Developing Smart Street Lights That Switch On As Cars Pass By
Jakarta is one of the biggest cities in the world. With 10 million inhabitants, it is the most populous in south east Asia and the 10th biggest on the planet.
Lighting such a city at night is an expensive business. Jakarta has over 200,000 street lights, which cost the equivalent of about $17 million dollars to run in 2007. The city has plans to double the number of street lights but would obviously like to minimise costs.
So Suprijadi, Thomas Muliawan and Sparisoma Viridi at the Institut Teknologi Bandung in Indonesia have come up with a novel plan. Their idea is to switch on street lights only when passing vehicles need them. And they’ve set up a model to test the idea.
The prototype is very simple. It consists of a toy car track monitored from above by a video camera. When the camera spots a toy car, it switches on lights by the side of the track.
In tests, the smart street lighting successfully recognised a passing car 91 per cent of the time at speeds of up to 0.91 m/s. (However, this drops to 77 per cent as the speed rises to 1.32 m/s).
This is clearly just a first step. It ought to be possible to recognise vehicles with much greater accuracy than this. Vehicle sensing technology is standard for some kinds of traffic lights. And some number plate recognition systems claim success rates of 99 per cent or higher.
The Indonesia team will be aware of the need to improve their system and to carry out other more stringent tests. Not least of these will be determining how well such a system can work in the various types of weather it is likely to experience.
Then there is the question of road safety. These guys will need to know how this kind of system influences driver behaviour, whether it can cope with motorcyclists and cyclists and how it will affect pedestrians and local residents.
Finally, they will need a cost-benefit analysis to determine how much the cost of producing and deploying this system will actually save.
But these are standard hurdles for any new driving technology. It may be that a partnership with an international organisation would help. After all, there are plenty of cities elsewhere in the world that are looking for innovative ways to reduce energy consumption.
Anybody interested in helping out?
Ref: arxiv.org/abs/1107.0845: Automatic Road Lighting System (ARLS) Model Based on Image Processing of Captured Video of Vehicle Toy Motion
Geoffrey Hinton tells us why he’s now scared of the tech he helped build
“I have suddenly switched my views on whether these things are going to be more intelligent than us.”
ChatGPT is going to change education, not destroy it
The narrative around cheating students doesn’t tell the whole story. Meet the teachers who think generative AI could actually make learning better.
Meet the people who use Notion to plan their whole lives
The workplace tool’s appeal extends far beyond organizing work projects. Many users find it’s just as useful for managing their free time.
Learning to code isn’t enough
Historically, learn-to-code efforts have provided opportunities for the few, but new efforts are aiming to be inclusive.
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.