Small-Object Detection in Remote Sensing Images with End-to-End Edge-Enhanced GAN and Object Detector Network

Remote Sensing

Subir Chowdhury¹  Dennis Chao¹  Jakaria Rabbi²  Nilanjan Ray²  Matthias Schubert³ 

[1] Alberta Geological Survey, Alberta Energy Regulator, Edmonton, AB T6B 2X3, Canada;Department of Computing Science, 2-32 Athabasca Hall, University of Alberta, Edmonton, AB T6G 2E8, Canada;Institute for Informatic, Ludwig-Maximilians-Universität München, Oettingenstraße 67, D-80333 Munich, Germany;

关键词: object detection;    faster region-based convolutional neural network (FRCNN);    single-shot multibox detector (SSD);    super-resolution;    remote sensing imagery;    edge enhancement;   

DOI  :  10.3390/rs12091432

来源: DOAJ

【 摘 要 】

The detection performance of small objects in remote sensing images has not been 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) showed remarkable image enhancement performance, but reconstructed images usually miss high-frequency edge information. Therefore, object detection performance showed degradation for small objects on recovered noisy and low-resolution remote sensing images. Inspired by the success of edge enhanced GAN (EEGAN) and ESRGAN, we applied a new edge-enhanced super-resolution GAN (EESRGAN) to improve the quality of remote sensing images and used different detector networks in an end-to-end manner where detector loss was backpropagated into the EESRGAN to improve the detection performance. We proposed an architecture with three components: ESRGAN, EEN, and Detection network. We used residual-in-residual dense blocks (RRDB) for both the ESRGAN and EEN, and for the detector network, we used a faster region-based convolutional network (FRCNN) (two-stage detector) and a single-shot multibox detector (SSD) (one stage detector). Extensive experiments on a public (car overhead with context) dataset and another self-assembled (oil and gas storage tank) satellite dataset showed superior performance of our method compared to the standalone state-of-the-art object detectors.

【 授权许可】

Unknown