Pairwise Semantic Stereo Challenge is one of the challenges of the 2019 IEEE GRSS Data Fusion Contest, organized by the Image Analysis and Data Fusion Technical Committee. The contest aims to promote research in semantic 3D reconstruction and stereo using machine intelligence and deep learning applied to satellite images.
The objective is to predict both 3D geometric models and segmentation maps of semantic classes for urban scenes from pairs of epipolar rectified satellite images.
For details about the 2019 IEEE GRSS Data Fusion Contest: http://www.grss-ieee.org/community/technical-committees/data-fusion/
The problem is to predict semantic labels and stereo disparities. Each input is a pair of epipolar rectified satellite images. You are intended to submit 2D semantic segmentation and stereo disparities in TIFF with the same height and width as the input image.
The contest will consist of two phases:
Performance is assessed using the pixel-wise mean Intersection over Union (mIoU) combined with the percentage of erroneous pixels with a threshold of 3 pixels for disparity values. We call this metric mIoU-3. The evaluation code is available at https://github.com/pubgeo/dfc2019.
The winners will have approximately one month (submission deadlline: April 26, 2019) to write their manuscript that will be included in the IGARSS 2019 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:
@InProceedings{US3D,
author = {Bosch, Marc and Foster, Kevin and Christie, Gordon and Wang, Sean and Hager, Gregory D and Brown, Myron},
title = {Semantic Stereo for Incidental Satellite Images},
booktitle = {The IEEE Winter Conference on Applications of Computer Vision},
month = {January},
year = {2019}
}
@Article{IADF_GRSM_201903,
author = {Saux, Bertrand Le and Yokoya, Naoto and Hänsch, Ronny and Brown, Myron and Hager, Greg},
title = {2019 IEEE GRSS Data Fusion Contest: Large-Scale Semantic 3D Reconstruction [Technical Committees]},
booktitle = {IEEE Geoscience and Remote Sensing Magazine},
month = {March},
year = {2019}
}
Start: Nov. 26, 2018, midnight
Description: Development phase: tune your models and submit prediction results on validation data.
Start: March 7, 2019, midnight
Description: Final phase: tune your models and submit prediction results on test data.
Start: March 23, 2019, midnight
Description: Future-development phase: tune your models and submit prediction results on test data.
Never
You must be logged in to participate in competitions.
Sign In# | Username | Score |
---|---|---|
1 | raoxi36 | 0.7726 |
2 | JiKun63 | 0.7373 |
3 | sghuffar23 | 0.7365 |