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/

Zendy Plus

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

Zendy Tools

Zendy Open

Object shape is a key cue that contributes to the semantic understanding ofobjects. In this work we focus on the categorization of real-world object pointclouds to particular shape types. Therein surface description andrepresentation of object shape structure have significant influence on shapecategorization accuracy, when dealing with real-world scenes featuring noisy,partial and occluded object observations. An unsupervised hierarchical learningprocedure is utilized here to symbolically describe surface characteristics onmultiple semantic levels. Furthermore, a constellation model is proposed thathierarchically decomposes objects. The decompositions are described asconstellations of symbols (shape motifs) in a gradual order, hence reflectingshape structure from local to global, i.e., from parts over groups of parts toentire objects. The combination of this multi-level description of surfaces andthe hierarchical decomposition of shapes leads to a representation which allowsto conceptualize shapes. An object discrimination has been observed inexperiments with seven categories featuring instances with sensor noise,occlusions as well as inter-category and intra-category similarities.Experiments include the evaluation of the proposed description and shapedecomposition approach, and comparisons to Fast Point Feature Histograms, aVocabulary Tree and a neural network-based Deep Learning method. Furthermore,experiments are conducted with alternative datasets which analyze thegeneralization capability of the proposed approach.

Visual Object Categorization Based on Hierarchical Shape Motifs Learned From Noisy Point Cloud Decompositions