Right now technology used in self-driving cars to allow it to detect objects and recognize obstacles involves radar, lasers, or cameras for the most part. However cars themselves are pretty expensive so imagine if you had a car outfitted with such technology, wouldn’t that result in cars being more expensive?That could potentially hamper the adoption of self-driving cars if and when they become commercially available. However the University of Cambridge has recently developed a new system called SegNet that could potentially help make self-driving cars cheaper to manufacture, with the savings passed down to customers.
So what is SegNet? According to its press release, “The first system, called SegNet, can take an image of a street scene it hasn’t seen before and classify it, sorting objects into 12 different categories — such as roads, street signs, pedestrians, buildings and cyclists – in real time. It can deal with light, shadow and night-time environments, and currently labels more than 90% of pixels correctly.”
However despite its potential, its researchers state there is still quite a long way to go. According to research leader Professor Roberto Cipolla, “It will take time before drivers can fully trust an autonomous car, but the more effective and accurate we can make these technologies, the closer we are to the widespread adoption of driverless cars and other types of autonomous robotics.”
In the meantime if you’d like to take SegNet for a spin, you can pop on over to its website, upload a photo of a street and watch it get analyzed on the spot.
Filed in . Read more about Self-Driving Cars.