Question

Identifying shelters/tents from satellite imagery

  • 10 November 2017
  • 1 reply
  • 1 view
mb_fdfa
Badge +1

As part of our role in providing humanitarian aid, we need to identify potentially thousands of shelters/tents in refugee camps with ghe aid of current satellite imagery (in the future possibly from drone imagery). It would be sufficient to identify their existence and capture a point feature - perimeter would be a bonus but not absolutely necessary at the moment.

Doing verification on automatically generated output would be much faster than the current options of manually digitising elements or field data capture.

Is there anyone who has experience in something comparable? I have virtually no experience with raster data, so thought I'd see if anyone in the FME Community has any inputs/thoughts on this.

Thanks in advance.

1 reply

redgeographics
Rank
Userlevel 5
Badge +25

If the tents are distinguishable by color from the surrounding area then you could filter out those pixels. I seem to recall an old tutorial by @dmitribagh where he filtered out the yellow roads from a Google Maps image but I can't seem to find that one.

Change detection could be useful too if you have a "before" image, see here.

If you have drone imagery with a z component (so a point cloud) you could potentially have an extra set of parameters to play with (elevation differences)

Reply


Community Stats

28,724
Posts
109,518
Replies
36,564
Members
Terms & ConditionsCookie settings
A product of
Safe Software respectfully acknowledges that we live, learn and work on the traditional and unceded territories of the Kwantlen, Katzie, and Semiahmoo First Nations.