Two-stage visual localisation: Landmark-based pose initialisation and model-based pose refinement

Z Z Chen, P Pe, J McDermid, N Pears

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


We show that landmark based localisation (LBL) and Lowe's model-based localisation (MBL) are complementary in that LBL provides a pose initialisation to MBL, which is a necessary input to the algorithm, and MBL can then refine that pose to a give more accurate pose estimate than LBL alone can provide. For LBL, we extend Betke and Gurvit's method, such that it can be used with standard perspective cameras (their original proposal was for omnidirectional cameras) in order to get a useful initial value as an input to Lowe's method. Intensive experiments have been carried out to analyse how camera parameters (intrinsic and extrinsic) affect the LBL position and orientation errors in the initial pose estimate. In error propagation experiments, we show that the position and orientation of a robot are sensitive to focal length and errors in imaged feature positions respectively. In the MBL pose refinement phase, we find that MBL is able to refine the position estimate, but the error in orientation estimate remains the same.

Original languageEnglish
Title of host publication2005 IEEE/RSJ International Conference on Intelligent Robots and Systems, Vols 1-4
Place of PublicationNEW YORK
Number of pages7
ISBN (Print)0-7803-8912-3
Publication statusPublished - 2005
EventIEEE/RSJ International Conference on Intelligent Robots and Systems - Edmonton
Duration: 2 Aug 20056 Aug 2005


ConferenceIEEE/RSJ International Conference on Intelligent Robots and Systems


  • mobile robots
  • localization
  • visual landmarks
  • navigation

Cite this