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

Dynamic temporal partitioning enhanced transformer for pediatric viral load forecasting.

Frontiers in public health·2026
Same author

Solid-phase synthesis of sterically hindered peptides via ribosome-mimicking molecular reactors.

Nature protocols·2026
Same author

Oncolytic Herpes Simplex Virus for Glioblastoma: Molecular Engineering, Tumor Microenvironment Barriers, and Clinical Translation.

Current issues in molecular biology·2026
Same author

Heterogeneous domain adaptation survival analysis with partially observed outcomes via dictionary learning and distribution alignment.

Journal of biomedical informatics·2026
Same author

Clinical analysis of 8 cases of interstitial pregnancy after embryo transfer.

Medicine·2026
Same author

Molecular mechanism leading to human coronary atherosclerosis assessed by proteomic analysis and RNA sequences.

European heart journal·2026

Related Experiment Video

Updated: Jan 16, 2026

Localizing Function-specific Targets for Transcranial Magnetic Stimulation in the Absence of Navigation Equipment
09:30

Localizing Function-specific Targets for Transcranial Magnetic Stimulation in the Absence of Navigation Equipment

Published on: May 23, 2025

1.3K

A ST-ConvLSTM Network for 3D Human Keypoint Localization Using MmWave Radar.

Siyuan Wei1, Huadong Wang1, Yi Mo1

  • 1School of Electronic Science and Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, China.

Sensors (Basel, Switzerland)
|September 27, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces a novel ST-ConvLSTM network for precise 3D human keypoint estimation using millimeter-wave radar. The model demonstrates significant improvements in posture recognition accuracy, even in complex environments.

Keywords:
binocular camera annotationhuman keypoint localizationmillimeter wave radarradar point cloud datasetspatiotemporal features fusion

More Related Videos

Tracking Infiltration Front Depth Using Time-lapse Multi-offset Gathers Collected with Array Antenna Ground Penetrating Radar
07:14

Tracking Infiltration Front Depth Using Time-lapse Multi-offset Gathers Collected with Array Antenna Ground Penetrating Radar

Published on: May 1, 2018

8.2K
Neuronavigated Focalized Transcranial Direct Current Stimulation Administered During Functional Magnetic Resonance Imaging
09:33

Neuronavigated Focalized Transcranial Direct Current Stimulation Administered During Functional Magnetic Resonance Imaging

Published on: November 15, 2024

2.0K

Related Experiment Videos

Last Updated: Jan 16, 2026

Localizing Function-specific Targets for Transcranial Magnetic Stimulation in the Absence of Navigation Equipment
09:30

Localizing Function-specific Targets for Transcranial Magnetic Stimulation in the Absence of Navigation Equipment

Published on: May 23, 2025

1.3K
Tracking Infiltration Front Depth Using Time-lapse Multi-offset Gathers Collected with Array Antenna Ground Penetrating Radar
07:14

Tracking Infiltration Front Depth Using Time-lapse Multi-offset Gathers Collected with Array Antenna Ground Penetrating Radar

Published on: May 1, 2018

8.2K
Neuronavigated Focalized Transcranial Direct Current Stimulation Administered During Functional Magnetic Resonance Imaging
09:33

Neuronavigated Focalized Transcranial Direct Current Stimulation Administered During Functional Magnetic Resonance Imaging

Published on: November 15, 2024

2.0K

Area of Science:

  • Computer Vision
  • Machine Learning
  • Radar Signal Processing

Background:

  • Accurate human keypoint localization is crucial for various applications but challenging in complex environments.
  • Millimeter-wave (mmWave) radar offers robust sensing capabilities for human activity recognition.

Purpose of the Study:

  • To develop a deep learning model for 3D human keypoint estimation using mmWave radar point clouds.
  • To introduce a new dataset and annotation system for mmWave radar-based human pose estimation.

Main Methods:

  • A ST-ConvLSTM network was designed to process multi-channel radar image inputs derived from fused point clouds.
  • Parallel pathways within the network extract spatiotemporal features from sequential radar data.
  • A hybrid human motion annotation system (HMAS) was used to create the mmWave radar 3D human keypoint dataset (MRHKD).

Main Results:

  • The ST-ConvLSTM network achieved mean absolute errors (MAEs) of 0.1075 m (horizontal), 0.0633 m (vertical), and 0.1180 m (depth).
  • The model effectively captures temporal dependencies and spatial patterns in radar imagery for improved localization.
  • Experimental results show enhanced posture recognition accuracy in challenging conditions.

Conclusions:

  • The proposed ST-ConvLSTM network is effective for 3D human keypoint estimation using mmWave radar.
  • The developed dataset and annotation system facilitate further research in this domain.
  • The model shows significant potential for applications requiring robust human pose estimation.