Automatic change detection in multitemporal X- and P-band SAR images using Gram-Schmidt process

Rosa, Rafael A. S.; Fernandes, David; Nogueira, Joao B.; Wimmer, Christian

doi:10.1109/igarss.2015.7326395

Cited by 9 publications

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…SAR-based mapping of forest disturbance has largely been based on two-date change-detection techniques [8][9][10][11][12][13][14][15][16][17][18]. These studies, mostly focused on detecting and mapping fire and logging induced disturbances in forests, show that X-, C-and L-bands are most sensitive SAR wavelengths for detecting disturbance effects in forested landscapes and that the sensitivity does not change across environments, but depend more on resolution and imaging mode.…”

Section: Related Studiesmentioning

confidence: 99%

“…The criteria in assessing the performance of the methods and the explanatory variables in damage classification were the five accuracy metrics, overall accuracy (OA), and user and producers accuracies by the categories damaged and non-damaged, and in volume estimation the error metrics of Equations (10) and (11) using both leave one out cross validation and data splitting (Sections 3.4.1 and 3.4.2). All results are shown here for the option data splitting.…”

Section: Feature Selection For Forest Classification and Accuracy Assmentioning

confidence: 99%

See 1 more Smart Citation

Boreal Forest Snow Damage Mapping Using Multi-Temporal Sentinel-1 Data

2019

View full text Add to dashboard Cite

Natural disturbances significantly influence forest ecosystem services and biodiversity. Accurate delineation and early detection of areas affected by disturbances are critical for estimating extent of damage, assessing economical influence and guiding forest management activities. In this study we focus on snow load damage detection from C-Band SAR images. Snow damage is one of the least studied forest damages, which is getting more common due to current climate trends. The study site was located in the southern part of Northern Finland and the SAR data were represented by the time series of C-band SAR scenes acquired by the Sentinel-1 sensor. Methods used in the study included improved k nearest neighbour method, logistic regression analysis and support vector machine classification. Snow damage recordings from a large snow damage event that took place in Finland during late 2018 were used as reference data. Our results showed an overall detection accuracy of 90%, indicating potential of C-band SAR for operational use in snow damage mapping. Additionally, potential of multitemporal Sentinel-1 data in estimating growing stock volume in damaged forest areas were carried out, with obtained results indicating strong potential for estimating the overall volume of timber within the affected areas. The results and research questions for further studies are discussed.

show abstract

Section: Related Studiesmentioning

confidence: 99%

Section: Feature Selection For Forest Classification and Accuracy Assmentioning

confidence: 99%

Boreal Forest Snow Damage Mapping Using Multi-Temporal Sentinel-1 Data

2019

View full text Add to dashboard Cite

show abstract

“…Principal component analysis (PCA) [9][10][11] is one of the state-of-the-art operators for modeling temporal spectral difference of unchanged pixels. Beyond PCA, Kauth-Thomas transformation [12], Gram-Schmidt orthonormalization process [13,14], multivariate alteration detection [15,16] and slow feature analysis [17,18] theories have been used for optical image change detection. However, these algorithms are mainly designed for optical images and usually fail to deal with SAR images with speckle.Given SAR images, we may meet a more complex situation in which the multi-temporal images are in different feature spaces and changed/unchanged pixels are linearly non-sparable, due to the coherent imaging mechanism.…”

mentioning

confidence: 99%

Differentially Deep Subspace Representation for Unsupervised Change Detection of SAR Images

Luo

et al. 2019

Remote Sensing

View full text Add to dashboard Cite

Temporal analysis of synthetic aperture radar (SAR) time series is a basic and significant issue in the remote sensing field. Change detection as well as other interpretation tasks of SAR images always involves non-linear/non-convex problems. Complex (non-linear) change criteria or models have thus been proposed for SAR images, instead of direct difference (e.g., change vector analysis) with/without linear transform (e.g., Principal Component Analysis, Slow Feature Analysis) used in optical image change detection. In this paper, inspired by the powerful deep learning techniques, we present a deep autoencoder (AE) based non-linear subspace representation for unsupervised change detection with multi-temporal SAR images. The proposed architecture is built upon an autoencoder-like (AE-like) network, which non-linearly maps the input SAR data into a latent space. Unlike normal AE networks, a self-expressive layer performing like principal component analysis (PCA) is added between the encoder and the decoder, which further transforms the mapped SAR data to mutually orthogonal subspaces. To make the proposed architecture more efficient at change detection tasks, the parameters are trained to minimize the representation difference of unchanged pixels in the deep subspace. Thus, the proposed architecture is namely the Differentially Deep Subspace Representation (DDSR) network for multi-temporal SAR images change detection. Experimental results on real datasets validate the effectiveness and superiority of the proposed architecture.For change detection using remotely sensed optical images, the most widely used criterion is difference operator [1] (for single channel images) or change vector analysis [6-8] (for multi-band/spectral images). Due to the temporal spectral variance caused by different atmospheric conditions, illumination and sensor calibration, image transformation has been widely used to yield robust change detection criteria. The core idea of the image transformation is to transform the multi-band/spectral image into a specific feature space, in which the unchanged temporal pixel pairs have similar representations while the changed ones differ from each other. Principal component analysis (PCA) [9][10][11] is one of the state-of-the-art operators for modeling temporal spectral difference of unchanged pixels. Beyond PCA, Kauth-Thomas transformation [12], Gram-Schmidt orthonormalization process [13,14], multivariate alteration detection [15,16] and slow feature analysis [17,18] theories have been used for optical image change detection. However, these algorithms are mainly designed for optical images and usually fail to deal with SAR images with speckle.Given SAR images, we may meet a more complex situation in which the multi-temporal images are in different feature spaces and changed/unchanged pixels are linearly non-sparable, due to the coherent imaging mechanism. Two main approaches have been developed in the literature: coherence change detection and incoherent change detection. The former uses the phase inf...

show abstract

“…La tabla 1.2 resume los métodos de detección de cambios de la categoría Transformación y sus características. [1,134,139] GS ortogonaliza vectores espectrales y produce: brillo, verdor, humedad y un componente de cambio…”

Section: Métodos Basados En Transformaciónunclassified

Técnicas de detección de cambios mediante teledetección para el desarrollo sostenible y la desertificación

Azzouzi¹

View full text Add to dashboard Cite

ligue islamique et au centre culturel islamique de Valencia (CCIV), à tous mes collègues de la société EDICOM à tous mes amis et à tous les personnes qui m'ont aidé de près ou de loin... "Ô mon Seigneur, accroît mes connaissances!" Coran (20/114) Agradecimientos Tras muchos años de trabajo, esto parece que por fin tiene un punto final, y no podría haberlo conseguido sin la ayuda, el apoyo, el consejo y el soporte de todos vosotros. Ante todo, quiero agradecer enormemente a mi directora Dr. Ana Vidal Pantaleoni por su apoyo, paciencia, atención y disponibilidad durante estos años, por darme la oportunidad de desarrollar mi carrera investigadora con ella en el Grupo de Aplicaciones de las Microondas (GAM). Muchísimas gracias. De igual manera quiero agradecer mi codirector Dr. Hadj Adda Bentounes por su labor en el desarrollo del presente trabajo. A la unión europea por su excelente programa de Erasmus Mundus (EMMAG),

show abstract

Automatic change detection in multitemporal X- and P-band SAR images using Gram-Schmidt process

Cited by 9 publications

References 20 publications

Boreal Forest Snow Damage Mapping Using Multi-Temporal Sentinel-1 Data

Boreal Forest Snow Damage Mapping Using Multi-Temporal Sentinel-1 Data

Differentially Deep Subspace Representation for Unsupervised Change Detection of SAR Images

Técnicas de detección de cambios mediante teledetección para el desarrollo sostenible y la desertificación

Contact Info

Product

Resources

About