News for hackers. Stuff that matters.
Re:Mapillary Now Able to Recognize and Label Objects in the ... by visarga on Tuesday September 27, 2016 @03:20PM (#12592263)
They apply CNNs to label pixels. The result could be used to improve other computer vision tasks. Applied to maps they think it would be good to measure vegetation density or the availability and sidewalks.

Hmm... okay.? I dunno what I expected.

Re:Mapillary Now Able to Recognize and Label Objects in the ... by aisofteng on Tuesday September 27, 2016 @08:51PM (#12594604)
>Here is a short list of areas where semantic segmentation is available: Graz, Paris, San Francisco, Hong Kong, Dar es Salaam, and Mexico City.

If the method is general, why only these areas?

Re:Mapillary Now Able to Recognize and Label Objects in the ... by milliams on Wednesday September 28, 2016 @04:49AM (#12596263)
I'm guessing limited computing power while refining the algorithms.
Re:Mapillary Now Able to Recognize and Label Objects in the ... by petern on Wednesday September 28, 2016 @08:14AM (#12597056)
It's because we need to upgrade and optimize some of the backend storage layout in order to cope with the data produced.

(I'm part of the Mapillary team)

Re:Mapillary Now Able to Recognize and Label Objects in the ... by aisofteng on Thursday September 29, 2016 @07:43PM (#12609653)
Thanks for elucidating - makes sense.