Machine learning classification method for wheelchair detection using bag-of-visual-words technique.

Area of Science:

• Computer Vision
• Machine Learning
• Rehabilitation Engineering

Background:

• Wheelchair users require enhanced safety and accessibility in smart healthcare environments.
• Autonomous navigation and mobility support systems can significantly benefit from accurate wheelchair detection.

Purpose of the Study:

• To develop an automatic wheelchair detection system using visual surveillance.
• To improve safety and accessibility for wheelchair users through enhanced mobility support.

Main Methods:

• A novel machine learning model utilizing the bag-of-visual-words (BoVWs) technique was developed.
• Key feature extraction, visual vocabulary construction, and histogram-based image representation were employed.
• A support vector machine (SVM) classifier was used for image classification.

Main Results:

• The proposed method achieved a high accuracy of 98.85% in wheelchair detection.
• The model demonstrated effectiveness in identifying wheelchairs within images.

Conclusions:

• Object detection techniques show significant potential for recognizing mobility aids.
• This technology can contribute to improved accessibility and safety in assistive technology applications.