Version 1
: Received: 19 March 2020 / Approved: 20 March 2020 / Online: 20 March 2020 (09:50:54 CET)
Version 2
: Received: 15 April 2020 / Approved: 16 April 2020 / Online: 16 April 2020 (03:08:50 CEST)
Version 3
: Received: 28 April 2020 / Approved: 29 April 2020 / Online: 29 April 2020 (13:33:56 CEST)
Rabbi, J.; Ray, N.; Schubert, M.; Chowdhury, S.; Chao, D. Small-Object Detection in Remote Sensing Images with End-to-End Edge-Enhanced GAN and Object Detector Network. Remote Sens.2020, 12, 1432.
Rabbi, J.; Ray, N.; Schubert, M.; Chowdhury, S.; Chao, D. Small-Object Detection in Remote Sensing Images with End-to-End Edge-Enhanced GAN and Object Detector Network. Remote Sens. 2020, 12, 1432.
Rabbi, J.; Ray, N.; Schubert, M.; Chowdhury, S.; Chao, D. Small-Object Detection in Remote Sensing Images with End-to-End Edge-Enhanced GAN and Object Detector Network. Remote Sens.2020, 12, 1432.
Rabbi, J.; Ray, N.; Schubert, M.; Chowdhury, S.; Chao, D. Small-Object Detection in Remote Sensing Images with End-to-End Edge-Enhanced GAN and Object Detector Network. Remote Sens. 2020, 12, 1432.
Abstract
The detection performance of small objects in remote sensing images is not satisfactory compared to large objects, especially in low-resolution and noisy images. A generative adversarial network (GAN)-based model called enhanced super-resolution GAN (ESRGAN) shows remarkable image enhancement performance, but reconstructed images miss high-frequency edge information. Therefore, object detection performance degrades for small objects on recovered noisy and low-resolution remote sensing images. Inspired by the success of edge enhanced GAN (EEGAN) and ESRGAN, we apply a new edge-enhanced super-resolution GAN (EESRGAN) to improve the image quality of remote sensing images and use different detector networks in an end-to-end manner where detector loss is backpropagated into the EESRGAN to improve the detection performance. We propose an architecture with three components: ESRGAN, Edge Enhancement Network (EEN), and Detection network. We use residual-in-residual dense blocks (RRDB) for both the ESRGAN and EEN, and for the detector network, we use the faster region-based convolutional network (FRCNN) (two-stage detector) and single-shot multi-box detector (SSD) (one stage detector). Extensive experiments on a public (car overhead with context) and a self-assembled (oil and gas storage tank) satellite dataset show superior performance of our method compared to the standalone state-of-the-art object detectors.
Computer Science and Mathematics, Computer Vision and Graphics
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Received:
16 April 2020
Commenter:
JAKARIA RABBI
Commenter's Conflict of Interests:
Author
Comment: Most of the figures are updated.
New results are included.
A new literature review is included.
Corrected a lot of grammar mistakes.
Abbreviations are included.
New discussions are included
Commenter: JAKARIA RABBI
Commenter's Conflict of Interests: Author