Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

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

LAG3-centered multiplex immune profiling as a prognostic biomarker in hepatocellular carcinoma patients receiving Anti-PD-1 antibodies plus lenvatinib therapy.

Frontiers in oncology·2026
Same author

Distinct trajectories of low anterior resection syndrome following ileostomy reversal.

Frontiers in medicine·2026
Same author

Pan-cancer analysis of tissue-plasma genomic concordance reveals enhanced concordance with liver metastasis and plasma clonality as predictor of poorer overall survival.

NPJ precision oncology·2026
Same author

RTF2Mesh: Restricted Tangent Face Based Mesh Compression With Neural Displacement Fields.

IEEE transactions on visualization and computer graphics·2026
Same author

OffsetCrust: Variable-Radius Offset Approximation with Power Diagrams.

IEEE transactions on visualization and computer graphics·2026
Same author

Aging induces the hepatic CYP4A-20-HETE axis with stage-dependent oxylipin remodeling.

Prostaglandins & other lipid mediators·2026

Related Experiment Video

Updated: Mar 11, 2026

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers
12:39

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

8.3K

Human Pose Estimation from Monocular Images: A Comprehensive Survey.

Wenjuan Gong1, Xuena Zhang2, Jordi Gonzàlez3

  • 1Department of Computer Science and Technology, China University of Petroleum, Qingdao 266580, China. wenjuangong@upc.edu.cn.

Sensors (Basel, Switzerland)
|November 30, 2016
PubMed
Summary

This survey provides a comprehensive review of human pose estimation from monocular images, covering both classic and deep learning-based methods. It categorizes approaches and details motion-related techniques for applications like video surveillance.

Keywords:
bottom-up methodsdiscriminative methodsgenerative methodshuman body modelshuman pose estimationtop-down methods

More Related Videos

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

5.6K
Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping
09:41

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Published on: April 21, 2023

2.3K

Related Experiment Videos

Last Updated: Mar 11, 2026

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers
12:39

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

8.3K
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

5.6K
Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping
09:41

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Published on: April 21, 2023

2.3K

Area of Science:

  • Computer Vision
  • Machine Learning
  • Image Analysis

Background:

  • Human pose estimation is crucial for understanding human actions in images.
  • Existing surveys often focus on specific aspects, leaving a gap in comprehensive reviews.
  • Recent deep learning advancements necessitate an updated overview.

Purpose of the Study:

  • To provide a comprehensive survey of human pose estimation from monocular images.
  • To cover milestone works and recent advancements, particularly those based on deep learning.
  • To offer a structured overview of the problem domain.

Main Methods:

  • The survey categorizes methods based on a standard computer vision pipeline: feature extraction, body models, and modeling methods.
  • Modeling methods are further classified into top-down vs. bottom-up and generative vs. discriminative approaches.
  • Motion-related methods are integrated, including motion features, models, and techniques for surveillance applications.

Main Results:

  • A structured review of human pose estimation techniques, including foundational and novel deep learning algorithms.
  • Categorization of methods into top-down/bottom-up and generative/discriminative paradigms.
  • Inclusion of motion-specific aspects relevant to video surveillance.

Conclusions:

  • This survey offers a unified perspective on human pose estimation from monocular images.
  • It identifies key modules, categorization strategies, and motion-related considerations.
  • The work serves as a valuable resource for researchers and practitioners in the field.