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

Emotion-Aware Contextual Modelling for Robust Driver Fatigue Detection.

Sensors (Basel, Switzerland)·2026
Same author

Evaluation of Water Status and Thermal Characteristics of Dried Carrot Half-Slices in Correlation with Physicochemical and Sensory Properties.

Molecules (Basel, Switzerland)·2026
Same author

Biomaterial physicochemical properties govern immune activation and bone regeneration: a titanium-focused design-oriented osteoimmunological framework.

Frontiers in immunology·2026
Same author

A Redox Amplification Interface Linking Mitochondrial Dysfunction, Immune-Derived Oxidants, and Biomaterial Electrochemistry in Chronic Inflammation.

International journal of molecular sciences·2026
Same author

Catalytic Enantioselective Elimination of Cyclobutanols.

Journal of the American Chemical Society·2026
Same author

Real-world utility of platelet count, hemoglobin, and iron levels as predictors of clinical response to vedolizumab in patients with ulcerative colitis: a retrospective, single-center study in Poland.

BMC gastroenterology·2026

Related Experiment Video

Updated: Aug 5, 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

677

Using Gesture Recognition for AGV Control: Preliminary Research.

Sebastian Budzan1, Roman Wyżgolik1, Marek Kciuk2

  • 1Department of Measurements and Control Systems, Silesian University of Technology, Akademicka 10A, 44-100 Gliwice, Poland.

Sensors (Basel, Switzerland)
|March 30, 2023
PubMed
Summary

This study explores 2D hand gesture recognition (HGR) for controlling automated guided vehicles (AGVs) in real-world conditions. RGB images and 3D imaging show promise for improved AGV control via gestures.

Keywords:
HMIautomatic guided vehiclegesture recognitionneural networks

More Related Videos

Author Spotlight: Deciphering the Cognitive and Neural Mechanisms of Gesture in Communication
07:18

Author Spotlight: Deciphering the Cognitive and Neural Mechanisms of Gesture in Communication

Published on: January 26, 2024

934
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

1.7K

Related Experiment Videos

Last Updated: Aug 5, 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

677
Author Spotlight: Deciphering the Cognitive and Neural Mechanisms of Gesture in Communication
07:18

Author Spotlight: Deciphering the Cognitive and Neural Mechanisms of Gesture in Communication

Published on: January 26, 2024

934
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

1.7K

Area of Science:

  • Computer Vision
  • Robotics
  • Human-Computer Interaction

Background:

  • Automated Guided Vehicles (AGVs) require intuitive control methods for complex industrial environments.
  • Real-world conditions like variable lighting and backgrounds pose challenges for existing 2D Hand Gesture Recognition (HGR) systems.
  • Developing robust HGR for AGV control necessitates specialized image databases and adaptable algorithms.

Purpose of the Study:

  • To investigate the efficacy of 2D Hand Gesture Recognition (HGR) for controlling Automated Guided Vehicles (AGVs).
  • To address challenges posed by complex backgrounds, changing lighting, and varying operator distances in real-world AGV operation.
  • To evaluate and compare various HGR algorithms, including classic methods, transfer-learned deep learning models (ResNet50, MobileNetV2), and a novel CNN.

Main Methods:

  • Creation of a dedicated 2D image database for HGR research under realistic conditions.
  • Implementation and testing of classic HGR algorithms.
  • Retraining of ResNet50 and MobileNetV2 models using transfer learning.
  • Development and evaluation of a novel Convolutional Neural Network (CNN) for HGR.
  • Utilizing Adaptive Vision Studio (AVS) / Zebra Aurora Vision and Python for algorithm prototyping and implementation.
  • Preliminary investigation into 3D HGR techniques.

Main Results:

  • RGB images yielded superior results compared to grayscale images for HGR in the AGV context.
  • Transfer learning approaches with ResNet50 and MobileNetV2 demonstrated effectiveness.
  • The proposed simple and effective CNN achieved competitive performance.
  • 3D imaging and depth map utilization show significant potential for enhanced HGR accuracy.

Conclusions:

  • 2D HGR, particularly using RGB images, is a viable method for AGV control.
  • Deep learning models, especially when retrained with transfer learning, offer robust solutions.
  • Future advancements in 3D HGR and depth sensing are expected to further improve AGV interaction and control.