November 29, 2017
CosmiQ Works, Radiant Solutions, and NVIDIA today announced the launch of their third SpaceNet™ competition, “Road Detection and Routing Challenge,” to derive road network and routing information from high-resolution satellite imagery. The competition, hosted on TopCoder, runs through February 2, 2018 and offers up to $50,000 in prizes for competitors to develop automated methods for extracting road networks from high-resolution satellite imagery.
The purpose of the challenge is to explore automated methods for extracting map-ready road networks and routing information from high-resolution satellite imagery. This will ultimately help create better maps, more rapidly, where they are needed most. Solving this challenge is an important stepping stone to unleashing the power of advanced computer vision algorithms applied to a variety of remote sensing data applications in both the public and private sector.
“We are excited to collaborate with our partners to launch the SpaceNet™ Challenge Round 3 to accelerate automated mapping research,” said Tony Frazier, president of Radiant Solutions. “Strong performance of participants’ algorithms from prior challenges demonstrates how engaging developers through open initiatives advances innovation across the community. Automated extraction of road networks has many valuable applications from disaster relief to autonomous vehicle navigation that impact our daily lives.”
CosmiQ Works Senior Research Scientist, Adam Van Etten, Ph.D, also stressed the importance of this type of technical capability for a variety of applications including humanitarian ones. “Optimized routing is crucial to a number of challenges, from the mundane – commuting – to the extreme, such as mass evacuation,” said Dr. Van Etten. “Satellite imagery may aid greatly in determining efficient routes through difficult terrain, particularly in cases of natural disasters or other dynamic events where the high revisit rate of satellites may provide updates faster than terrestrial methods.”
“Growth in AI algorithms is fueled by high-quality, labeled, open source datasets like SpaceNet,” said Kevin Berce, Sr. Director Business Development, Federal at NVIDIA. “We are excited about another opportunity for researchers to develop high-impact geospatial applications using NVIDIA’s GPUS and deep learning tools on the SpaceNet data corpus.”
“SpaceNet™ data lowers the barrier to entry for developers, researchers, and startups to access high quality geospatial data,” said David Lindenbaum, Principal Engineer at CosmiQ Works. “This enables the entire research and development community to focus on developing solutions to challenging geospatial problems instead of spending time on data acquisition,” he added. “Such solutions have the potential to be honed to power new commercial, academic, and government use cases.”
The entire SpaceNet™ data set is available for download at the Amazon Web Services (AWS) SpaceNet™ homepage.
About CosmiQ Works
CosmiQ Works is an IQT Lab exploring how the nation’s intelligence agencies can leverage new and emerging commercial space capabilities. CosmiQ Works is a division of IQT, the non-profit strategic investor that accelerates the development and delivery of cutting-edge technologies to U.S. government agencies that keep our nation safe. Visit www.cosmiqworks.org for more information.
About Radiant Solutions
Radiant Solutions provides highly specialized, innovative geospatial multisource data, analytics, software and services to deliver critical insights and intelligence where and when it matters most. Poised to transform how customers support global mapping and intelligence missions at scale, Radiant Solutions harnesses the proliferation of pervasive information-gathering sensors, open-source software, cloud computing, machine learning and big data analytics. Our combined team of over 1,000 sensor and spacecraft engineers, geospatial analysts, developers, data scientists and DevOps engineers delivers innovative geospatial solutions that keep our nation safe, protect critical infrastructure, and preserve scarce natural resources. Building on the pedigree of MDA Information Systems, RadiantBlue, DigitalGlobe Intelligence Solutions and HumanGeo, the newly combined Radiant Solutions has a strong track record with its advanced capabilities, open approach and experience supporting mission that helps customers in the GEOINT community reach critical decisions faster and with greater accuracy. Radiant Solutions is based in Herndon, VA with major offices across Virginia, Maryland, Florida, Michigan, and Colorado. Radiant Solutions is a business unit Maxar Technologies, a U.S. operating company (NYSE: MAXR; TSX: MAXR). For more information visit: www.RadiantSolutions.com.
NVIDIA’s (NASDAQ:NVDA) invention of the GPU in 1999 sparked the growth of the PC gaming market, redefined modern computer graphics and revolutionized parallel computing. More recently, GPU deep learning ignited modern AI — the next era of computing — with the GPU acting as the brain of computers, robots and self-driving cars that can perceive and understand the world. More information at http://nvidianews.nvidia.com/.