ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., III-3, 99-106, 2016
https://doi.org/10.5194/isprs-annals-III-3-99-2016
© Author(s) 2016. This work is distributed under
the Creative Commons Attribution 3.0 License.
 
03 Jun 2016
EFFICIENT WIDE BASELINE STRUCTURE FROM MOTION
Mario Michelini and Helmut Mayer Institute for Applied Computer Science, Bundeswehr University Munich, Munich, Germany
Keywords: Structure from Motion, Wide Baseline, Pose Estimation, Hierarchical, Graph, Reconstruction, Embedding Abstract. This paper presents a Structure from Motion approach for complex unorganized image sets. To achieve high accuracy and robustness, image triplets are employed and (an approximate) camera calibration is assumed to be known. The focus lies on a complete linking of images even in case of large image distortions, e.g., caused by wide baselines, as well as weak baselines. A method for embedding image descriptors into Hamming space is proposed for fast image similarity ranking. The later is employed to limit the number of pairs to be matched by a wide baseline method. An iterative graph-based approach is proposed formulating image linking as the search for a terminal Steiner minimum tree in a line graph. Finally, additional links are determined and employed to improve the accuracy of the pose estimation. By this means, loops in long image sequences are implicitly closed. The potential of the proposed approach is demonstrated by results for several complex image sets also in comparison with VisualSFM.
Conference paper (PDF, 3670 KB)


Citation: Michelini, M. and Mayer, H.: EFFICIENT WIDE BASELINE STRUCTURE FROM MOTION, ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., III-3, 99-106, https://doi.org/10.5194/isprs-annals-III-3-99-2016, 2016.

BibTeX EndNote Reference Manager XML