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

As a consequence of an ever-increasing number of service robots, there is agrowing demand for highly accurate real-time 3D object recognition. Consideringthe expansion of robot applications in more complex and dynamic environments,itis evident that it is not possible to pre-program all object categories andanticipate all exceptions in advance. Therefore, robots should have thefunctionality to learn about new object categories in an open-ended fashionwhile working in the environment.Towards this goal, we propose a deep transferlearning approach to generate a scale- and pose-invariant object representationby considering shape and texture information in multiple colorspaces. Theobtained global object representation is then fed to an instance-based objectcategory learning and recognition,where a non-expert human user exists in thelearning loop and can interactively guide the process of experience acquisitionby teaching new object categories, or by correcting insufficient or erroneouscategories. In this work, shape information encodes the common patterns of allcategories, while texture information is used to describes the appearance ofeach instance in detail.Multiple color space combinations and networkarchitectures are evaluated to find the most descriptive system. Experimentalresults showed that the proposed network architecture out-performed theselected state-of-the-art approaches in terms of object classification accuracyand scalability. Furthermore, we performed a real robot experiment in thecontext of serve-a-beer scenario to show the real-time performance of theproposed approach.

Open-Ended Fine-Grained 3D Object Categorization by Combining Shape and Texture Features in Multiple Colorspaces