Qin finishes fourth in worldwide IARPA challenge

Rungjun QinAssistant Professor and TDA affiliate Rongjun Qin (shown at right) placed fourth out of 364 participants worldwide in the Multi-view Stereo 3D Mapping Master Challenge hosted by the Intelligence Advanced Research Projects Activity (IARPA), within the Office of the Director of National Intelligence.

The competition, which drew experts from the academia, industry, and the public sector, is designed to advance research and innovation within the intelligence community. Specifically, IARPA is using the crowdsourcing approach to develop automated analytics tools for use with the enormous amounts of data generated by commercial satellites.

Participants were charged with creating an algorithm that converts 2D satellite images taken from different angles into point clouds of 3D coordinates that indicate the position and height of features. Submissions were judged on accuracy compared to ground truth and completeness.

The challenge lived up to its billing: Only 21 of 364 participating coders generated results, and among the top five finishers, Qin was the lone full-time faculty member among four full-time coders to generate results.

Multi-view satellite image

Multi-view satellite image from IARPA multi-view data. Large color image above: Qin’s color-coded 3D reconstruction of trees.

Qin’s research in geospatial data analytics regularly tackles 2D/3D imaging issues and utilizes his mix of expertise in both computer science and geodetic engineering.

Now, Qin is further developing the software and consolidating this working branch. He hopes this software can be used for city-wide, state-wide and country-wide 3D reconstruction of ground topography to sub-meter level. The work being done will provide a solid foundation towards the future satellite-based intelligent sensing and data analysis.

See the IARPA Challenge concluding workshop video here. (Dr. Qin’s presentation starts at 1:07.)

Share this page
Suggested Articles
Foundations of Data Science & AI Community of Practice bridges connections into foundational and applied research with AI

The Foundations of Data Science & AI Community of Practice at TDAI aims to build a community at Ohio State focused on artificial intelligence, as well as theoretical and algorithmic foundations,...

COVIDCommons launched to compile COVID-19 models and datasets

Ayaz Hyder, TDAI affiliate and assistant professor of environmental health sciences, has been using his expertise in computational epidemiology to help develop a shared data resource that can be used...

Libraries, Data, and Privacy

By Alison Armstrong, MALS, and Amanda Rinehart, MLIS and MS, Botany/Plant Biology Librarians have a long history of respecting, protecting, and defending patron[i] confidentiality and privacy; the freedom to read...

Columbus tops for tech workers

Columbus, Ohio, tops SmartAsset‘s list of Best Cities to Work in Tech in 2017. The site, which provides tools to aid financial decision-making, notes that “the city also benefits from being...

Developing a drug repurposing knowledge graph can guide COVID-19 efforts

The fight against COVID-19 has provided a host of challenges to experts in varying fields to find ways that improve or redesign current systems in a way better suited for...