Accurate Camera Registration in Urban Environments Using High-Level Feature Matching

Anil Armagan, Martin Hirzer, Peter Roth and Vincent Lepetit

Abstract

We propose a method for accurate camera pose estimation in urban environments from single images and 2D maps made of the surrounding buildings’ outlines. Our approach bridges the gap between learning-based approaches and geometric approaches: We use recent semantic segmentation techniques for extracting the buildings’ edges and the façades’ normals in the images and minimal solvers [14] to compute the camera pose accurately and robustly. We propose two such minimal solvers: one based on three correspondences of buildings’ corners from the image and the 2D map and another one based on two corner correspondences plus one façade correspondence.

Session

Spotlights

Files

Paper (PDF)
Supplementary (PDF)
Video (MP4)

DOI

10.5244/C.31.9
https://dx.doi.org/10.5244/C.31.9

Citation

Bibtex

            @inproceedings{BMVC2017_9,
                title={Accurate Camera Registration in Urban Environments Using High-Level Feature Matching},
                author={Anil Armagan, Martin Hirzer, Peter Roth and Vincent Lepetit},
                year={2017},
                month={September},
                pages={9.1-9.12},
                articleno={9},
                numpages={12},
                booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
                publisher={BMVA Press},
                editor={Tae-Kyun Kim, Stefanos Zafeiriou, Gabriel Brostow and Krystian Mikolajczyk},
                doi={10.5244/C.31.9},
                isbn={1-901725-60-X},
                url={https://dx.doi.org/10.5244/C.31.9}
            }