University of Wollongong
Browse

Substitute three-dimensional perception using depth and colour sensors

Download (1.49 MB)
conference contribution
posted on 2024-11-16, 07:51 authored by Simon Meers, Koren Ward
The development of sensor-actuator systems that can provide the user with perception of the environment without any use of the eyes is a difficult task. Firstly, the sensors must work effectively under differing conditions. Secondly, the actuators (or auditory feedback) must present the environmental information to the user in a manner that is easy to understand. Thirdly, the whole system needs to be compact, efficient and robust to be practical for a blind person to use. This paper firstly reviews current research in the area of substitute vision systems and discusses their limitations. We then provide details of the substitute vision system that we have developed that is not only aimed at overcoming many of the limitations of existing substitute vision systems, but is also intended to provide the user with more comprehensive perception of the environment. This is achieved by using a combination of range and colour sensors and by delivering the environmental information to the user via electro-tactile feedback in a form that is easy for the user to understand. We provide details of the development of our Electro Neural-Vision System (ENVS) as well as the results we have achieved with various range and colour sensors.

Funding

Gaze Tracking Haptic User Interface for the Blind

Australian Research Council

Find out more...

History

Citation

This conference paper was originally published as Meers, S and Ward, K, Substitute three-dimensional perception using depth and colour sensors, in Proceedings of the 2007 Australasian Conference on Robotics and Automation, December 2007, Brisbane.

Parent title

Proceedings of the 2007 Australasian Conference on Robotics and Automation, ACRA 2007

Language

English

RIS ID

25555

Usage metrics

    Categories

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC