DISHA: Low-Energy Sparse Transformer at Edge for Outdoor Navigation for the Visually Impaired Individuals

TL;DR

This paper introduces DISHA, a low-energy sparse transformer model for outdoor sidewalk detection to assist visually impaired individuals, achieving high accuracy and extended battery life on edge devices.

Contribution

The paper presents a novel pruning technique for transformers that enhances outdoor navigation accuracy while reducing energy consumption on edge devices.

Findings

Up to 32.49% improvement in detection accuracy.

Extended battery life by 1.4 hours.

Effective deployment on edge devices for real-time navigation.

Abstract

Assistive technology for visually impaired individuals is extremely useful to make them independent of another human being in performing day-to-day chores and instill confidence in them. One of the important aspects of assistive technology is outdoor navigation for visually impaired people. While there exist several techniques for outdoor navigation in the literature, they are mainly limited to obstacle detection. However, navigating a visually impaired person through the sidewalk (while the person is walking outside) is important too. Moreover, the assistive technology should ensure low-energy operation to extend the battery life of the device. Therefore, in this work, we propose an end-to-end technology deployed on an edge device to assist visually impaired people. Specifically, we propose a novel pruning technique for transformer algorithm which detects sidewalk. The pruning technique ensures low latency of execution and low energy consumption when the pruned transformer algorithm is deployed on the edge device. Extensive experimental evaluation shows that our proposed technology provides up to 32.49% improvement in accuracy and 1.4 hours of extension in battery life with respect to a baseline technique.