A Multitask Benchmark Dataset for Satellite Video: Object Detection, Tracking, and Segmentation

Video satellites can continuously image large areas and provide dynamic, real-time monitoring of hotspots and objects. The intelligent processing and analysis of satellite video have become a research hotspot in the field of remote sensing. However, the lack of high-quality satellite video datasets...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on geoscience and remote sensing 2023, Vol.61, p.1-21
Main Authors: Li, Shengyang, Zhou, Zhuang, Zhao, Manqi, Yang, Jian, Guo, Weilong, Lv, Yixuan, Kou, Longxuan, Wang, Han, Gu, Yanfeng
Format: Article
Language:English
Subjects:
Algorithms
Annotations
Benchmarks
Boxes
Datasets
Detection
Horizontal orientation
Hot spots
Image processing
Image segmentation
Object recognition
Remote sensing
Satellite imagery
Satellite tracking
Satellites
Video
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Video satellites can continuously image large areas and provide dynamic, real-time monitoring of hotspots and objects. The intelligent processing and analysis of satellite video have become a research hotspot in the field of remote sensing. However, the lack of high-quality satellite video datasets limits the development of relevant object detection, object tracking, and object segmentation. In this article, we build the largest scale satellite video dataset with the most task types supported and object categories, named the satellite video multimission benchmark (SAT-MTB). First, multitask annotation of aircraft, ships, cars, trains, and their corresponding 14 categories of fine-grained objects in 249 satellite videos is performed based on horizontal bounding boxes (HBBs), oriented bounding boxes (OBBs), and masks, which cover more than 50 000 frames and 1 033 511 annotated object instances. Then, we review the tasks of object detection, object tracking, and object segmentation based on satellite videos, providing a comprehensive overview of progress in related datasets and algorithm research. Finally, we establish the first public benchmark of multitask algorithms for satellite video object detection, object tracking, and object segmentation, evaluating and analyzing the performance of a total of 47 representative algorithms under different tasks on the constructed dataset. The proposed SAT-MTB will significantly advance research in intelligent processing and analysis of satellite video and related applications.
ISSN:0196-2892
1558-0644
DOI:10.1109/TGRS.2023.3278075