“There are a couple of steps. You acquire data through partners. You do a bunch of engineering on that data to get it into the right format and conflate it with other sources of data, and then you do a bunch of operations, which is what this tool is about, to hand massage the data. And out the other end pops something that is higher quality than the sum of its parts.” Michael Weiss-Malik (Google engineer)
Google Maps is a mapping service and database, accessible for free online and on mobile platforms. It offers an incredible range of data, ranging from satellite imagery of the entire planet, road and route planning information, local businesses locations, and a huge collection of “street-view” pictures over hundreds of cities around the world.
Google Street View cars have driven over five million miles in 46 countries. Beyond the direct utility these “human-level” images of cities have, Google is using powerful OCR algorithms (developed partially through Google Books) to extract text from signs and businesses and feeding this information back into its database.
Where does all of this information come from? The base layer (for the US) comes from TIGER data from the US Census Bureau. This is just the start- for one thing, many small details such as roads don’t exactly line up with the real world. Google employs hundreds of people to analyze imagery and make small corrections. In addition, Google often corrects errors reported in its maps from users within minutes.
Even more impressive is Google Map Maker, a bottom-up way to edit Google Maps. Anyone around the world can use this service to improve the places that they experience every day, making Google Maps a richer experience for everyone by adding landmarks and utilizing local knowledge.
Why does Google care about having the world’s most accurate and comprehensive maps? If Google’s mission is to organize and monetize all of the world’s information, it needs more than search spiders. It needs to move into the physical world, collect, organize, and make searchable the huge amount of data that the world contains. It needs to create an interface between the online and offline worlds.
One example of the ways the Google Maps database will revolutionize the world is Google’s self-driving car initiative. This project is being led by Sebastian Thrun, who was integral in the development of Street View. Google’s cars have completed over 480,000 driverless miles accident free. Google Maps will take a huge role when this service is commercialized: the cars need to know exactly where to drive if they will be useful.