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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

We present a novel method for estimation of 3D human poses from amulti-camera setup, employing distributed smart edge sensors coupled with abackend through a semantic feedback loop. 2D joint detection for each cameraview is performed locally on a dedicated embedded inference processor. Only thesemantic skeleton representation is transmitted over the network and raw imagesremain on the sensor board. 3D poses are recovered from 2D joints on a centralbackend, based on triangulation and a body model which incorporates priorknowledge of the human skeleton. A feedback channel from backend to individualsensors is implemented on a semantic level. The allocentric 3D pose isbackprojected into the sensor views where it is fused with 2D joint detections.The local semantic model on each sensor can thus be improved by incorporatingglobal context information. The whole pipeline is capable of real-timeoperation. We evaluate our method on three public datasets, where we achievestate-of-the-art results and show the benefits of our feedback architecture, aswell as in our own setup for multi-person experiments. Using the feedbacksignal improves the 2D joint detections and in turn the estimated 3D poses.

Real-Time Multi-View 3D Human Pose Estimation using Semantic Feedback to Smart Edge Sensors