2016 IEEE GRSS Data Fusion Contest:
Very High Temporal Resolution from Space
The Contest: Goals and Organization
The 2016 IEEE GRSS Data Fusion Contest, organized by the Image Analysis and Data Fusion Technical Committee, aims at promoting progress on fusion and analysis methodologies for multisource remote sensing data.
New multi-source, multi-temporal data including Very High Resolution (VHR) multi-temporal imagery and video from space are released this year. Submissions to the contest are scientific papers presenting the research work done on these data. The best ones will be included in the Technical Program of IGARSS 2016, presented in an oral Invited Session, and published in the IGARSS 2016 Proceedings.
The following challenging data sources are released to the community. First, VHR images (DEIMOS-2 standard products) acquired at two different dates, before and after orthorectification:
- Panchromatic data at 1 m spatial resolution point spacing
- Multispectral data at 4 m spatial resolution point spacing
Second, a video from an in-orbit camera:
- High-Definition Video acquired from the International Space Station (ISS), at 1-m spatial resolution
The data cover an urban and harbor area in Vancouver, Canada, and were acquired and provided for the Contest by Deimos Imaging and Urthecast.
Participants to the Contest are requested to submit 4-page original manuscripts using these data. The topic of each manuscript is totally open in the domain of extremely high resolution and multisource image interpretation. Possible topics include (but are not restricted to): registration (image to image, video to image), change detection, multi-temporal analysis, object detection and tracking (buildings, cars, vessels), image classification (multisensor or multiresolution).
Submission deadline for both tracks is April 29, 2016.
Each manuscript will be evaluated and ranked by an Award Committee on the basis of its novelty, scientific contribution, methodological approach, experimental validation, and clarity of explanation.
The imaging data were acquired on March, 31, and May, 30, 2015, over Vancouver, Canada (49°15’N 123°6’W), from the DEIMOS-2 satellite. DEIMOS-2 operates from a Sun-synchronous orbit at a mean altitude of 620km. The spacecraft design is based on an agile platform for fast and precise off-nadir imaging (up to +/-30° over nominal scenarios and up to +/-45° in emergency cases), and carries a push-broom very high resolution camera with 5 spectral channels (1 panchromatic, 4 multispectral with red, green, blue and NIR bands).
For each date, four images are provided: panchromatic images at 1 m resolution and multispectral product (R, G, B, NIR) at 4 m resolution, both at levels 1B (a calibrated and radiometrically corrected product, not resampled; with the geometric information contained in a RPC separated file) and 1C (a calibrated and radiometrically corrected product, manually orthorectified and resampled to a map grid; the geometric information is contained in the GeoTIFF tags.) Level 1C images cover exactly the same ground area for both dates.
The full colour, UHD video was acquired over Vancouver on July, 2nd, 2015. The High-Resolution camera, Iris, is installed on the Zvezda module of the International Space Station (ISS). Iris uses a CMOS detector to capture RGB videos with a Ground Sample Distance as fine as 1-meter, at 3 frames per second. Iris videos use image frames that have been fully ortho-rectified and resampled to 1-meter. Frame format is 3840×2160 pixels and cover approximately 3.8km × 2.1km.
Results, Awards, and Prizes
- The authors of the 4 best ranking manuscripts will:
- Be awarded IEEE Certificates of Recognition. The award ceremony will take place during the Technical Committees and Chapter Chairs Dinner at IGARSS 2016, Beijing, China
- Present their manuscripts in an oral Invited Session dedicated to the Contest at IGARSS 2016
- Publish their manuscripts in the Proceedings of IGARSS 2016
- The first and second ranked teams will co-author a journal paper (in a limit of 3 co-authors per submission), which will summarize the outcome of the Contest and will be submitted to IEEE JSTARS. To maximize impact and promote the potential of current multisource remote sensing technologies, the open-access option will be used for this journal submission.
- The authors of the winning manuscript (1st ranking) will receive as a prize an NVIDIA GPU graphics card.
The costs for open-access publication, for the winners participations to the Technical Committees and Chapter Chairs Dinner at IGARSS 2016 will be supported by the GRSS. The winner team prize is kindly sponsored by the IGARSS 2016 team.
- Jon A. Benediktsson, University of Iceland
- Sven Cowan, UrtheCast, Canada
- Jenny Q. Du, Mississippi State University, MS
- Roberto Fabrizi, Deimos Imaging, Spain
- Paolo Gamba, University of Pavia, Italy
- Bertrand Le Saux, ONERA, France
- Gabriele Moser, University of Genoa, Italy
- Fabio Pacifici, DigitalGlobe Inc., CO
- Devis Tuia, University of Zurich, Switzerland
The Rules of the Game
- Data can be requested by registering for the Contest. Participants must read and accept the Contest Terms and Conditions.
- Deadline for manuscript submission is April 29, 2016, 23:59 UTC – 12 hours (e.g., April 30, 2016, 7:59 in New York City, 13:59 in Paris, or 19:59 in Beijing).
- Each submitted manuscript will be authored by one or more co-authors (team of participants). One and only one submission originating from each team will be allowed to the Contest. Should multiple entries from the same team be received for the same track, then exclusively the first submission received will be considered.
- Submission will be processed using the easy chair service dedicated to the Data Fusion Contest 2016.
- Submission will be compliant with the following formatting instructions:
- The manuscript will be written in English, will describe the addressed problem, the proposed method, and the experimental results, and will provide the necessary references.
- The manuscript will be formatted as a PDF file following the guidelines and templates for IGARSS 2016 full papers. Click here for details.
Failure to follow any of these rules will automatically make the submission invalid, resulting in the manuscript not being evaluated.
Participants to the Contest are not requested to submit an extended abstract to IGARSS 2016 by the corresponding conference deadline in January 2016. They will submit their 4-page full papers directly to the Contest by April 29, 2016. The received manuscripts will be evaluated by the Award Committee of the Contest, and the 4 best ranking full papers will be directly included in the IGARSS Technical Program and Proceedings.
The Contest is being organized in collaboration with Deimos Imaging and UrtheCast. The IADF TC wishes to express its greatest appreciation to Deimos Imaging and UrtheCast, for acquiring and providing the data used in the competition and for indispensable contribution to the organization of the Contest, and to the IEEE GRSS for continuously supporting the annual Data Fusion Contest through funding and resources.
How to Get the Data
The data are provided only for the purpose of participation in the 2016 Data Fusion Contest. To request the data set, please click here to proceed to registration.
By submitting the registration form, participants acknowledge that they register to the Contest, that they have read the following Contest Terms and Conditions, and that they agree to these terms and conditions:
- The owner of the data and of the copyright on the data is Deimos Imaging, Spain.
- The data are only available for the scientific purposes of the 2016 IEEE GRSS Data Fusion Contest.
- Any dissemination or distribution of the data by any registered user is strictly forbidden.
- The data can be used in scientific publications subject to approval by the IEEE GRSS Image Analysis and Data Fusion Technical Committee and by the data owner on a case-by-case basis. To submit a scientific publication for approval, the publication shall be sent as an attachment to an e-mail addressed to email@example.com and firstname.lastname@example.org.
- In any scientific publication using the data, the data shall be identified as “grss_dfc_2016” and shall be referenced as follows: “[REF. NO.] 2016 IEEE GRSS Data Fusion Contest. Online: http://www.grss-ieee.org/community/technical-committees/data-fusion”.
- Any scientific publication using the data shall include a section “Acknowledgement”. This section shall include the following sentence: “The authors would like to thank Deimos Imaging for acquiring and providing the data used in this study, and the IEEE GRSS Image Analysis and Data Fusion Technical Committee.”