NETE Towards 3D Pipe Reconstruction Employing Affine Transformations from Video Information

The development of a virtual scenario is desirablein a number of hostile environments such as in mining, or sewerpipelines to inspect its current condition and to identify possiblefailures. Obtaining a virtual image through the reconstruction ofthe mineshaft or inner pipe is a valuable tool for assessment andfault detection. In this paper, we present results for our 3Dreconstruction approach, which proposes to employ regions withaffine 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 arerequired to obtain the orientation and position of the camera andto get the structure of the scene leading to the creation of the 3Denvironment. The algorithm is presented as well as its results,which highlights the potential of the method.