Towards 3D pipe reconstruction employing affine transformations from video information

The development of a virtual scenario is desirable in a number of hostile environments such as in mining, or sewer pipelines to inspect its current condition and to identify possible failures. Obtaining a virtual image through the reconstruction of the mineshaft or inner pipe is a valuable tool for assessment and fault detection. In this paper, we present results for our 3D reconstruction approach, which proposes to employ regions with affine transformations that are used as dense correspondences. These features are calculated through local correspondences, such as the SIFT (Scale-invariant feature transform) and SURF (Speeded Up Robust Features). The correspondences are required to obtain the orientation and position of the camera and to get the structure of the scene leading to the creation of the 3D environment. The algorithm is presented as well as its results, which highlights the potential of the method.