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

Human pose estimation is a very active research field, stimulated by itsimportant applications in robotics, entertainment or health and sportssciences, among others. Advances in convolutional networks triggered noticeableimprovements in 2D pose estimation, leading modern 3D markerless motion capturetechniques to an average error per joint of 20 mm. However, with theproliferation of methods, it is becoming increasingly difficult to make aninformed choice. Here, we review the leading human pose estimation methods ofthe past five years, focusing on metrics, benchmarks and method structures. Wepropose a taxonomy based on accuracy, speed and robustness that we use toclassify de methods and derive directions for future research.

A review of 3D human pose estimation algorithms for markerless motion capture