Navigation assistive system for the blind using a portable depth sensor

Abstract

The lightweight and low-cost 3-dimensional depth sensors have gained much attention in the computer vision and robotics community. While its performance has been proven successful in the robotics community, these sensors have not been utilized successfully for many assistive devices. Leveraging on this gap, this paper presents the design, implementation, and preliminary evaluation of a haptic feedback system for the blind using 3-D depth sensors. The proposed portable system interprets the visual scene using the depth sensor, converts it into distance map, processes, and evaluates this information using a tablet computer. In addition, it provides haptic cues to the user through an array of vibration motors woven into the gloves. Throughout preliminary evaluation, this system has shown to successfully identify, track, and present closest objects, closest humans, multiple humans, and perform real-time distance measurements.