Abstract
High-resolution satellite images (HRSIs) obtained from onboard satellite linear array cameras suffer from geometric disturbance in the presence of attitude jitter. Therefore, detection and compensation of satellite attitude jitter are crucial to reduce the geopositioning error and to improve the geometric accuracy of HRSIs. In this work, a generative adversarial network (GAN) architecture is proposed to automatically learn and correct the deformed scene features from a single remote sensing image. In the proposed GAN, a convolutional neural network (CNN) is designed to discriminate the inputs, and another CNN is used to generate so-called fake inputs. To explore the usefulness and effectiveness of a GAN for jitter detection, the proposed GANs are trained on part of the PatternNet dataset and tested on three popular remote sensing datasets, along with a deformed Yaogan-26 satellite image. Several experiments show that the proposed model provides competitive results. The proposed GAN reveals the enormous potential of GAN-based methods for the analysis of attitude jitter from remote sensing images.
Highlights
Research Center of Satellite Technology, Harbin Institute of Technology, Harbin 150001, China; Abstract: High-resolution satellite images (HRSIs) obtained from onboard satellite linear array cameras suffer from geometric disturbance in the presence of attitude jitter
We proposed a new generative adversarial network (GAN)-based image jitter compensation network (RestoreGAN) for remote sensing images
According to the jitter detection results for ZY-3 and Yaogan-26 satellites images [5,7], satellite jitter in the body coordinate system is composed of three parts: a sinusoidal curve with the dominant frequency and maximum amplitude, several highfrequency curves with small amplitude, and several low-frequency curves with small amplitude
Summary
Detection and compensation of satellite attitude jitter are crucial to reduce the geopositioning error and to improve the geometric accuracy of HRSIs. In this work, a generative adversarial network (GAN). The proposed GAN reveals the enormous potential of GAN-based methods for the analysis of attitude jitter from remote sensing images. In the application of high-resolution (HR) optical satellites, attitude jitter is a key factor affecting the accuracy of geopositioning and 3D mapping. The linear array pushbroom camera has been used in high resolution remote sensing as a mature sensor device. With respect to a satellite equipped with CCD linear array sensors, attitude jitter can deteriorate the geopositioning and mapping accuracy of HR satellites in both plane and height [6]. The warping of remote sensing images and the attitude variations are well known and are of wide concern
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
