Wheelchair Behavior Recognition for Visualizing Sidewalk Accessibility by Deep Neural Networks

TL;DR

This paper presents a deep learning-based system that uses wheelchair acceleration data to recognize sidewalk accessibility features and barriers, aiding visualization for improved mobility support.

Contribution

It introduces a novel combination of supervised, weakly supervised, and self-supervised neural networks to assess sidewalk accessibility from wheelchair sensor data.

Findings

Accurately classifies road surface conditions using neural networks.

Effectively extracts knowledge of sidewalk barriers without manual labels.

Demonstrates potential for real-time accessibility visualization.

Abstract

This paper introduces our methodology to estimate sidewalk accessibilities from wheelchair behavior via a triaxial accelerometer in a smartphone installed under a wheelchair seat. Our method recognizes sidewalk accessibilities from environmental factors, e.g. gradient, curbs, and gaps, which influence wheelchair bodies and become a burden for people with mobility difficulties. This paper developed and evaluated a prototype system that visualizes sidewalk accessibility information by extracting knowledge from wheelchair acceleration using deep neural networks. Firstly, we created a supervised convolutional neural network model to classify road surface conditions using wheelchair acceleration data. Secondly, we applied a weakly supervised method to extract representations of road surface conditions without manual annotations. Finally, we developed a self-supervised variational autoencoder to assess sidewalk barriers for wheelchair users. The results show that the proposed method estimates sidewalk accessibilities from wheelchair accelerations and extracts knowledge of accessibilities by weakly supervised and self-supervised approaches.