As Google makes the Street View cursor in After Maps,

Question

In Google Maps Street View, your cursor turns into a rectangular / oval shape when you hover over different parts of the scene. For example:

http://maps.google.com/?q=loc:+Maryland+Ave+at+e.+26th+st+Baltimore+MD+US&ie=UTF8&z=16&iwloc=A&layer=c&cbll=39.319313,-76.618426&panoid=6W2XgkHoGuf6_SQ_QVL6_S = 12,307.06., 0,3.16

When you move the cursor over a building, it “hugs” the walls. It is not as simple as after the intersection, because if you continue to move to the left, you can see a change in angle when it touches different faces of buildings.

Do they do some kind of image analysis to identify the faces of the buildings, or when they take a picture, do they do some kind of laser range finder and then combine it with the image?

Answer 1

They use laser range scanners. And according to Google Lat Long Blog :

We were able to accomplish this by making a compact representation of the building facade and road geometry for all panoramic views using laser point clouds and the differences between successive photographs.