Overview

Competition timeline

Important dates

From To / On Title Tasks
2020-11-18 Train and validation sets available all
2020-11-18 2021-04-05 Training phase all
2021-03-31 Registration deadline for competition participants all
2021-04-05 Test datasets available 1
2021-04-05 2021-04-09 Test phase 1
2021-04-09 Submission deadline for results 1
2021-04-12 Test datasets available 2&3
2021-04-12 2021-04-16 Test phase 2&3
2021-04-16 Submission deadline for results 2&3
2021-04-12 2021-04-23 Write short method description all
2021-04-23 Method descriptions due all
2021-07-01 Full data disclosure: round truth for test set, participant results all

How to register?

Please check the Registration page.

How to download dataset and evaluation tools?

  • The train and validation sets for all tasks are available under the Downloads page.
  • Evaluation tools will be open sourced soon so participant can check their results themselves.
  • Test sets for all tasks will be released at the start of the test phase.
  • All competition material (full dataset, participant results, evaluation tools) will be released publicly at the end of the competition.

About the competition

This competition consists in solving several challenges which arise during the digitization of historical maps. We are particularly interested in a large map series consisting in many Paris atlases over half a century (1860's-1940's). For each year, a set of approximately 20 sheets forms a tiled view of the city. Such maps are highly detailed and very accurate even in modern standards. The graphical nature of the content is visible in the full map sheet illustrated below.

A sample map sheet A sample map sheet (link to larger version)

This material provides a very valuable resource for historians and a rich body of scientific challenges for the document analysis and recognition (DAR) community: map-related challenges (overlapping of many information layers) and document-related ones (document preservation).

Excerpt showing map-related challenges Excerpt showing map-related challenges

Excerpt showing document-related challenges Excerpt showing document-related challenges

We expect this competition to provide solutions for three levels of scientific problems:

These tasks are necessary step during the digitization of historical maps, ie when gradually turning a raster image into a set of vector geometries projected onto a particular geographical coordinate reference system. Automatic approaches with good generalization power will provide an enormous gain for the Geographical Information Systems (GIS) communities looking for solutions when digitizing old maps, and create a great potential for many historical studies.