Resolution Transfer for Object Detection from Satellite Imagery

Smallsat constellations are an increasingly common source of global-scale overhead imagery that are refreshed with a higher frequency than traditional satellites. The smaller size and lower cost of smallsats enable frequent revisits, but result in images with lower resolution and quality than the hi...

Full description

Saved in:
Bibliographic Details
Main Authors: Yellin, Florence, Smith, Eric, Albright, Michael, McCloskey, Scott
Format: Conference Proceeding
Language:English
Subjects:
Airplanes
Annotations
Image resolution
Small satellites
Training
Training data
Visualization
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Smallsat constellations are an increasingly common source of global-scale overhead imagery that are refreshed with a higher frequency than traditional satellites. The smaller size and lower cost of smallsats enable frequent revisits, but result in images with lower resolution and quality than the high resolution (HR) images from traditional satellites. In order to benefit from the increased temporal frequency provided by smallsat constellations, new approaches are needed to automatically detect objects in their imagery. We present a super resolution (SR) approach that incorporates domain adaptation (DA) to enable object detection from low resolution (LR) images without the need for paired training data or annotations in the LR domain. Our Resolution Transfer approach addresses the resolution and quality loss for smallsats, as demonstrated via airplane detection.
ISSN:2831-7475
DOI:10.1109/ICPR56361.2022.9956559