6533b7d2fe1ef96bd125f7c8

RESEARCH PRODUCT

Homography based egomotion estimation with a common direction

Rémi BoutteauFriedrich FraundorferOlivier SaurerPascal VasseurMarc PollefeysCédric Demonceaux

subject

0209 industrial biotechnologyComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONHomography02 engineering and technology[ INFO.INFO-CV ] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]homography estimationGröbner basis020901 industrial engineering & automationArtificial IntelligenceRobustness (computer science)0202 electrical engineering electronic engineering information engineeringStructure from motion[INFO.INFO-RB]Computer Science [cs]/Robotics [cs.RO]Computer visionComputingMilieux_MISCELLANEOUSstructure-from-motionMathematicsegomotion estimationPhotogrammetrie und Bildanalysebusiness.industryApplied Mathematics[ INFO.INFO-RB ] Computer Science [cs]/Robotics [cs.RO][INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]Standard methodsReference planeComputational Theory and Mathematics020201 artificial intelligence & image processingComputer Vision and Pattern RecognitionArtificial intelligencebusinessSoftwareIndex Terms—Computer vision

description

International audience; In this paper, we explore the different minimal solutions for egomotion estimation of a camera based on homography knowing the gravity vector between calibrated images. These solutions depend on the prior knowledge about the reference plane used by the homography. We then demonstrate that the number of matched points can vary from two to three and that a direct closed-form solution or a Gröbner basis based solution can be derived according to this plane. Many experimental results on synthetic and real sequences in indoor and outdoor environments show the efficiency and the robustness of our approach compared to standard methods.

yearjournalcountryeditionlanguage
2017-02-01
10.1109/tpami.2016.2545663https://doi.org/10.1109/tpami.2016.2545663