eduzhai > Applied Sciences > Engineering >

Enhanced Normalized Mutual Information for Localization in Noisy Environments

  • king
  • (0) Download
  • 20210507
  • Save

... pages left unread,continue reading

Document pages: 5 pages

Abstract: Fine localization is a crucial task for autonomous vehicles. Although manyalgorithms have been explored in the literature for this specific task, thegoal of getting accurate results from commodity sensors remains a challenge. Asautonomous vehicles make the transition from expensive prototypes to productionitems, the need for inexpensive, yet reliable solutions is increasing rapidly.This article considers scenarios where images are captured with inexpensivecameras and localization takes place using pre-loaded fine maps of local roadsas side information. The techniques proposed herein extend schemes based onnormalized mutual information by leveraging the likelihood of shades ratherthan exact sensor readings for localization in noisy environments. Thisalgorithmic enhancement, rooted in statistical signal processing, offerssubstantial gains in performance. Numerical simulations are used to highlightthe benefits of the proposed techniques in representative applicationscenarios. Analysis of a Ford image set is performed to validate the corefindings of this work.

Please select stars to rate!


0 comments Sign in to leave a comment.

    Data loading, please wait...