Organizations must self-identify in the challenge forum.Ĭompetition Length – The challenge is longer (nine weeks instead of three weeks) to allow developers more time to implement and improve their solutions. Organizations/companies can also participate but will not be eligible for prize money and but can place in the standings if they are willing to share their solution. Teams – In the spirit of encouraging more collaboration, we are allowing teams of up to five people. Our belief is that it makes sense to build from existing solutions, as many improvements in computer vision follow this trend. The implementations for the Round 1 winning algorithms are described on CosmiQ Works’ blog. We are interested in evaluating the potential benefits of various image processing techniques and seeing how multi-spectral information can be used to improve performance.Įxternal Data and Pretrained Models – The use of external data and pretrained models are explicitly allowed. The footprints cover new areas in four geographically diverse cities to help developers improve algorithm training for different building types and construction materials.ĭata formats - Multiple imagery formats (panchromatic, multi-spectral, RGB-pansharpen, multispectral-pansharpen) are provided to allow experimentation with different types of imagery for training. Improved training data - The quality of the building footprints has been improved using 30 cm image strips from WorldView-3 (versus a 50 cm mosaic) and more accurate and consistent techniques to derive the “ground truth” footprints. The insights we gained from Round 1 of the competition informed the following changes for Round 2: The results of the first challenge were a step toward automation, though there remained room for improvement. We utilized the SpaceNet on AWS open corpus of satellite imagery and geospatial data as the source of training data for The SpaceNet Challenge. 30cm WorldView-3 imagery and building footprints in Las Vegas, Nevada There are many everyday uses that will benefit from better maps including disaster response, security analytics, and autonomous vehicle navigation. Algorithms to generate such features have the potential to drastically improve the accuracy, currency, completeness, and consistency of maps. Nevertheless, there are many places in the world that remain unmapped – including populated urban areas.
The first objects that mappers often trace are the easily identifiable infrastructure – buildings and roads. Why automate the extraction of building footprints? Online mapping platforms like OpenStreetMap (OSM) provide a simple interface for the public to help improve maps by “tracing” objects to draw points, lines, and polygons from satellite imagery. We expect more improvement before the contest ends and hope to see these algorithms eventually incorporated into mapping workflows. Early results on the leaderboard show more than a 2x improvement in algorithm performance compared to Round 1. This month, we kicked off The SpaceNet Challenge Round 2 as a follow-on to our first competition to continue engaging the machine learning community with $15,500 of prizes. Although there is still admittedly a way to go before mapping will be fully automated, current algorithms are showing promise. The question is, can computer vision algorithms help us actually create maps? We believe – yes. DigitalGlobe, CosmiQ Works, and NVIDIA launched SpaceNet last year to encourage the applications of such algorithms to geospatial data, including automating the creation of map data from satellite imagery. Each week, it seems a new deep learning technique is published. Machine learning is currently one of the most active areas of innovation.
0 kommentar(er)
