Kybernetika 46 no. 5, 926-937, 2010

The structure-from-motion reconstruction pipeline - a survey with focus on short image sequences

Klaus Häming and Gabriele Peters

Abstract:

The problem addressed in this paper is the reconstruction of an object in the form of a realistically textured 3D model from images taken with an uncalibrated camera. We especially focus on reconstructions from {\em short} image sequences. By means of a description of an easy to use system, which is able to accomplish this in a fast and reliable way, we give a survey of all steps of the reconstruction pipeline. For the purpose of developing a coherent reconstruction system it is necessary to integrate a number of different techniques such as feature detection, algorithms of the RANSAC-family, and methods for auto-calibration. We describe and review recent developments of distinct strands of these techniques. While developing our system the necessity of improvements of several steps of the state-of-the-art reconstruction pipeline emerged. Two of these innovations are introduced in detail in this paper: an advanced SIFT-based feature detector and a two-stage RANSAC process facilitating a faster selection of relevant object points. In addition, we give a recommendation regarding auto-calibration for short image sequences.

Keywords:

RANSAC, structure from motion, feature detection, auto-calibration

Classification:

68U10, 68U05