6533b7d5fe1ef96bd1263e09
RESEARCH PRODUCT
Accurate keyframe selection and keypoint tracking for robust visual odometry
Marco FanfaniFabio BellaviaCarlo Colombosubject
0209 industrial biotechnologyMatching (graph theory)Computer scienceVisual odometryComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION02 engineering and technologyKeyframe selectionRANSAC020901 industrial engineering & automation0202 electrical engineering electronic engineering information engineeringStructure from motionComputer visionVisual odometryVisual Odometry Structure from Motion RANSAC feature matching keyframe selectionPoseSelection (genetic algorithm)Settore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniRANSACSettore INF/01 - InformaticaFeature matchingbusiness.industryStructure from motionPattern recognitionComputer Science ApplicationsHardware and ArchitectureFeature (computer vision)Pattern recognition (psychology)020201 artificial intelligence & image processingComputer Vision and Pattern RecognitionArtificial intelligencebusinessSoftwaredescription
This paper presents a novel stereo visual odometry (VO) framework based on structure from motion, where a robust keypoint tracking and matching is combined with an effective keyframe selection strategy. In order to track and find correct feature correspondences a robust loop chain matching scheme on two consecutive stereo pairs is introduced. Keyframe selection is based on the proportion of features with high temporal disparity. This criterion relies on the observation that the error in the pose estimation propagates from the uncertainty of 3D points—higher for distant points, that have low 2D motion. Comparative results based on three VO datasets show that the proposed solution is remarkably effective and robust even for very long path lengths.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 2016-07-08 |