CHANGE DETECTION IN REMOTE SENSING IMAGES USING CONDITIONAL ADVERSARIAL NETWORKS

By M. Lebedev, Y. Vizilter, O. Vygolov, V. Knyaz, A. Y. Rubis. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2018

543 citations recorded by the source corpus.

Abstract. We present a method for change detection in images using Conditional Adversarial Network approach. The original network architecture based on pix2pix is proposed and evaluated for difference map creation. The paper address three types of experiments: change detection in synthetic images without objects relative shift, change detection in synthetic images with small relative shift of objects, and change detection in real season-varying remote sensing images.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/ae15e5ccccaaff44ab542003386349ef1d3b7511

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

End-to-End Change Detection for High Resolution Satellite Images Using Improved UNet++ (2019, methodology): “Fortunately, a publicly available dataset of satellite image pairs are presented by Lebedev [54].”
Remote Sensing Image Change Detection With Transformers (2021, background): “Much recent work aims to improve the feature discriminative power of the neural networks, by designing multilevel feature fusion structures [2], [9], [10], [12], [26], [30], combining generative adversarial network (GAN)-based optimization objectives [23], [26], [28], [31], and increasing the RF of ”
SwinSUNet: Pure Transformer Network for Remote Sensing Image Change Detection (2022, background): “The CDD [44] dataset contains 11 pairs of bi-temporal images with seasonal changes, which include 7 pairs of images with the sizes of pixels and 4 pairs of images with the sizes of pixels.”
SemiCDNet: A Semisupervised Convolutional Neural Network for Change Detection in High Resolution Remote-Sensing Images (2020, background): “Note that two periods of image clips can be stacked [33], [34] or act as independent branches [35] when they are fed into different FCN architectures.”
SNUNet-CD: A Densely Connected Siamese Network for Change Detection of VHR Images (2021, methodology): “To evaluate our method, we design a series of comparative experiments on CDD [1] data set, one of the most common evaluation data sets in the ﬁeld of change detection.”
Optical Remote Sensing Image Change Detection Based on Attention Mechanism and Image Difference (2021, methodology): “The proposed approach was evaluated on ﬁve change detection data sets: the season-varying data set [48], the WHU building change detection data set [1], the SZTAKI AirChange benchmark set [49], the Onera Satellite change detection (OSCD) data set [50], and the LEVIR-CD data set [51].”
Transformers in Remote Sensing: A Survey (2022, methodology): “SwinSUNet [56] Change Detection CCD [82],”
An Empirical Study of Remote Sensing Pretraining (2022, methodology): “The first and second row separately show the change detection results of a sample image from CDD and LEVIR dataset.”
DASNet: Dual Attentive Fully Convolutional Siamese Networks for Change Detection in High-Resolution Satellite Images (2020, methodology): “Compared with the selected baselines, the proposed method yielded state-of-the-art results on the CCD dataset [40] and the BCDD dataset [41] , and the F1 scores reached 91.”
A Deeply Supervised Attention Metric-Based Network and an Open Aerial Image Dataset for Remote Sensing Change Detection (2021, methodology): “To make full use of the rich change information contained in high-resolution images, a CDD [35] was released containing 16000 image pairs.”