|IARPA 3D Mapping Challenge Now Open|
|Written by Sue Gee|
|Monday, 11 July 2016|
A challenge starting on Top Coder this week asks, "Can you develop the Multi-View Stereo (MVS) 3D mapping algorithm for commercial satellite imagery with the best accuracy and completeness?".
The challenge, which is being conducted on behalf of IARPA consists of two contests—Explorer and Master—which progress in level of difficulty. Solvers will be asked to generate and submit an algorithm to convert high-resolution satellite images to 3D point clouds for the contest datasets.
According to the challenge site:
IARPA is conducting this Challenge to invite the broader research community of industry and academia, with or without experience in multi-view satellite imagery, to participate in a convenient, efficient and non-contractual way. IARPA’s use of a crowdsourcing approach to stimulate breakthroughs in science and technology also supports the White House’s Strategy for American Innovation, as well as government transparency and efficiency.
The Explorer phase opened on July 11 and registered competitors now have access to its datasets which include Digital Globe commercial satellite images covering challenge sites in full National Imagery Transmission Format (NITF) format and a KML bounding box for the challenge area.
Participants are asked to develop a Multi-View Stereo (MVS) solution to generate dense 3D point clouds using the commercial satellite images provided. Each submitted point cloud will be registered to ground truth using X, Y, and Z translational search and then compared to determine accuracy and completeness metric scores where:
The judging criteria may be adjusted for the Master contest based on lessons learned from the Explorer contest and feedback provided by the solvers.
Like other Top Coder contests, throughout the Challenge, an online leaderboard will display solvers’ rankings and accomplishments, giving them various opportunities to have their work viewed and appreciated by stakeholders from industry, government and academic communities.
Solvers will be eligible to win cash prizes during both the Explorer and Master challenges from a total prize purse of $100K. Winners will be invited to present their solutions at a conference hosted by IARPA in the fall, where they will detail their approach. Excellent paper submissions will also be eligible for cash prizes.
The prize pool for the Explorer phase is $16,500 with cash prizes for the top 5 competitors plus five Docker incentives of $100 each (for providing software in a Docker container) and 10 Feedback awards of $100. The Master phase follows in September with larger cash prizes.
To take part you need to join Topcoder, a community that now has 1 million members that runs challenges and competitions in data science, development and design. You also need to register for each phase of the contest. The age restriction is 13 and above and the contest is void where it is prohibited by law.
or email your comment to: firstname.lastname@example.org
|Last Updated ( Tuesday, 12 July 2016 )|