Task-Related Self-Supervised Learning For Remote Sensing Image Change Detection

Cai, Zhinan; Jiang, Zhiyu; Yuan, Yuan

doi:10.1109/icassp39728.2021.9414387

Cited by 16 publications

(7 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Generative self-supervised methods like autoencoder and pretext tasks / data augmentations like image inpainting and pixel based contrastive learning can be helpful. Change detection [93,120,151,98,230,199,215,186,186] is usually also a pixellevel task which utilizes multitemporal information to detect changing pixels. In hyperspectral image analysis, most of the tasks are based on pixel level, including hyperspectral image classification 4 [106,100,101], image denoising [233], spectral unmixing [99], target detection [232], image restoration [102] and super-resolution [105,104].…”

Section: B Applicationsmentioning

confidence: 99%

See 1 more Smart Citation

Self-Supervised Learning in Remote Sensing: A review

Wang

Albrecht

Braham

et al. 2022

IEEE Geosci. Remote Sens. Mag.

136

View full text Add to dashboard Cite

In deep learning research, self-supervised learning (SSL) has received great attention triggering interest within both the computer vision and remote sensing communities. While there has been a big success in computer vision, most of the potential of SSL in the domain of earth observation remains locked. In this paper, we provide an introduction to, and a review of the concepts and latest developments in SSL for computer vision in the context of remote sensing. Further, we provide a preliminary benchmark of modern SSL algorithms on popular remote sensing datasets, verifying the potential of SSL in remote sensing and providing an extended study on data augmentations. Finally, we identify a list of promising directions of future research in SSL for earth observation (SSL4EO) to pave the way for fruitful interaction of both domains.

show abstract

Section: B Applicationsmentioning

confidence: 99%

“…Dong et al [151]: GAN discriminator for temporal prediction. Cai et al[230]: clustering for hard sample mining. Leenstra et al[186]: triplet loss + binary cross entropy loss.…”

mentioning

confidence: 99%

Self-Supervised Learning in Remote Sensing: A review

Wang

Albrecht

Braham

et al. 2022

IEEE Geosci. Remote Sens. Mag.

136

View full text Add to dashboard Cite

show abstract

“…The change-detection method based on the different images is the most-applied, pixel-level change-detection method [ 174 ]. For the different images, different methods are used to obtain the final change-detection results, including the thresholding method, pattern classification method, Markov random field method, multivariate statistical analysis method, and so on [ 175 , 176 , 177 ]. Due to the advantage of multi-level complex-feature extraction, end-to-end, pre-training, large-scale training sets, and other deep learning training mechanisms have also been applied to change detection [ 178 ].…”

Section: Remote Sensing Monitoring Approachesmentioning

confidence: 99%

Remote Sensing Approaches for Meteorological Disaster Monitoring: Recent Achievements and New Challenges

2022

IJERPH

View full text Add to dashboard Cite

Meteorological disaster monitoring is an important research direction in remote sensing technology in the field of meteorology, which can serve many meteorological disaster management tasks. The key issues in the remote sensing monitoring of meteorological disasters are monitoring task arrangement and organization, meteorological disaster information extraction, and multi-temporal disaster information change detection. To accurately represent the monitoring tasks, it is necessary to determine the timescale, perform sensor planning, and construct a representation model to monitor information. On this basis, the meteorological disaster information is extracted by remote sensing data-processing approaches. Furthermore, the multi-temporal meteorological disaster information is compared to detect the evolution of meteorological disasters. Due to the highly dynamic nature of meteorological disasters, the process characteristics of meteorological disasters monitoring have attracted more attention. Although many remote sensing approaches were successfully used for meteorological disaster monitoring, there are still gaps in process monitoring. In future, research on sensor planning, information representation models, multi-source data fusion, etc., will provide an important basis and direction to promote meteorological disaster process monitoring. The process monitoring strategy will further promote the discovery of correlations and impact mechanisms in the evolution of meteorological disasters.

show abstract

“…It enables the detection and analysis of surface changes on Earth through the comparative analysis of remote sensing images captured within the same geographic region over time. As multi-spectral, hyperspectral, and synthetic aperture radar (SAR) satellites alongside other advanced remote sensing platforms continue to proliferate, the diversity of obtainable remote sensing datasets is rapidly expanding [7,8]. This expansion is propelling the advancement of CD techniques.…”

Section: Introduction 1backgroundmentioning

confidence: 99%

Enhanced Graph Structure Representation for Unsupervised Heterogeneous Change Detection

Tang,

Yang,

Han

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

Heterogeneous change detection (CD) is widely applied in various fields such as urban planning, environmental monitoring, and disaster management. It enhances the accuracy and comprehensiveness of surface change monitoring by integrating multi-sensor remote sensing data. Scholars have proposed many graph-based methods to address the issue of incomparable heterogeneous images caused by imaging differences. However, these methods often overlook the influence of changes in vertex status on the graph structure, which limits their ability to represent image structural features. To tackle this problem, this paper presents an unsupervised heterogeneous CD method based on enhanced graph structure representation (EGSR). This method enhances the representation capacity of the graph structure for image structural features by measuring the unchanged probabilities of vertices, thereby making it easier to detect changes in heterogeneous images. Firstly, we construct the graph structure using image superpixels and measure the structural graph differences of heterogeneous images in the same image domain. Then, we calculate the unchanged probability of each vertex in the structural graph and reconstruct the graph structure using this probability. To accurately represent the graph structure, we adopt an iterative framework for enhancing the representation of the graph structure. Finally, at the end of the iteration, the final change map (CM) is obtained by binary segmentation of the graph vertices based on their unchanged probabilities. The effectiveness of this method is validated through experiments on four sets of heterogeneous image datasets and two sets of homogeneous image datasets.

show abstract

Task-Related Self-Supervised Learning For Remote Sensing Image Change Detection

Cited by 16 publications

References 22 publications

Self-Supervised Learning in Remote Sensing: A review

Self-Supervised Learning in Remote Sensing: A review

Remote Sensing Approaches for Meteorological Disaster Monitoring: Recent Achievements and New Challenges

Enhanced Graph Structure Representation for Unsupervised Heterogeneous Change Detection

Contact Info

Product

Resources

About