twitter: @_jakobj
github: https://github.com/jakobj/
Locate crosswalks in Bern
https://www.swisstopo.admin.ch/en/geodata/images/ortho/swissimage10.html
with the help of aerial photographs
(SWISSIMAGE 10cm)
Supervised machine learning
-> need (lots of) examples!
(46.94926, 7.45258, ...)
(46.94984, 7.45432, ...)
(46.94836, 7.45973, ...)
?
?
(Semi)manual annotation of full-scale images
-> extraction of ~1000 positive examples (50x50px)
(negative samples were generated automatically & reviewed)
Small convolutional neural network
(2x [Conv2d + ReLU + MaxPool2d] + 1x FC)
Output: probability that input image patch contains crosswalk
~20k parameters, ~40min training time, ~150 loc
positions of crosswalks within the photograph in pixels
+
coordinates of each photograph
=
(+ merging regions of interest)
~2500 ROIs imported into map.geo.admin.ch
Thanks to everyone involved for making this possible!
It was awesome!
Computer symbol: PanierAvide (Creative Commons)
Student photo: CollegeDegrees360 (Creative Commons)