The multitemporal semantic change detection challenge track (Track MSD) of the 2021 IEEE GRSS Data Fusion Contest, organized by the Image Analysis and Data Fusion Technical Committee (IADF TC) of the IEEE Geoscience and Remote Sensing Society (GRSS) and Microsoft Research and Microsoft AI for Earth, aims to promote research in automatic land cover change detection and classification from multitemporal, multiresolution, and multispectral imagery.
The task of Track MSD is to create bitemporal high resolution land cover maps using only low-resolution and noisy land cover labels for training. Such a scenario is often encountered around the world, as the proliferation of new sensors with either high spatial resolution (submeter) or high temporal resolution (weekly or even daily) remains unmatched by equally rich label data. Instead, detecting change would have to rely on the analysis of a sequence of input images in an unsupervised manner or with aid of weak, noisy, and outdated labels.
Participants will receive a dataset of 2250 tiles covering the US state of Maryland. For each tile, the following layers of data will be provided:
Participants will need to infer high-resolution land cover maps that identify changes between the 2013 and 2017 high-resolution imagery for a subset of these 2250 tiles. The land cover change maps will be calculated between classes of a simplified scheme based on that of the noisy 30m low-resolution labels. The change maps will be scored on their accuracy in identifying areas with several particular kinds of change, described in the “Land cover change” section below.
The challenge is twofold: identifying what has changed between two high-resolution aerial images, and identifying what class of change it is based on weak labels.
For details about the 2021 IEEE GRSS Data Fusion Contest: http://www.grss-ieee.org/community/technical-committees/data-fusion/
The task of Track MSD is to create bitemporal high resolution land cover maps using only low-resolution and noisy land cover labels for training. Participants are required to submit land cover change maps in TIFF at a 1m GSD with the Byte (uint8) data type.
The contest consists of two phases:
Performance is assessed using the intersection-over-union (IoU) averaged over 8 types of changes.
The winners will have approximately one month (submission deadlline: April 23, 2021) to write their manuscript that will be included in the IGARSS 2021 proceedings. Manuscripts are 4-page IEEE-style formatted. Each manuscript describes the addressed problem, the proposed method, and the experimental results.
Participants of this challenge acknowledge that they have read and agree to the following Contest Terms and Conditions:
Start: Jan. 4, 2021, noon
Description: Development phase: tune your models and submit prediction results on validation data.
Start: March 8, 2021, noon
Description: Test phase: tune your models and submit prediction results on test data.
Start: March 12, 2021, noon
Description: Future-development phase: tune your models and submit prediction results on test data.
You must be logged in to participate in competitions.Sign In