Simultaneous localization and mapping using multiple view feature descriptors

Jason Meltzer, Rakesh Gupta, Ming Hsuan Yang, Stefano Soatto

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Citations (Scopus)

Abstract

We propose a vision-based SLAM algorithm incorporating feature descriptors derived from multiple views of a scene, incorporating illumination and viewpoint variations. These descriptors are extracted from video and then applied to the challenging task of wide baseline matching across significant viewpoint changes. The system incorporates a single camera on a mobile robot in an extended Kalman filter framework to develop a 3D map of the environment and determine egomotion. At the same time, the feature descriptors are generated from the video sequence, which can be used to localize the robot when it returns to a mapped location. The kidnapped robot problem is addressed by matching descriptors without any estimate of position, then determining the epipolar geometry with respect to a known position in the map.

Original languageEnglish
Title of host publication2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Pages1550-1555
Number of pages6
Publication statusPublished - 2004 Dec 1
Event2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) - Sendai, Japan
Duration: 2004 Sep 282004 Oct 2

Publication series

Name2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Volume2

Conference

Conference2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
CountryJapan
CitySendai
Period04/9/2804/10/2

    Fingerprint

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

Meltzer, J., Gupta, R., Yang, M. H., & Soatto, S. (2004). Simultaneous localization and mapping using multiple view feature descriptors. In 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (pp. 1550-1555). (2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS); Vol. 2).