For the first time since 2009, Google has revamped its Street View cameras. As of last month, the new and improved cameras got to work capturing the streets of the world in high-resolution. The images are soon to be translated into more detailed and colourful Street View images.
The new camera design is not just geared at upgrading the Street View experience, however. Google is also looking to analyse the images using artificial intelligence.
By feeding more detail into its image recognition algorithms, Google will be able to generate a deeper dataset for its search tool, enabling it to answer much more complicated queries.
The aim is for the company’s search algorithms to be able to process queries that assume knowledge about the appearance of locations.
News of the upgrade was first published by Wired, who discussed the ins and outs of the new tech with Jen Fitzpatrick, Vice President of Engineering and Project Management at Google, who also leads the maps division.
“People are coming to us every day with harder and deeper questions,” she told Wired. The aim, according to Fitzpatrick, is for the company’s search algorithms to be able to process queries that assume knowledge about the appearance of locations.
For instance, one might search something like: “What’s the name of the pink store next to the church on the corner?” In order to do this, Google needs “richer and deeper information,” said Fitzpatrick.
Another idea use of artificial intelligence that Google is pursuing is its potential to identify and read information like signs and place names. The algorithms could learn to recognise information displayed in shop windows such as methods of payment and opening hours.