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

Allogeneic Hematopoietic Cell Transplant Following Standard of Care Brexucabtagene Autoleucel in Adults with B-Cell Acute Lymphoblastic Leukemia: Results from the Real-World Outcomes Collaborative of Chimeric Antigen Receptor T in Adult Acute Lymphoblastic Leukemia.

Transplantation and cellular therapy·2026
Same author

Thymic Composition Predicts Radiation Pneumonitis in Locally Advanced NSCLC.

Journal of thoracic oncology : official publication of the International Association for the Study of Lung Cancer·2026
Same author

AI-driven digital holographic microscopy for label-free quantitative cellular analysis: toward low-cost and field-deployable platforms.

Biomedical optics express·2026
Same author

Morphological investigation of astrocyte brain cells using quantitative phase imaging.

Biomedical optics express·2026
Same author

A Machine-Learning Assisted Genetic Risk Score Identifies Improved Weight Loss After Endoscopic Sleeve Gastroplasty.

Obesity surgery·2026
Same author

Security authentication and tracking of unmanned moving vehicles with optical ID tags.

Optics express·2026

Related Experiment Video

Updated: Dec 14, 2025

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision
08:15

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Published on: March 28, 2025

1.0K

Human gesture recognition under degraded environments using 3D-integral imaging and deep learning.

Gokul Krishnan, Rakesh Joshi, Timothy O'Connor

    Optics Express
    |July 17, 2020
    PubMed
    Summary

    This study introduces a novel 3D integral imaging and deep learning algorithm for robust human gesture recognition, even in challenging conditions like low light or occlusion. The new method significantly outperforms existing techniques, offering improved accuracy for human activity recognition.

    More Related Videos

    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

    2.0K
    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

    5.0K

    Related Experiment Videos

    Last Updated: Dec 14, 2025

    Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision
    08:15

    Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

    Published on: March 28, 2025

    1.0K
    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

    2.0K
    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

    5.0K

    Area of Science:

    • Computer Vision
    • Artificial Intelligence
    • Biomedical Imaging

    Background:

    • Human gesture recognition is crucial for human-computer interaction.
    • Degraded environmental conditions (occlusion, low illumination) pose significant challenges for existing recognition systems.
    • Three-dimensional (3D) imaging offers richer data compared to 2D, potentially improving recognition accuracy.

    Purpose of the Study:

    • To propose and evaluate a novel spatio-temporal human gesture recognition algorithm using 3D integral imaging and deep learning.
    • To enhance the robustness of human gesture recognition in degraded environments.
    • To demonstrate the superiority of the proposed 3D integral imaging approach over conventional 2D methods and existing algorithms.

    Main Methods:

    • Utilized 3D integral imaging to capture spatio-temporal data of human gestures.
    • Employed a deep learning architecture combining a Convolutional Neural Network (CNN) for spatial feature extraction and a Bi-directional Long Short-Term Memory (BiLSTM) network for temporal modeling.
    • Compared the proposed method against conventional 2D imaging, spatio-temporal interest points with support vector machines (STIP-SVMs), and distortion invariant non-linear correlation-based filters.

    Main Results:

    • The proposed 3D integral imaging and deep learning approach demonstrated significant improvements in human gesture recognition accuracy, particularly under degraded conditions.
    • 3D integral imaging provided superior performance compared to conventional 2D imaging systems.
    • The algorithm showed substantial gains over previously published methods, highlighting its effectiveness in challenging environments.

    Conclusions:

    • The developed algorithm offers a promising solution for reliable human gesture and activity recognition in adverse conditions.
    • Deep learning applied to 3D integral imaging data represents a powerful approach for overcoming limitations in current gesture recognition systems.
    • This work pioneers the use of deep learning with 3D integral imaging for human activity recognition in degraded environments.