Structure from Motion Estimation with Positional Cues

Linus Svärm, Magnus Oskarsson

Research output: Chapter in Book/Report/Conference proceedingPaper in conference proceedingpeer-review

Abstract

We present a system for structure from motion estimation using additional positioning data such as GPS data. The system incorporates the additional data in the outlier detection, the initial estimates and the final bundle adjustment. The initial solution is based on a novel objective function which is solved using convex optimization. This objective function is also used for outlier detection and removal. The initial solution is then refined based on a novel near $L_2$ minimization of the reprojection error using convex optimization methods. We present results on synthetic and real data, that shows the robustness, accuracy and speed of the proposed method.
Original languageEnglish
Title of host publicationLecture Notes in Computer Science (Image Analysis : 18th Scandinavian Conference, SCIA 2013, Espoo, Finland, June 17-20, 2013. Proceedings)
EditorsJoni-Kristian Kämäräinen, Markus Koskela
PublisherSpringer
Pages522-532
Number of pages11
Volume7944
ISBN (Print)978-3-642-38885-9 (print), 978-3-642-38886-6 (online)
DOIs
Publication statusPublished - 2013
Event18th Scandinavian Conference on Image Analysis (SCIA 2013) - Espoo, Finland
Duration: 2013 Jun 172013 Jun 20

Publication series

Name
Volume7944
ISSN (Print)1611-3349
ISSN (Electronic)0302-9743

Conference

Conference18th Scandinavian Conference on Image Analysis (SCIA 2013)
Country/TerritoryFinland
CityEspoo
Period2013/06/172013/06/20

Subject classification (UKÄ)

  • Mathematics
  • Computer Vision and Robotics (Autonomous Systems)

Fingerprint

Dive into the research topics of 'Structure from Motion Estimation with Positional Cues'. Together they form a unique fingerprint.

Cite this