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

Next-Generation models of Gallbladder Carcinoma: Linking biological insights to precision medicine.

Critical reviews in oncology/hematology·2025
Same author

[Rare differential diagnosis of an osteolytic lesion of the mandible in a young adult].

Pathologie (Heidelberg, Germany)·2024
Same author

Applications of Quantum Dots in Preventive Oncology.

Asian Pacific journal of cancer prevention : APJCP·2024
Same author

Antenatally diagnosed kidney tumor: Answers.

Pediatric nephrology (Berlin, Germany)·2020
Same author

Antenatally diagnosed renal tumor: Questions.

Pediatric nephrology (Berlin, Germany)·2020
Same author

Draft genome of Ompok bimaculatus (Pabda fish).

BMC research notes·2019

Related Experiment Video

Updated: Jul 19, 2025

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

3.8K

Multi-Camera-Based Human Activity Recognition for Human-Robot Collaboration in Construction.

Youjin Jang1, Inbae Jeong2, Moein Younesi Heravi1

  • 1Department of Civil, Construction and Environmental Engineering, North Dakota State University, Fargo, ND 58108, USA.

Sensors (Basel, Switzerland)
|August 12, 2023
PubMed
Summary

Multiple cameras improve human activity recognition for construction robots, enhancing safety and productivity in human-robot collaboration. This approach overcomes single-camera limitations for more reliable human behavior detection.

Keywords:
human activity recognitionhuman pose estimationlong short-term memorymultiple camerasparticle filter

More Related Videos

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment
06:49

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment

Published on: December 11, 2015

8.9K
Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery
05:12

Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery

Published on: August 12, 2021

2.1K

Related Experiment Videos

Last Updated: Jul 19, 2025

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

3.8K
Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment
06:49

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment

Published on: December 11, 2015

8.9K
Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery
05:12

Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery

Published on: August 12, 2021

2.1K

Area of Science:

  • Robotics
  • Computer Vision
  • Human-Robot Interaction

Background:

  • Increasing use of construction robots necessitates robust human activity recognition for safety and productivity.
  • Single or RGB-depth cameras face limitations like occlusion, poor lighting, and motion blur, hindering reliable human detection.
  • Accurate human behavior recognition is vital for preventing collisions in human-robot collaborative construction environments.

Purpose of the Study:

  • To propose and evaluate a multiple-camera approach for enhanced human activity recognition in construction settings.
  • To address the limitations of single-camera systems in recognizing human activities during human-robot collaboration.
  • To improve the accuracy and reliability of human behavior detection for safer construction operations.

Main Methods:

  • Utilized a particle filter to estimate 3D human pose by fusing 2D joint locations from multiple cameras.
  • Applied a long short-term memory network (LSTM) for recognizing ten distinct human activities in construction collaboration tasks.
  • Compared the performance of human activity recognition models using one, two, three, and four cameras.

Main Results:

  • The study demonstrated that employing multiple cameras significantly enhances human activity recognition performance.
  • Increased camera count led to more accurate and reliable identification and differentiation of various human activities.
  • The proposed multiple-camera system outperformed single-camera approaches in recognizing human behaviors.

Conclusions:

  • Multiple-camera systems offer a more robust solution for human activity recognition in human-robot collaboration within construction.
  • This approach contributes to advancing the safety and efficiency of construction sites through improved human-robot interaction.
  • The findings support the wider adoption of advanced sensing techniques for safer and more productive collaborative robotics.