![]() We believe that advancing automated feature extraction techniques will serve important downstream uses of map data. Today, map features such as roads, building footprints, and points of interest are primarily created through manual techniques. DigitalGlobe, CosmiQ Works, and NVIDIA have partnered to release the SpaceNet data set to the public to enable developers and data scientists. One area for innovation is the application of computer vision and deep learning to extract information from satellite imagery at scale. The commercialization of the geospatial industry has led to an explosive amount of data being collected to characterize our changing planet. There are other, less significant differences, so if you participated in the first contest please read this document carefully to make sure you are aware of changes in the details. All winning solutions must be submitted as docker containers with all preprocessing and postprocessing steps.Organizations can participate but will not be eligible for prize money.Source code and algorithm description of round 1 winners is available.Usage of external data and pretrained models are explicitly allowed.The length of the competition is longer (2 months).The quality of the building footprint annotations has been improved.There are multiple new imagery formats (PAN, MUL, RGB-PanSharpen, MUL-PanSharpen).There are much more data, featuring 4 cities.The most important differences are the following: Most of the problem statement is identical to the specification used in the first challenge. ![]() This contest is the second edition of the SpaceNet building footprint detection challenge. ** To win the Early Incentive your solution must be the first to reach a threshold of 400,000 for the average F-score of all the cities. * The winning entry on the Paris data set must score higher than 400,000, which is above a score derived solely from OpenStreetMaps (OSM). ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |