This amazing 'neural network' program describes what it sees on a trip through Amsterdam
The program can identify what it's looking at, live, through an ordinary laptop webcam
Your support helps us to tell the story
From reproductive rights to climate change to Big Tech, The Independent is on the ground when the story is developing. Whether it's investigating the financials of Elon Musk's pro-Trump PAC or producing our latest documentary, 'The A Word', which shines a light on the American women fighting for reproductive rights, we know how important it is to parse out the facts from the messaging.
At such a critical moment in US history, we need reporters on the ground. Your donation allows us to keep sending journalists to speak to both sides of the story.
The Independent is trusted by Americans across the entire political spectrum. And unlike many other quality news outlets, we choose not to lock Americans out of our reporting and analysis with paywalls. We believe quality journalism should be available to everyone, paid for by those who can afford it.
Your support makes all the difference.A digital 'neural network' has been put through its paces on the streets of Amsterdam - with a video showing how the program can identify people, vehicles and even different types of food by analysing live webcam images.
The NeuralTalk code was originally designed as a way to automatically caption images - but after some tweaking by American coder and artist Kyle McDonald, it was made to caption live video instead.
NeuralTalk and Walk from Kyle McDonald on Vimeo.
The software isn't 100 per cent accurate, but it's pretty impressive - seeing a man walking with a bag, the software produces the caption: 'Man walking down the street with a suitcase'.
It also manages to correctly identify boats, cars and bicycles (useful for when you're using it in Amsterdam).
The software really comes into its own when McDonald approaches a group of guys at a hot dog stand.
Looking at the laptop's screen, they're surprised to see the program identifying them correctly - as 'a man holding a hot dog in a bun'.
Pointing the webcam at the hot dog stand's counter, the program correctly says it is a 'refrigerator filled with lots of food and drinks'.
It's a cool thing in itself, but the technology could have important applications - such as helping the blind by automatically describing images and videos. But for now, the hot dog stand is a major achievement.
Join our commenting forum
Join thought-provoking conversations, follow other Independent readers and see their replies
Comments