SAT-MTB-MLSC: A Benchmark Dataset for Satellite Video Multi-label Scene Classification
The SAT-MTB-MLSC dataset consists of 2,232 satellite videos for training and 1,317 satellite videos for testing with overall 141,960 frames. There are 14 classes of static ground things (airport, sea, buildings, runway, parking lot, railway, overpass, coastline, harbor, intersection, bridge, stadium, railway station, roundabout) and 4 classes of dynamic objects (moving car, moving plane, moving ship, moving train) predefined in the dataset.
Dataset Statistics:
Downloads:
Training dataset: Coming soon.
Test dataset: Coming soon.
Publications:
附件下载: