StreetView coming to Italy

Google StreetView cars have been spotted in Italy, indicating that StreetView data will be coming soon.

The interesting part is that these don’t seem to be normal StreetView cars.  These come equipped with a handful of SICK laser scanners.  What for?  Educating Silicon does a good job of breaking down the question.  From their post:

So, what is Google doing with 3D laser data? The obvious application is 3D reconstruction for Google Earth. Their current efforts to do this involve user-generated 3D models from Sketchup. They have quite a lot of contributed models, but there is only so far you can get with an approach like that. With an automated solution, they could go for blanket 3D coverage. For an idea of what the final output might look like, have a look at the work of Frueh and Zakhor at Berkeley. They combined aerial and ground based laser with photo data to create full 3D city models. In am not sure Google will go to quite this length, but it certainly looks like they’re made a start on collecting the street-level data. Valleywag claims Google are hiring 300 drivers for their European data gathering efforts, so they will soon be swimming in laser data.

Maybe this is how Google will start mass-generating buildings for Google Earth to catch back up to Microsoft’s stockpile in Virtual Earth.

Comments

  1. 3D buildings from Street View could be a good idea, but what about all those bushes, trees, cars, people, bicycles, signs, pets, etc., getting in the way?

  2. I wonder about that myself. I don’t have enough knowledge about the laser systems to be able to give a qualified answer. If I find out how that works, I’ll be sure to post it.

  3. Good question – Getting rid of all the foreground stuff like cars and bushes is a real problem. In the example 3D model I linked, the system strips out all the foreground clutter, and then fills in the holes in the building façade by interpolation.
    No question that doing this kind of reconstruction on a large scale is a really hard problem. But it has been done for pretty large examples by the research group at Berkeley, and if anyone can make it work on the large scale, it’s Google.

  4. Mark – Thanks for the info. I’m sure it must be very hard for the system to determine things like:

    “Is that two light poles, or two columns sticking out from the building?”

    I agree with your last statement — if anyone can do it large scale, it’s Google.

  5. Have a look at an illustration of the process here:
    http://www-video.eecs.berkeley.edu/~frueh/3d/proc/index.html

    As you can see from the pics, it’s not perfect, but it does a reasonable job.

Trackbacks

  1. [...] on their post, it seems that the Manhattan refresh is the only new imagery for now — no Italy or Atlanta yet. Along with fresh, sharper imagery, you’ll now be able to look upward as [...]

Leave a Reply