Detect

Jakob

Geo.Hackmin Week, 01.-06. March 2021

  • BA & MA in Physics
  • PhD in Computational Neuroscience
  • now at Department of Physiology, Uni Bern; modeling of plasticity & learning in brains
  • so far: consumer of geo data
  • why this hackathon?
    • learn something
    • build something
    • open data is awesome!

twitter: @_jakobj

github: https://github.com/jakobj/

About me

Locate crosswalks in Bern

The goal

https://www.swisstopo.admin.ch/en/geodata/images/ortho/swissimage10.html

with the help of aerial photographs

(SWISSIMAGE 10cm)

The method

Supervised machine learning

-> need (lots of) examples!

(46.94926, 7.45258,  ...)

(46.94984, 7.45432, ...)

(46.94836, 7.45973, ...)

?

?

Gathering data

(Semi)manual annotation of full-scale images

-> extraction of ~1000 positive examples (50x50px)

(negative samples were generated automatically & reviewed)

Training the machine

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

Exporting the data (1/2)

positions of crosswalks within the photograph in pixels

+

coordinates of each photograph

=

(+ merging regions of interest)

Exporting the data (2/2)

~2500 ROIs imported into map.geo.admin.ch

Lessons learned

  • time management
    • pick a project that's realistic, a week is short!
    • making some choice may be better than making the best
  • applied machine learning
    • consider the difficulty of the classification task; you may not always need a model trained on ImageNet
    • poor performance is likely an issue of the data, rather than the model; check (and retrain) missclassifications!
    • data augmentation FTW!
  • geo data: coordinate transformations are a pain

Closing remarks

  • simple supervised-ML methods are suitable for detecting regions of interest in aerial photographs
  • (likely) every single design choice in this project can be improved
  • give it a try! code & some doc (MIT license): https://github.com/jakobj/xdetect

Thanks to everyone involved for making this possible!

It was awesome!

Computer symbol: PanierAvide (Creative Commons)

Student photo: CollegeDegrees360 (Creative Commons)

Credits

XDetect

By jakobj

XDetect

Detect pedestrian crossings (or other persistent structures) in the SWISSIMAGE 10 cm dataset.

  • 161
Loading comments...

More from jakobj