Real-time Object Detection using Deep Learning for helping People with Visual Impairments

Abstract

Object detection plays a crucial role in the development of Electronic Travel Aids (ETAs), capable to guide a person with visual impairments towards a target object in an unknown indoor environment. In such a scenario, the object detector runs on a mobile device (e.g. smartphone) and needs to be fast, accurate, and, most importantly, lightweight. Nowadays, Deep Neural Networks (DNN) have become the state-of-the-art solution for object detection tasks, with many works improving speed and accuracy by proposing new architectures or extending existing ones. A common strategy is to use deeper networks to get higher performance, but that leads to a higher computational cost which makes it impractical to integrate them on mobile devices with limited computational power. In this work we compare different object detectors to find a suitable candidate to be implemented on ETAs, focusing on lightweight models capable of working in real-time on mobile devices with a good accuracy. In particular, we select two models: SSD Lite with Mobilenet V2 and Tiny-DSOD. Both models have been tested on the popular OpenImage dataset and a new dataset, named L-CAS Office dataset, collected to further test models' performance and robustness in a real scenario inspired by the actual perception challenges of a user with visual impairments.

Intelligent Environments and Assistive Technologies For Assisting Visually Impairment People: A Systematic Literature Review

“…Terreran et al [81] suggested a system that uses an R-CNN based model for object recognition and a haptic device for real-time feedback. The core findings reveal high accuracy in object detection, making it notably useful for visually impaired individuals.…”

“…• IEEE: 41 articles ( 40.6% of total) • Springer: 15 articles ( 14.8% of total) • ACM: 10 articles ( 9.9% of total) Deep Learning 63 articles [90], [106], [51], [97], [109], [81], [54], [110], [55], [114] Fig. 8: Publications made per functionality and working principles per year…”