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

We present a Bayesian object observation model for complete probabilisticsemantic SLAM. Recent studies on object detection and feature extraction havebecome important for scene understanding and 3D mapping. However, 3D shape ofthe object is too complex to formulate the probabilistic observation model;therefore, performing the Bayesian inference of the object-oriented features aswell as their pose is less considered. Besides, when the robot equipped with anRGB mono camera only observes the projected single view of an object, asignificant amount of the 3D shape information is abandoned. Due to theselimitations, semantic SLAM and viewpoint-independent loop closure usingvolumetric 3D object shape is challenging. In order to enable the completeformulation of probabilistic semantic SLAM, we approximate the observationmodel of a 3D object with a tractable distribution. We also estimate thevariational likelihood from the 2D image of the object to exploit its observedsingle view. In order to evaluate the proposed method, we perform pose andfeature estimation, and demonstrate that the automatic loop closure worksseamlessly without additional loop detector in various environments.

A Variational Observation Model of 3D Object for Probabilistic Semantic SLAM