Wheelchair Behavior Recognition for Visualizing Sidewalk Accessibility by Deep Neural Networks
This research aims to visualize sidewalk accessibility information for people with mobility difficulties by identifying environmental factors that burden wheelchair users, offering an incremental improvement in data collection and analysis for accessibility mapping.
This paper proposes a method to estimate sidewalk accessibility from wheelchair behavior using a smartphone's triaxial accelerometer. It employs deep neural networks to classify road surface conditions, extract representations without manual annotations, and assess sidewalk barriers, demonstrating its ability to estimate and extract knowledge of accessibilities from wheelchair accelerations.
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.