[HOT] Building Detection using Machine Learning

Andrew Buck andrew.r.buck at gmail.com
Thu Dec 22 00:04:38 UTC 2016

I agree with what the others have said so far... this probably won't be
used to feed into the main database but could have other uses.

One place where it could be good is in very sparsely populated areas
like northern Africa, where there are huge areas of empty space with a
few isolated settlements.  In the past we used micro tasking to have
users quickly scan though and find village locations and then manually
mapped the buildings using the microtask results to find the villages to
map.  This worked very well and your algorithm looks robust enough to
find the majority of villages.  Also in that case false positives are no
problem at all as the mapper just won't map anything when they look
there and false negatives are not such a big deal (as long as you
identify at least one building in the village the mapper can map the
rest themselves anyway).

Lastly, this could be used to re-check already mapped villages to see if
they need to be revisited to map new buildings, etc.  You could scan an
area and for each village spit out a set of numbers of how many
buildings are in both datasets, how many are only in yours, and how many
are only in OSM.  Based on that we can prioritize areas to be re-looked
at by human mappers to update to the new imagery.

So all in all this is a very useful tool to have in our toolbox, but
just not for direct inclusion into the main database.


On 12/19/2016 08:17 AM, Philip Hunt wrote:
> Hi all,
> I attended my first Humanitarian OpenStreetMap Team (HOT) mapping event a few months ago and was interested to see how successful machine learning would be at detecting buildings in satellite images. The results look promising but I wanted to know if it could be useful to the community and if it’s worth pursuing further. I thought I would post a sample of the results and then quickly explain the process and issues.
> Results
> ———
> These are the results of a test I ran on project 2101 (Rongo, Kenya - PMI/USAID) on 1 November 2016. These images show the buildings detected by the algorithm on the first six unstarted tasks from the project. Potential buildings are marked with green rectangles:
> https://s3-eu-west-1.amazonaws.com/hot-osm-ml-test-data/2101_4.png
> https://s3-eu-west-1.amazonaws.com/hot-osm-ml-test-data/2101_5.png
> https://s3-eu-west-1.amazonaws.com/hot-osm-ml-test-data/2101_9.png
> https://s3-eu-west-1.amazonaws.com/hot-osm-ml-test-data/2101_12.png
> https://s3-eu-west-1.amazonaws.com/hot-osm-ml-test-data/2101_13.png
> https://s3-eu-west-1.amazonaws.com/hot-osm-ml-test-data/2101_14.png
> As you can see the initial results look promising - most of the buildings have been detected and the false positive rate is pretty low.
> Process
> ————
> I’ve been using the Viola–Jones machine learning algorithm, which requires training to know what is and isn’t a building. Once the algorithm is trained, it can be used to detect buildings in new images in a few seconds.
> The whole process looks like this:
> - Get the HOT project and task data using the HOT API
> - Get the satellite imagery of the area from OSM
> - Get the nearby existing buildings from the OSM API
> - Find the existing buildings in the satellite imagery and use these to train the algorithm
> - Run through each incomplete task in the HOT project and detect buildings
> - Output the results as OSM XML
> - Load the output into JOSM, validate and upload to OSM
> Issues
> ———
> I loaded the output of the algorithm into JOSM and completed tasks 1 and 2 of project 2101. However it still took a bit of work to make sure the data is good enough for OSM and I think an experienced mapper would have taken roughly the same amount of time starting from scratch.
> The main issue is the algorithm can’t rotate the detected rectangle to fit the building shape (as you can see from the example images above, none of the rectangles are rotated). I’ve tried using methods such as line detection to detect the building and rotate and crop the rectangle around the edges - this worked well some of the time and other times went horribly wrong. 
> The second issue is false positives. While the examples above we’re generally clean, sometimes the algorithm would think a field was a building. Because data uploaded to OSM needs to be accurate it can take some time checking each potential building in JOSM.
> Another potential issue could be training samples. When testing I trained a new algorithm for each project, using local existing building data from OSM as training data. The assumption here is that nearby buildings will look like buildings in the project area and that nearby building data is available and accurate.
> Next Steps
> —————
> The Viola–Jones objection detection research paper was first published in 2001 so the algorithm has been around for a while. Machine learning has improved since then and neural networks are showing a lot of promise - using these could increase the reliability and also allow the detected rectangle to be fixed around the edge of the building - meaning a lot less editing in JOSM. I’m also aware of similar projects, but I haven’t found anything that’s able to detect buildings or ready for use yet:
> https://github.com/trailbehind/DeepOSM (find misconfigured roads in OSM)
> https://github.com/patrick-dd/landsat-landstats (predicts population size)
> https://github.com/larsroemheld/OSM-HOT-ConvNet
> I'm not suggesting this could replace volunteers (since algorithms will never be completely accurate), but maybe this could help speed things up or be used to quickly estimate building locations over large areas.
> Please let me know your thoughts. Could this could be a useful tool for HOT or any other volunteer organisations and is it worth taking any further?
> Thanks,
> Philip Hunt 
> _______________________________________________
> HOT mailing list
> HOT at openstreetmap.org
> https://lists.openstreetmap.org/listinfo/hot

-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 901 bytes
Desc: OpenPGP digital signature
URL: <http://lists.openstreetmap.org/pipermail/hot/attachments/20161221/a2df106f/attachment.sig>

More information about the HOT mailing list