Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: May 25, 2026

Sit-to-stand-and-walk from 120% Knee Height: A Novel Approach to Assess Dynamic Postural Control Independent of Lead-limb

Sit-to-stand-and-walk from 120% Knee Height: A Novel Approach to Assess Dynamic Postural Control Independent of Lead-limb

Published on: August 30, 2016

Hierarchical pose estimation for human gait analysis.

Jens Spehr¹, Simon Winkelbach, Friedrich M Wahl

¹Institut für Robotik und Prozessinformatik, Technische Universität Braunschweig, D-38106 Braunschweig, Germany. J.Spehr@tu-bs.de

Computer Methods and Programs in Biomedicine

|February 7, 2012

Summary

This study introduces novel linked hierarchical graphical models for efficient human body pose analysis. These models leverage shared visual primitives to accelerate likelihood evaluation, improving human gait analysis and body detection.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

The effect of distal tibial rotation during high tibial osteotomy on the contact pressures in the knee and ankle joints.

Knee surgery, sports traumatology, arthroscopy : official journal of the ESSKA·2015

Same author

Effect of medial opening wedge high tibial osteotomy on intraarticular knee and ankle contact pressures.

Journal of orthopaedic research : official publication of the Orthopaedic Research Society·2014

Same author

Information and communication technologies for promoting and sustaining quality of life, health and self-sufficiency in ageing societies--outcomes of the Lower Saxony Research Network Design of Environments for Ageing (GAL).

Informatics for health & social care·2014

Same author

Workspace and pivot point for robot-assisted endoscope guidance in functional endonasal sinus surgery (FESS).

The international journal of medical robotics + computer assisted surgery : MRCAS·2014

Same author

The Lower Saxony research network design of environments for ageing: towards interdisciplinary research on information and communication technologies in ageing societies.

Informatics for health & social care·2010

Same author

Monitoring systems for the support of home care.

Informatics for health & social care·2010

Area of Science:

Computer Vision
Machine Learning
Robotics

Background:

Articulated structures, such as the human body, possess numerous degrees of freedom, complicating configuration likelihood evaluation.
Existing methods struggle with the computational complexity of analyzing all possible human body configurations.

Purpose of the Study:

To develop efficient probabilistic models for evaluating the likelihood of articulated structures.
To improve human body pose and gait analysis by exploiting shared visual primitives.
To introduce a scalable hierarchical representation for human body analysis.

Main Methods:

Proposed novel linked hierarchical graphical models.
Utilized a hierarchical Markov random field to integrate shared visual primitives within a probabilistic framework.

Related Experiment Videos

Last Updated: May 25, 2026

Sit-to-stand-and-walk from 120% Knee Height: A Novel Approach to Assess Dynamic Postural Control Independent of Lead-limb

Sit-to-stand-and-walk from 120% Knee Height: A Novel Approach to Assess Dynamic Postural Control Independent of Lead-limb

Published on: August 30, 2016

Developed a scalable hierarchical representation of the human body.

Main Results:

The proposed models efficiently evaluate likelihoods of articulated structures by sharing visual primitives.
The hierarchical representation is well-suited for human gait analysis from frontal camera views.
Sharing primitives significantly accelerated evaluation speed.
The framework demonstrated robustness in scalable human body detection.

Conclusions:

Linked hierarchical graphical models offer an efficient approach to likelihood evaluation for articulated structures.
The proposed method enhances human gait analysis and scalable body detection.
Integrating shared visual primitives in a hierarchical probabilistic framework improves performance and scalability.