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

Related Concept Videos

Force Classification

Force Classification

Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...

You might also read

Related Articles

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

Sort by

Same author

Speech enhancement for ambisonics input-output systems: Spatio-temporal reverberation shaping and a neural filtering framework.

The Journal of the Acoustical Society of America·2026

Same author

Gait Recognition via Enhanced Visual-Audio Ensemble Learning with Decision Support Methods.

Sensors (Basel, Switzerland)·2025

Same author

Exploring the causal associations between diet-derived circulating antioxidants and the risk of endometriosis: a Mendelian randomization study.

Frontiers in nutrition·2024

Same author

Tsallis Entropy-Based Complexity-IPE Casualty Plane: A Novel Method for Complex Time Series Analysis.

Entropy (Basel, Switzerland)·2024

Same author

Erratum to: circRNA circSnx12 confers Cisplatin chemoresistance to ovarian cancer by inhibiting ferroptosis through a miR-194-5p/SLC7A11 axis.

BMB reports·2024

Same author

Erratum to: circRNA circSnx12 confers Cisplatin chemoresistance to ovarian cancer by inhibiting ferroptosis through a miR-194-5p/SLC7A11 axis.

BMB reports·2023

Search research articles

Related Experiment Video

Updated: Jul 11, 2025

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

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

Published on: December 15, 2023

Indoor Human Action Recognition Based on Dual Kinect V2 and Improved Ensemble Learning Method.

Ruixiang Kan¹, Hongbing Qiu^1,2, Xin Liu³

¹School of Information and Communication, Guilin University of Electronic Technology, Guilin 541004, China.

Sensors (Basel, Switzerland)

|November 14, 2023

Summary

This summary is machine-generated.

This study introduces a novel dual Kinect V2 system for indoor human action recognition, overcoming self-occlusion and non-line-of-sight challenges. The system achieves a 30.25% improvement in action recognition accuracy.

Keywords:

Kinect V2 binocular system ensemble learning fuzzy c-means algorithm human action recognition random forest

More Related Videos

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

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

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

Published on: March 28, 2025

Related Experiment Videos

Last Updated: Jul 11, 2025

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

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

Published on: December 15, 2023

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

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

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

Published on: March 28, 2025

Area of Science:

Computer Vision
Human-Computer Interaction
Machine Learning

Background:

Indoor human action recognition is crucial for applications but faces challenges like self-occlusion and non-line-of-sight (NLOS) conditions.
Existing non-contact systems struggle with orientation constraints and identification limitations in complex environments.

Purpose of the Study:

To develop a novel system for robust indoor human action recognition, specifically addressing self-occlusion and NLOS scenarios.
To enhance the precision and reliability of human action recognition in challenging indoor environments.

Main Methods:

Utilized a dual Kinect V2 system with advanced Transmission Control Protocol (TCP).
Implemented a data-adaptive adjustment mechanism based on localization for self-occlusion mitigation.
Employed ensemble learning, including Chirp acoustic signal identification with fuzzy c-means-AdaBoost for NLOS positioning.
Integrated Random Forest and bat algorithm for intricate action identification.

Main Results:

The proposed system significantly mitigates self-occlusion in dynamic orientations.
Positioning accuracy in NLOS contexts is improved through optimized ensemble learning techniques.
Human action recognition precision is augmented by a substantial 30.25% compared to state-of-the-art methods.

Conclusions:

The novel dual Kinect V2 system effectively handles self-occlusion and NLOS situations in indoor human action recognition.
The advanced ensemble learning and adaptive mechanisms provide superior performance in complex scenarios.
The system demonstrates a significant leap in human action recognition accuracy, offering a promising solution for various applications.