To read this content please select one of the options below:

Super-resolution with generative adversarial networks for improved object detection in aerial images

Aslan Ahmet Haykir (Department of Computer Engineering, Istanbul Technical University, Istanbul, Turkey)
Ilkay Oksuz (Department of Computer Engineering, Istanbul Technical University, Istanbul, Turkey)

Information Discovery and Delivery

ISSN: 2398-6247

Article publication date: 21 November 2022

Issue publication date: 24 November 2023

139

Abstract

Purpose

Data quality and data resolution are essential for computer vision tasks like medical image processing, object detection, pattern recognition and so on. Super-resolution is a way to increase the image resolution, and super-resolved images contain more information compared to their low-resolution counterparts. The purpose of this study is analyzing the effects of the super resolution models trained before on object detection for aerial images.

Design/methodology/approach

Two different models were trained using the Super-Resolution Generative Adversarial Network (SRGAN) architecture on two aerial image data sets, the xView and the Dataset for Object deTection in Aerial images (DOTA). This study uses these models to increase the resolution of aerial images for improving object detection performance. This study analyzes the effects of the model with the best perceptual index (PI) and the model with the best RMSE on object detection in detail.

Findings

Super-resolution increases the object detection quality as expected. But, the super-resolution model with better perceptual quality achieves lower mean average precision results compared to the model with better RMSE. It means that the model with a better PI is more meaningful to human perception but less meaningful to computer vision.

Originality/value

The contributions of the authors to the literature are threefold. First, they do a wide analysis of SRGAN results for aerial image super-resolution on the task of object detection. Second, they compare super-resolution models with best PI and best RMSE to showcase the differences on object detection performance as a downstream task first time in the literature. Finally, they use a transfer learning approach for super-resolution to improve the performance of object detection.

Keywords

Acknowledgements

This paper has been produced benefiting from the 2232 International Fellowship for Outstanding Researchers Program of TUBITAK (Project No. 118C353). However, the entire responsibility of the publication/paper belongs to the owner of the paper. The financial support received from TUBITAK does not mean that the content of the publication is approved in a scientific sense by TUBITAK.

Citation

Haykir, A.A. and Oksuz, I. (2023), "Super-resolution with generative adversarial networks for improved object detection in aerial images", Information Discovery and Delivery, Vol. 51 No. 4, pp. 349-357. https://doi.org/10.1108/IDD-05-2022-0048

Publisher

:

Emerald Publishing Limited

Copyright © 2022, Emerald Publishing Limited

Related articles