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

The Cutting Edge: Interventional Strategies for Pain Management.

Physical medicine and rehabilitation clinics of North America·2026
Same author

Artificial Intelligence Across the Radiology Workflow: A Nine-Stage Narrative Review.

Diagnostics (Basel, Switzerland)·2026
Same author

An explainable multi-stage framework for brain tumor classification using hybrid feature fusion and EfficientNetB5 model.

Scientific reports·2026
Same author

A gated task-attentive multi-task network for unified retinal image analysis.

Scientific reports·2026
Same author

Characteristics and Outcomes of Patients With Malignancies Prior to Colorectal Cancer: A Propensity Score Matched Analysis.

Journal of gastrointestinal cancer·2026
Same author

Rodent Social Behavior Recognition Using a Global Context-Aware Vision Transformer Network.

AI (Basel, Switzerland)·2026

Related Experiment Video

Updated: Jan 9, 2026

Human Brown Adipose Tissue Depots Automatically Segmented by Positron Emission Tomography/Computed Tomography and Registered Magnetic Resonance Images
09:21

Human Brown Adipose Tissue Depots Automatically Segmented by Positron Emission Tomography/Computed Tomography and Registered Magnetic Resonance Images

Published on: February 18, 2015

12.6K

EfficientPoseSegNet: a weakly supervised, attention-guided framework for human pose estimation, anatomical

Muhammad Zaheer Sajid1, Muhammad Fareed Hamid2, Imran Qureshi3

  • 1Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, 65211, USA. ms2wt@missouri.edu.

Scientific Reports
|December 5, 2025
PubMed
Summary

This study introduces EfficientPoseSegNet, a deep learning model for enhanced airport security. It accurately detects concealed objects and analyzes human poses and body parts in millimeter-wave images.

Keywords:
Body part segmentationHuman pose estimationKeypoint estimationObject detection, anomaly detectionPose refinement, 2D pose correction

More Related Videos

Author Spotlight: Development of an Automated Camera-Based System for Real-Time Blast Overpressure Monitoring and TBI Risk Assessment in Military Training
06:20

Author Spotlight: Development of an Automated Camera-Based System for Real-Time Blast Overpressure Monitoring and TBI Risk Assessment in Military Training

Published on: December 6, 2024

3.2K
Bioelectric Analyses of an Osseointegrated Intelligent Implant Design System for Amputees
14:31

Bioelectric Analyses of an Osseointegrated Intelligent Implant Design System for Amputees

Published on: July 15, 2009

14.5K

Related Experiment Videos

Last Updated: Jan 9, 2026

Human Brown Adipose Tissue Depots Automatically Segmented by Positron Emission Tomography/Computed Tomography and Registered Magnetic Resonance Images
09:21

Human Brown Adipose Tissue Depots Automatically Segmented by Positron Emission Tomography/Computed Tomography and Registered Magnetic Resonance Images

Published on: February 18, 2015

12.6K
Author Spotlight: Development of an Automated Camera-Based System for Real-Time Blast Overpressure Monitoring and TBI Risk Assessment in Military Training
06:20

Author Spotlight: Development of an Automated Camera-Based System for Real-Time Blast Overpressure Monitoring and TBI Risk Assessment in Military Training

Published on: December 6, 2024

3.2K
Bioelectric Analyses of an Osseointegrated Intelligent Implant Design System for Amputees
14:31

Bioelectric Analyses of an Osseointegrated Intelligent Implant Design System for Amputees

Published on: July 15, 2009

14.5K

Area of Science:

  • Computer Vision and Machine Learning
  • Transportation Science and Logistics
  • Security and Surveillance Technologies

Background:

  • Automated detection of concealed objects, anatomical keypoints, and human body parts in millimeter-wave images is crucial for airport security.
  • Existing systems face challenges due to poor image quality, limited annotations, and privacy concerns.
  • Need for efficient, robust, and privacy-compliant solutions for real-time security screening.

Purpose of the Study:

  • To develop EfficientPoseSegNet, a hybrid deep learning framework for efficient annotation use in security screening images.
  • To enable accurate concealed object detection, human pose estimation, and body part segmentation.
  • To enhance the reliability and scalability of automated security screening systems.

Main Methods:

  • Utilized parallel EfficientNet and DenseNet backbones for multi-scale feature extraction from low-resolution scans.
  • Incorporated a Convolutional Block Attention Module (CBAM) to focus on critical anatomical areas and reduce noise.
  • Employed spatial heatmaps with soft-argmax for keypoint extraction, body segmentation into 17 regions, and Stochastic Weight Averaging (SWA) for robust training under weak supervision.

Main Results:

  • Achieved high accuracy in keypoint detection (99.79%), pose estimation (99%), and body segmentation (97% IoU).
  • Demonstrated strong performance in concealed object detection with an average anomaly detection AUC of 0.94.
  • EfficientPoseSegNet shows significant improvements in test loss and mean absolute error on the TSA Passenger Screening Dataset.

Conclusions:

  • EfficientPoseSegNet offers a scalable, privacy-compliant solution for real-time human pose estimation, body part segmentation, and concealed object detection.
  • The hybrid deep learning framework effectively addresses challenges in millimeter-wave image analysis for enhanced transportation safety.
  • This approach significantly contributes to the advancement of security screening technologies in fast-paced environments.