Search research articles

Search research articles

Related Experiment Video

Updated: Oct 9, 2025

Home-Based Monitor for Gait and Activity Analysis

Home-Based Monitor for Gait and Activity Analysis

Published on: August 8, 2019

Evaluation of 2D-/3D-Feet-Detection Methods for Semi-Autonomous Powered Wheelchair Navigation.

Cristian Vilar Giménez¹, Silvia Krug^1,2, Faisal Z Qureshi^1,3

¹Department of Electronics Design, Mid Sweden University, Holmgatan 10, 851 70 Sundsvall, Sweden.

Journal of Imaging

|December 23, 2021

Summary

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

Enhancing Apple Cultivar Classification Using Multiview Images.

Journal of imaging·2024

Same author

A Deep CNN Transformer Hybrid Model for Skin Lesion Classification of Dermoscopic Images Using Focal Loss.

Diagnostics (Basel, Switzerland)·2023

Same author

A Study on the Correlation between Change in the Geometrical Dimension of a Free-Falling Molten Glass Gob and Its Viscosity.

Sensors (Basel, Switzerland)·2022

Same author

A Temporal Boosted YOLO-Based Model for Birds Detection around Wind Farms.

Journal of imaging·2021

Same author

Realworld 3D Object Recognition Using a 3D Extension of the HOG Descriptor and a Depth Camera.

Sensors (Basel, Switzerland)·2021

Same author

Multi-Camera Based Setup for Geometrical Measurement of Free-Falling Molten Glass Gob.

Sensors (Basel, Switzerland)·2021

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

Caregiver

Area of Science:

Robotics and Human-Computer Interaction
Computer Vision and Machine Learning

Background:

Powered wheelchairs improve mobility for individuals with special needs.
Advancements in powered wheelchairs focus on enhanced safety and control through sensors.
Autonomous navigation in powered wheelchairs presents significant development challenges.

Purpose of the Study:

To develop a contactless control system for powered wheelchairs using caregiver's position as a reference.
To compare the effectiveness of 3DHOG and YOLOv4-Tiny for caregiver recognition.
To investigate the feasibility of using monocular RGB cameras for caregiver-based wheelchair control.

Main Methods:

A custom dataset (Miun-Feet) was created for training and evaluating object recognition models.

Keywords:

3D object recognition 3DHOG Intel RealSense ModelNet40 YOLO YOLO-Tiny depth camera feature descriptor histogram of oriented gradients wheelchair

More Related Videos

Clinical-oriented Three-dimensional Gait Analysis Method for Evaluating Gait Disorder

Clinical-oriented Three-dimensional Gait Analysis Method for Evaluating Gait Disorder

Published on: March 4, 2018

3D Kinematic Gait Analysis for Preclinical Studies in Rodents

3D Kinematic Gait Analysis for Preclinical Studies in Rodents

Published on: August 3, 2019

Related Experiment Videos

Last Updated: Oct 9, 2025

Home-Based Monitor for Gait and Activity Analysis

Home-Based Monitor for Gait and Activity Analysis

Published on: August 8, 2019

Clinical-oriented Three-dimensional Gait Analysis Method for Evaluating Gait Disorder

Clinical-oriented Three-dimensional Gait Analysis Method for Evaluating Gait Disorder

Published on: March 4, 2018

3D Kinematic Gait Analysis for Preclinical Studies in Rodents

3D Kinematic Gait Analysis for Preclinical Studies in Rodents

Published on: August 3, 2019

Two real-time object recognition approaches were compared: 3DHOG and YOLOv4-Tiny.

A novel method was developed to calculate caregiver's distance and angle using only RGB data.

Main Results:

YOLOv4-Tiny significantly outperformed the 3DHOG descriptor in caregiver recognition accuracy.
Depth channel information did not improve recognition accuracy, suggesting RGB-only approaches are viable.
The proposed RGB-based method accurately computes caregiver's relative position to the powered wheelchair.

Conclusions:

Contactless control of powered wheelchairs using caregiver's feet location is feasible.
Monocular RGB cameras are sufficient for caregiver position detection, reducing system complexity and cost.
This research paves the way for more intuitive and safer powered wheelchair control systems.