photo-realistic virtual reconstructions of monuments and sites, but also stratigraphy layers and separate building blocks can be reconstructed. These can then be used as detailed records of the excavations or allow virtual re-assemblage of monuments. Since the motion of the camera is also computed, it also becomes possible to augment video streams of ancient remains with virtual reconstruction. The proposed approach retrieves both the structure of a scene and the motion of the camera from an image sequence. In a first step features are extracted and matched over consecutive images. This step is followed by a structurefrom -motion algorithm that yields a sparse 3D reconstruction (i.e. the matched 3D features) and the path of the camera. These results are enhanced through auto-calibration and bundle adjustment. To allow a full surface reconstruction of the observed scene, the images are rectified so that a standard stereo algorithm can be used to determine dense disparity maps. By combining several of these maps, accurate depth maps are computed. These can then be integrated together to yield a dense 3D surface model. By making use of texture mapping photo-realistic models can be obtained.