Accuracy improvement with input image upscaling for in-orbit object detection

Daeun Seo; Jinse Kwon; Hyungshin Kim

doi:10.1117/12.2638632

26 October 2022 Accuracy improvement with input image upscaling for in-orbit object detection

Daeun Seo, Jinse Kwon, Hyungshin Kim

Proceedings Volume 12267, Image and Signal Processing for Remote Sensing XXVIII; 1226708 (2022) https://doi.org/10.1117/12.2638632
Event: SPIE Remote Sensing, 2022, Berlin, Germany

Conference Poster

Abstract

We are studying in-orbit real-time object detection for remote sensing satellites. Due to the small object size of remote sensing images, it is hard to achieve high detection accuracy, especially for resource-constrained spacecraft computers. Lightweight object detection models such as YOLO and SSD are feasible choices to achieve acceptable detection speed on board. This study proposes an accuracy-improvement method for the lightweight neural networks with an upscaling ratio estimator without retraining the model. The estimator exploits a scaling ratio that determines how much the image should be resized. With our scaling estimator, we have achieved 10.09% higher accuracy than the original YOLOv4-Tiny models with a 40% detection speed overhead.

Citation Download Citation

Daeun Seo, Jinse Kwon, and Hyungshin Kim "Accuracy improvement with input image upscaling for in-orbit object detection", Proc. SPIE 12267, Image and Signal Processing for Remote Sensing XXVIII, 1226708 (26 October 2022); https://doi.org/10.1117/12.2638632

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available