Good Thinking

Prototype system enables the visually impaired to ‘see’ the world with sound

Prototype system enables the v...
Sight through sound - CASBliP prototype
Sight through sound - CASBliP prototype
View 3 Images
A research project aims to provide 'sight' for the visually impaired via acoustic maps
A research project aims to provide 'sight' for the visually impaired via acoustic maps
Sight through sound - CASBliP prototype
Sight through sound - CASBliP prototype
View gallery - 3 images

If you’re lucky enough to have perfect eye sight, it is incredibly difficult to imagine what the world is like for a visually impaired person. There have been some astounding breakthroughs in the development of new technologies to assist the blind which aim to replicate the function of the eye, but this project takes a totally different approach. The Cognitive Aid System for Blind People (CASBLiP) uses lasers and digital video images to create a three-dimensional acoustic map which, when relayed through headphones, enables users to "see" the world with sound.

Laser and digital video camera images will be used to analyze the distance of obstacles and help to predict the movement of people and motor vehicles as the user nears them. This spatial information will then be transformed and presented to the user via headphones as an "audible map". The signals received via headphones will guide and assist the user to negotiate and navigate the obstacles and dangers of the outside world. The user will also wear glasses with miniature video cameras mounted on them. These will provide the necessary video vision.

Once developed, this is how it will work - as you move around, the sounds received via headphones will alter and the stereo audio system will enable you to interpret sounds and then place them in accordance with their distance to you. For example, as you walk away from an object, the sound will decrease. Walk closer to an object and the sound will increase. If an object is on your right, you’ll hear it on your right and you will also be warned via audio tone to get out of the way if something is headed straight for you.

The CASBliP project has been three years in the making so far and has been made possible by funding from the European Union (EU). There are a number of universities and blind institutions involved in the consortium.

Researchers from the University of Bristol used algorithms and real-time image processing to identify common street objects and obstacles - such as people, trees or street furniture – to create a “depth map”, capable of calculating distances. This system is also capable of predicting movement.

Meanwhile, technology was being developed at the University of Laguna in Spain to make it possible to transform spatial information into three-dimensional acoustic maps. A gyroscopic sensor developed by the University of Marche in Italy, detects how the user moves their head. As the user moves position or changes their direction of their head, the relative position of sounds will also move. If the user turns toward a sound to their left, the sound will move left towards the sound picture.

Also, the University of Marche worked closely with the Cavazza Institute in Italy to include a GPS location system into the unit to help complement the other technologies. This may help to assist a visually impaired person by adding mapping services to the device, including the ability to add verbal directions to the required destination.

All the developed components will be put together to create a device that "sees" the world through hearing.

So far, two prototype devices mounted on a helmet have been developed. They have been tested in real world environments by participants from the German Federation of the Blind and Partially Sighted and the Francesco Cavazza Institute in Italy.

The first design (M1) uses a laser sensor that was initially developed by Siemens to detect passengers in cars. The system cannot be seen by others as it is mounted within glasses and uses infrared light. It is effective for users that are capable of recognizing familiar items such as trees or people from the sound information they receive.

A second version (M2) sees two digital video cameras added to either side of a helmet. This system can predict and detect the movement of objects.

“We know that the technology works,” says Guillermo Peris-Fajarnés, who coordinated the project from the Research Group on Graphic Technologies at the Universidad Politecnica de Valencia. “Our tests have been very successful and blind people have been able to navigate comfortably in controlled tests and even along a normal street.”

“There is still a lot of development work to do before this could go on the market, especially to prove that the system is 100% reliable,” Peris-Fajarnés notes. “You can't risk it going wrong while a user is crossing the road.”

If the funding for the project runs out, it is hoped that the consortium will complete this incredible work with funding from other sources on the way to enriching the lives of the huige number of people ( 20 million in America qalone suffering from some form of significant visual impairment.

CasBlip via: ICT Results.

View gallery - 3 images
No comments
There are no comments. Be the first!