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

This paper presents a feature encoding method of complex 3D objects forhigh-level semantic features. Recent approaches to object recognition methodsbecome important for semantic simultaneous localization and mapping (SLAM).However, there is a lack of consideration of the probabilistic observationmodel for 3D objects, as the shape of a 3D object basically follows a complexprobability distribution. Furthermore, since the mobile robot equipped with arange sensor observes only a single view, much information of the object shapeis discarded. These limitations are the major obstacles to semantic SLAM andview-independent loop closure using 3D object shapes as features. In order toenable the numerical analysis for the Bayesian inference, we approximate thetrue observation model of 3D objects to tractable distributions. Since theobservation likelihood can be obtained from the generative model, we formulatethe true generative model for 3D object with the Bayesian networks. To capturethese complex distributions, we apply a variational auto-encoder. To analyzethe approximated distributions and encoded features, we perform classificationwith maximum likelihood estimation and shape retrieval.

A Variational Feature Encoding Method of 3D Object for Probabilistic Semantic SLAM