Unsupervised Change Detection in Satellite Images With Generative Adversarial Network

Ren, Caijun; Wang, Xiangyu; Gao, Jian; Zhou, Xiren; Chen, Huanhuan

doi:10.1109/tgrs.2020.3043766

Cited by 46 publications

(17 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…PSNR, largely based on mean-squared error (MSE), is a metric that is based on the average difference between corresponding pixels in two images. • The realism and diversity of the synthesized images are measured by Inception Score (IS) [42], Top-k prediction accuracy, Frechet Inception Distance (FID) score [42] and KL divergence [59]. • The pixel-wise semantic consistency of the synthesized images is measured using mean Intersection-over-Union (mIoU).…”

Section: Evaluation Metricsmentioning

confidence: 99%

GAN-Based Satellite Imaging: A Survey on Techniques and Applications

et al. 2022

View full text Add to dashboard Cite

Satellite image analysis is widely used in many real-time applications, from agriculture to the military. Due to the wide range of Generative Adversarial Network (GAN) applications in multiple areas of satellite imaging, a comprehensive review is required in this area. This paper takes the first step in this direction by categorizing the GAN-based satellite imaging research using seven considerations. We discuss not only the challenges but also future research trends and directions. Among the major findings, we have observed increasing componentization and modularization of GANs to be used as elements of larger systems. In addition to the GAN types used exclusively in each application, we demonstrate the deep neural network architectures used as the generator structure. Eventually, we summarize the results and evaluate the significant impact of GANs on improving performance compared to traditional approaches.

show abstract

Section: Evaluation Metricsmentioning

confidence: 99%

GAN-Based Satellite Imaging: A Survey on Techniques and Applications

et al. 2022

View full text Add to dashboard Cite

show abstract

“…UCD is usually divided into a method [3,16,26,30] based on the concept of Change Vector Analysis [23] (CVA) or a method [25] based on a Generative Adversarial Network (GAN) using an unlabeled bi-temporal pair image. However, because they use pre-trained weights without direct training on the dataset, the performance is low, or largescale unlabeled bi-temporal pair images are required to train the GAN model.…”

Section: Unsupervised Change Detection (Ucd)mentioning

confidence: 99%

“…To solve this data collection problem, various unsupervised change detection (UCD) methods [10,14,21,25] have been proposed. UCD approaches effectively solve the problem of expensive annotations in change detection, but they still require correctly registered bi-temporal HSR images, or the performance was low compared to supervised learning methods.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Change Detection Based on Image Reconstruction Loss

Noh¹,

Ju²,

Seo³

et al. 2022

Preprint

View full text Add to dashboard Cite

To train the change detector, bi-temporal images taken at different times in the same area are used. However, collecting labeled bi-temporal images is expensive and time consuming. To solve this problem, various unsupervised change detection methods have been proposed, but they still require unlabeled bi-temporal images. In this paper, we propose unsupervised change detection based on image reconstruction loss using only unlabeled single temporal single image. The image reconstruction model is trained to reconstruct the original source image by receiving the source image and the photometrically transformed source image as a pair. During inference, the model receives bitemporal images as the input, and tries to reconstruct one of the inputs. The changed region between bi-temporal images shows high reconstruction loss. Our change detector showed significant performance in various change detection benchmark datasets even though only a single temporal single source image was used. The code and trained models will be publicly available for reproducibility.

show abstract

“…However, for segmentation tasks with unobvious target boundaries, the result of using this loss function to train a model may be unsatisfactory. Since the generative adversarial network (GAN) was proposed [25] , plenty of generation problems have taken advantage of its idea [26] . SegAN [14] regards the image segmentation problem as an image generation problem.…”

Section: Related Workmentioning

confidence: 99%

An Encoder-Decoder Network for Automatic Clinical Target Volume Target Segmentation of Cervical Cancer in CT Images

et al. 2022

Self Cite

View full text Add to dashboard Cite

Cervical cancer is a common gynecological cancer, and its common treatment method radiotherapy depends on target area delineation. The manual delineation work takes a long time and has low accuracy, so automating such delineation is important. At present, some traditional image segmentation algorithms for target area delineation have low accuracy rates. Deep learning algorithms also face some difficulties, such as insufficient data and long training time. As the popular network used in medical image segmentation, U-net still has several disadvantages when handling small targets with unclear boundaries. According to the characteristics of the clinical target volume target segmentation task of cervical cancer, this study modified the U-net structure and optimized the training loss to improve the accuracy of small target detection. The modified structure could handle target boundaries well with operations such as bilinear upsampling. Finally, the proposed algorithm was evaluated on the dataset and compared with several deep learning-based algorithms. Results indicate that the proposed approach has certain superiority.

show abstract

Unsupervised Change Detection in Satellite Images With Generative Adversarial Network

Cited by 46 publications

References 35 publications

GAN-Based Satellite Imaging: A Survey on Techniques and Applications

GAN-Based Satellite Imaging: A Survey on Techniques and Applications

Unsupervised Change Detection Based on Image Reconstruction Loss

An Encoder-Decoder Network for Automatic Clinical Target Volume Target Segmentation of Cervical Cancer in CT Images

Contact Info

Product

Resources

About