SAT-MTB:A Multi-task Benchmark Dataset for Satellite Videos: Object Detection, Tracking, and Segmentation
SatMTB contains 249 videos with more than 50,000 sequential frames. The object categories are divided into two levels of coarse and fine granularity, with aircraft, ships, vehicles, trains and their corresponding 14 types of fine-grained objects annotated frame by frame in the form of horizontal bounding box, rotating bounding box, masks, etc. The total number of annotation instances is 1,033,511.
SatMTB contains the significant challenges in satellite video, such as multi-task, fine-grained objects, small targets, complex backgrounds.
Sample Videos:
Download:
Baidu Netdisk:https://pan.baidu.com/s/1wYPXHBA64NiT6nNEED5tFA password:s5y7
Onedrive: https://1drv.ms/u/s!As6OdROt0o4Xin0rQCMXCUyvwvRg password:s5y7
Unzip password:CSU@2023 (SAT-MTB_Dataset.zip)
Publications:
附件下载: