SAT-MTB-MLSC: A Benchmark Dataset for Satellite Video Multi-label Scene Classification

发布时间:2023-04-10

 Introduction:

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:

To be continued

附件下载:

  010-82178817  所长信箱  纪检信箱:jijian@csu.ac.cn
  010-82581990  北京市海淀区邓庄南路9号 (邮编:100094)