Elevating satellite imagery
The task presented to participants was to generate and submit an algorithm to convert high-resolution satellite images to 3D point clouds for datasets. The task proved to be a daunting one, as only 21 of 364 coders generated results. Qin’s top five finish is especially impressive as he was the only academic faculty member whose code produced results and who participated in the final worldwide challenge. The remaining top finishers are full time researchers whose daily activities are dedicated to generating such code.
IARPA’s coding challenge is a part of the agency’s ongoing effort to advance research and innovation within the Intelligence Community. Among the goals and objectives of the Challenge are:
- To promote and benchmark research in multiple view stereo algorithms applied to satellite imagery
- Foster innovation through crowdsourcing and moving beyond current research limitations for 3D point clouds
- Cultivate and sustain an ongoing collaborative community dedicated to this technology and research
Dr. Qin’s research is in the area of geospatial data analytics. The goal of his research group is to develop and apply geospatial data acquisition, remote sensing techniques on managing cyber infrastructure, monitoring large-scale environmental changes. This involves solving problems of 2D/3D urban scene understanding, geometric modeling and calibration of passive/active sensors, analysis of imaging spectrum data, etc.
Dr. Qin holds a dual appointment in the Departments of Civil, Environmental and Geodetic Engineering and Electrical and Computer Engineering. Visit his website HERE.
View Professor Qin's Big Data for Good video.
