English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Change detection, i.e., anomaly detection from local maps built by a mobilerobot at multiple different times, is a challenging problem to solve inpractice. Most previous work either cannot be applied to scenarios where thesize of the map collection is large, or simply assumed that the robotself-location is globally known. In this paper, we tackle the problem ofsimultaneous self-localization and change detection, by reformulating theproblem as a map retrieval problem, and propose a local map descriptor with acompressed bag-of-words (BoW) structure as a scalable solution. We make thefollowing contributions. (1) To enable a direct comparison of the spatiallayout of visual features between different local maps, the origin of the localmap coordinate (termed "viewpoint") is planned by scene parsing and determinedby our "viewpoint planner" to be invariant against small variations inself-location and changes, aiming at providing similar viewpoints for similarscenes (i.e., the relevant map pair). (2) We extend the BoW model to enable theuse of not only the appearance (e.g., polestar) but also the spatial layout(e.g., spatial pyramid) of visual features with respect to the plannedviewpoint. The key observation is that the planned viewpoint (i.e., the originof local map coordinate) acts as a pseudo viewpoint that is usually required byspatial BoW (e.g., SPM) and also by anomaly detection (e.g., NN-d, LOF). (3)Experimental results on a challenging "loop-closing" scenario show that theproposed method outperforms previous BoW methods in self-localization, andfurthermore, that the use of both appearance and pose information in changedetection produces better results than the use of either information alone.

Local Map Descriptor for Compressive Change Retrieval