An effective navigation system would improve the mobility of millions of blind people all over the world. A new “eye” developed by scientists in Japan will allow blind people to cross busy roads in total safety for the first time. The “electronic eye”, which would be mounted on a pair of glasses, will be capable of detecting the existence and location of a pedestrian crossing, and at the same time measure the width of the road to the nearest step and detect the colour of the traffic lights. This research appears today (19th November) in the journal Measurement Science and Technology published by the UK's Institute of Physics.

Tadayoshi Shioyama and Mohammad Uddin, from the Kyoto Institute of Technology in Japan, have developed a system that is able to detect the existence of a pedestrian crossing in front of a blind person using a single camera. When combined with two other techniques the authors have produced, for measuring the width of the road and the colour of traffic lights, a single camera can now give the blind all the information they need to cross a road in safety.

Although some crossings make a sound when it is safe to cross, many do not. This issue has been tackled in the past. Adaptations have, for example, been made to the most common travel aid used by blind people, the white cane. There are some canes with added functions which use lasers or ultrasound to detect more distant obstacles. One such is the Talking Cane from Sten Lšfving Optical Sensors in Sweden. But this technology can’t give information about the location of a crossing, width of the road or the colour of the traffic lights.

Professor Shioyama said: “The camera would be mounted at eye level, and be connected to a tiny computer. It will relay information using a voice speech system and give vocal commands and information through a small speaker placed near the ear”.

The device developed at Kyoto is the final product of a research programme that aimed to give blind people all the navigation information they needed to cross a road from a single small camera. Last year, the authors announced that they had designed a computer-aided camera that could measure the length of a crossing to within one step length - and simultaneously detect the colour of the traffic lights. Crucially, it couldn’t tell you where the crossing actually was until now.

Using images from a single camera, the device has a simple structure: unlike sophisticated stereo camera systems it does not need camera calibration. (The information is obtained using a 'camera coordinate system,' so separate images do not need to be taken to calibrate the device). The length of a pedestrian crossing is measured by projective geometry: the camera makes an image of the white lines painted on the road, and then the actual distances are determined using the properties of geometric shapes as seen in the image. Experiments carried out by Shioyama and his colleagues showed that the crossing length could be measured to within an error of only 5 per cent of the full length - which is less than one step.

Shioyama and Uddin have now made a breakthrough in detecting the location of crossings in the first place and added this to their original camera. To do this they used a calculation called the “projective invariant” which takes the distance between the white lines (called the band width) and a set of linear points on the edges of the white lines, to give an accurate way of detecting what is or isn’t a crossing in a given image.

They used this technique to analyse 196 images and it proved successful in detecting whether there was a crossing present in 194 of them. In the two images where the system made a mistake, it said there wasn’t a crossing where there really was one.

Katherine Phipps, Accessible Environments spokesperson at the Royal National Institute of the Blind said: "Mobility is a serious issue for blind and partially sighted people and new tools like this that may help people with sight problems get around safely are always welcome”.

PLEASE MENTION Measurement Science and Technology AS THE SOURCE OF THIS ARTICLE, PUBLISHED BY THE INSTITUTE OF PHYSICS. IF PUBLISHING ONLINE PLEASE CARRY A HYPERLINK TO www.iop.org/journals/mst

Useful Link:
Royal National Institute for the Blind (RNIB)
www.rnib.org.uk

The paper ‘Detection of pedestrian crossings with projective invariants from image data’ by T. Shioyama and M. S. Uddin will be published online on Friday 19th November 2004 in Measurement Science and Technology (www.iop.org/journals/mst) Volume 15, Issue 12, pp 2400-2405. The paper can be downloaded free of charge from 19th November from http://stacks.iop.org/MST/15/2400

Professor T Shioyama, Kyoto Institute of Technology, Tel: 0081 (0)75 724 7355. If telephoning, note Japan is 9 (nine) hours ahead of GMT.

The Institute of Physics is a leading international professional body and learned society with over 37,000 members, which promotes the advancement and dissemination of a knowledge of and education in the science of physics, pure and applied. It has a world-wide membership and is a major international player in:
- scientific publishing and electronic dissemination of physics;
- setting professional standards for physicists and awarding professional qualifications;
- promoting physics through scientific conferences, education and science policy advice.

The Institute is a member of the Science Council, and a nominated body of the Engineering Council. The Institute works in collaboration with national physical societies and plays an important role in transnational societies such as the European Physical Society and represents British and Irish physicists in international organisations. In Great Britain and Ireland the Institute is active in providing support for physicists in all professions and careers, encouraging physics research and its applications, providing support for physics in schools, colleges and universities, influencing government and informing public debate.

Reference URL
http://www.iop.org/journals/mst