Skip to Main content Skip to Navigation
Conference papers

Visual words for 3D reconstruction and pose computation

Srikrishna Bhat 1 Marie-Odile Berger 1 Frédéric Sur 1
1 MAGRIT - Visual Augmentation of Complex Environments
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : Visual vocabularies are standard tools in the object/image classification literature, and are emerging as a new tool for building point correspondences for pose estimation. This paper proposes several visual word based methods for point matching, with structure from motion and pose estimation applications in view. The three dimensional geometry of a scene is first extracted with bundle adjustment techniques based on the keypoint correspondences. These correspondences are obtained by grouping the set of all SIFT descriptors from the training images into visual words. We obtain a more accurate 3D geometry than with classical image-to-image point matching. In the second step, these visual words serve as 3D point descriptors robust to viewpoint change, and are then used for building 2D-3D correspondences for a test image, yielding the pose of the camera by solving the PnP problem. We compare several visual word formation techniques w.r.t robustness to viewpoint change between the learning and test images and discuss the required computational time.
Document type :
Conference papers
Complete list of metadata

Cited literature [22 references]  Display  Hide  Download

https://hal.inria.fr/inria-00576915
Contributor : Frédéric Sur <>
Submitted on : Tuesday, March 15, 2011 - 4:16:39 PM
Last modification on : Tuesday, May 18, 2021 - 3:42:01 PM
Long-term archiving on: : Thursday, June 16, 2011 - 3:04:38 AM

File

PID1714817.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Srikrishna Bhat, Marie-Odile Berger, Frédéric Sur. Visual words for 3D reconstruction and pose computation. The First Joint 3DIM/3DPVT Conference, May 2011, Hangzhou, China. pp.326 - 333, ⟨10.1109/3DIMPVT.2011.48⟩. ⟨inria-00576915⟩

Share

Metrics

Record views

430

Files downloads

486