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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Multi-human 3D pose estimation plays a key role in establishing a seamlessconnection between the real world and the virtual world. Recent efforts adopteda two-stage framework that first builds 2D pose estimations in multiple cameraviews from different perspectives and then synthesizes them into 3D poses.However, the focus has largely been on developing new computer visionalgorithms on the offline video datasets without much consideration on theenergy constraints in real-world systems with flexibly-deployed andbattery-powered cameras. In this paper, we propose an energy-efficientedge-assisted multiple-camera system, dubbed E$^3$Pose, for real-timemulti-human 3D pose estimation, based on the key idea of adaptive cameraselection. Instead of always employing all available cameras to perform 2D poseestimations as in the existing works, E$^3$Pose selects only a subset ofcameras depending on their camera view qualities in terms of occlusion andenergy states in an adaptive manner, thereby reducing the energy consumption(which translates to extended battery lifetime) and improving the estimationaccuracy. To achieve this goal, E$^3$Pose incorporates an attention-based LSTMto predict the occlusion information of each camera view and guide cameraselection before cameras are selected to process the images of a scene, andruns a camera selection algorithm based on the Lyapunov optimization frameworkto make long-term adaptive selection decisions. We build a prototype ofE$^3$Pose on a 5-camera testbed, demonstrate its feasibility and evaluate itsperformance. Our results show that a significant energy saving (up to 31.21%)can be achieved while maintaining a high 3D pose estimation accuracy comparableto state-of-the-art methods.

E$^3$Pose: Energy-Efficient Edge-assisted Multi-camera System for Multi-human 3D Pose Estimation