Incremental 3D reconstruction using affine invariance in stereo image

Abstract

The need for mapping small objects in such areas as museum collections may be met by using laser scanning techniques which are likely the best and the most reliable. However, the costs associated with these techniques prohibit their use apart from that such objects are too fragile for repeated handling. Therefore, the alternative is the use of passive methods like stereovision. In this paper we presents a contribution to the problem of 3D surface reconstruction under affine projections in stereo image. Method starts by using the affine invariance to caracterize shape on the objects contours. Such approximation is interesting if we consider small objects regards to the distance from sensors. Additionally, a methodology to estimate the affine transformation that best aligns the matched contours is also presented: a scale factor a, a shift value lo and an affinity matrix A are computed to establish a local matching of points that preserves the circular order of points. In order to validate the proposed matching methodology, some results on stereovision context are exposed with scene containing small archeological 3D objects.