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 an approach for recognizing all objects in a scene and estimatingtheir full pose from an accurate 3D instance-aware semantic reconstructionusing an RGB-D camera. Our framework couples convolutional neural networks(CNNs) and a state-of-the-art dense Simultaneous Localisation and Mapping(SLAM) system, ElasticFusion, to achieve both high-quality semanticreconstruction as well as robust 6D pose estimation for relevant objects. Whilethe main trend in CNN-based 6D pose estimation has been to infer object'sposition and orientation from single views of the scene, our approach exploresperforming pose estimation from multiple viewpoints, under the conjecture thatcombining multiple predictions can improve the robustness of an objectdetection system. The resulting system is capable of producing high-qualityobject-aware semantic reconstructions of room-sized environments, as well asaccurately detecting objects and their 6D poses. The developed method has beenverified through experimental validation on the YCB-Video dataset and a newlycollected warehouse object dataset. Experimental results confirmed that theproposed system achieves improvements over state-of-the-art methods in terms ofsurface reconstruction and object pose prediction. Our code and video areavailable at https://sites.google.com/view/object-rpe.

Object-RPE: Dense 3D Reconstruction and Pose Estimation with Convolutional Neural Networks for Warehouse Robots