Machine learning classification method for wheelchair detection using bag-of-visual-words technique.
Purpose: The primary goal of this study is to enhance safety and accessibility for individuals using wheelchairs by enabling automatic wheelchair detection through a visual surveillance system. This contributes to the development of smart healthcare systems that facilitate autonomous navigation and...
| Published in: | Disability & Rehabilitation: Assistive Technology Vol. 20; no. 6; pp. 1781 - 1792 |
|---|---|
| Main Authors: | , , , , |
| Format: | equations & formulas pictorial research tables/charts Journal Article |
| Published: |
Taylor & Francis Ltd
Aug2025
|
| Online Access: | View this record in EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=187408892&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 187408892 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 17483107 1X04 jtl: Disability & Rehabilitation: Assistive Technology issn: 17483107 maglogo: Y pubinfo: dt: Aug2025 vid: 20 iid: 6 pid: 377 pub: Taylor & Francis Ltd place: Philadelphia, Pennsylvania artinfo: ui: 187408892 183619494 187408892 187408892 10.1080/17483107.2025.2476105 187408892 ppf: 1781 ppct: 11 formats: fmt: – @attributes: type: T – @attributes: type: P tig: atl: Machine learning classification method for wheelchair detection using bag-of-visual-words technique. aug: au: Jalab, Hamid A. Al-Shamayleh, Ahmad Sami Abualhaj, Mosleh M. Shambour, Qusai Y. Omer, Herman Khalid affil: Information and Communication Technology Research Group, Scientific Research Center, Al-Ayen University, Thi Qar, Iraq sug: subj: Persons with Disabilities Wheelchairs Machine Learning Patient Safety Quality Improvement Health Services Accessibility Detection Algorithms Patient Navigation Human Image Processing, Computer Assisted Cluster Analysis Descriptive Statistics Motion Capture ROC Curve Logistic Regression Neural Networks (Computer) Comparative Studies ab: Purpose: The primary goal of this study is to enhance safety and accessibility for individuals using wheelchairs by enabling automatic wheelchair detection through a visual surveillance system. This contributes to the development of smart healthcare systems that facilitate autonomous navigation and improve mobility support. Materials and Methods: A novel machine learning model based on the bag-of-visual-words (BoVWs) technique was developed for wheelchair detection. The approach involves key feature extraction, visual vocabulary construction, and histogram-based image representation. A support vector machine (SVM) classifier was employed to classify images based on these features after converting them into histograms of visual words. The model was evaluated using a publicly available image dataset. Results and Conclusions: The proposed method achieved an accuracy of 98.85%, demonstrating its effectiveness in identifying wheelchairs in images. These findings highlight the potential of object detection techniques in recognizing mobility aids, contributing to improved accessibility and safety in rehabilitation and assistive technology applications. IMPLICATIONS FOR REHABILITATION: This study investigates an automated method for identifying wheelchair users in images using the bag-of-visual-words (BoVWs) technique. Previous detection algorithms often struggle under adverse conditions such as low lighting, poor weather or occlusions. Development of automated method using computer vision technique to identify wheelchair users in images using classifiers has the potential to improve accessibility and the quality of life for individuals with disabilities. The proposed method categorises individuals as either wheelchair users or pedestrians. The results show improvements in the detection which can effectively identify mobility aids in images. pubtype: Academic Journal doctype: equations & formulas pictorial research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|