Centre dedocumentation
scientifique

Learning deep semantic segmentation network under multiple weakly-supervised constraints for cross-domain remote sensing image semantic segmentation / Yansheng Li in ISPRS Journal of photogrammetry and remote sensing, vol 175 (May 2021)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 175 (May 2021) . - pp 20 - 33 Titre : Learning deep semantic segmentation network under multiple weakly-supervised constraints for cross-domain remote sensing image semantic segmentation Type de document : Article/Communication Auteurs : Yansheng Li, Auteur ; Te Shi, Auteur ; Yongjun Zhang, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 20 - 33 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] classification semi-dirigée [Termes descripteurs IGN] données d'apprentissage [Termes descripteurs IGN] programmation par contraintes [Termes descripteurs IGN] segmentation sémantique Résumé : (auteur) Due to its wide applications, remote sensing (RS) image semantic segmentation has attracted increasing research interest in recent years. Benefiting from its hierarchical abstract ability, the deep semantic segmentation network (DSSN) has achieved tremendous success on RS image semantic segmentation and has gradually become the mainstream technology. However, the superior performance of DSSN highly depends on two conditions: (I) massive quantities of labeled training data exist; (II) the testing data seriously resemble the training data. In actual RS applications, it is difficult to fully meet these conditions due to the RS sensor variation and the distinct landscape variation in different geographic locations. To make DSSN fit the actual RS scenario, this paper exploits the cross-domain RS image semantic segmentation task, which means that DSSN is trained on one labeled dataset (i.e., the source domain) but is tested on another varied dataset (i.e., the target domain). In this setting, the performance of DSSN is inevitably very limited due to the data shift between the source and target domains. To reduce the disadvantageous influence of data shift, this paper proposes a novel objective function with multiple weakly-supervised constraints to learn DSSN for cross-domain RS image semantic segmentation. Through carefully examining the characteristics of cross-domain RS image semantic segmentation, multiple weakly-supervised constraints include the weakly-supervised transfer invariant constraint (WTIC), weakly-supervised pseudo-label constraint (WPLC) and weakly-supervised rotation consistency constraint (WRCC). Specifically, DualGAN is recommended to conduct unsupervised style transfer between the source and target domains to carry out WTIC. To make full use of the merits of multiple constraints, this paper presents a dynamic optimization strategy that dynamically adjusts the constraint weights of the objective function during the training process. With full consideration of the characteristics of the cross-domain RS image semantic segmentation task, this paper gives two cross-domain RS image semantic segmentation settings: (I) variation in geographic location and (II) variation in both geographic location and imaging mode. Extensive experiments demonstrate that our proposed method remarkably outperforms the state-of-the-art methods under both of these settings. The collected datasets and evaluation benchmarks have been made publicly available online (https://github.com/te-shi/MUCSS). Numéro de notice : A2021-261 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2021.02.009 date de publication en ligne : 06/03/2021 En ligne : https://doi.org/10.1016/j.isprsjprs.2021.02.009 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97302 [article]

Detecting ground deformation in the built environment using sparse satellite InSAR data with a convolutional neural network / Nantheera Anantrasirichai in IEEE Transactions on geoscience and remote sensing, vol 59 n° 4 (April 2021)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 59 n° 4 (April 2021) . - pp 2940 - 2950 Titre : Detecting ground deformation in the built environment using sparse satellite InSAR data with a convolutional neural network Type de document : Article/Communication Auteurs : Nantheera Anantrasirichai, Auteur ; Juliet Biggs, Auteur ; Krisztina Kelevitz, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 2940 - 2950 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications [Termes descripteurs IGN] apprentissage automatique [Termes descripteurs IGN] bati [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] complétion [Termes descripteurs IGN] covariance [Termes descripteurs IGN] déformation de la croute terrestre [Termes descripteurs IGN] données d'apprentissage [Termes descripteurs IGN] effet atmosphérique [Termes descripteurs IGN] image radar moirée [Termes descripteurs IGN] interféromètrie par radar à antenne synthétique [Termes descripteurs IGN] interpolation spatiale [Termes descripteurs IGN] matrice [Termes descripteurs IGN] optimisation (mathématiques) [Termes descripteurs IGN] représentation parcimonieuse [Termes descripteurs IGN] Royaume-Uni [Termes descripteurs IGN] zone urbaine Résumé : (auteur) The large volumes of Sentinel-1 data produced over Europe are being used to develop pan-national ground motion services. However, simple analysis techniques like thresholding cannot detect and classify complex deformation signals reliably making providing usable information to a broad range of nonexpert stakeholders a challenge. Here, we explore the applicability of deep learning approaches by adapting a pretrained convolutional neural network (CNN) to detect deformation in a national-scale velocity field. For our proof-of-concept, we focus on the U.K. where previously identified deformation is associated with coal-mining, ground water withdrawal, landslides, and tunneling. The sparsity of measurement points and the presence of spike noise make this a challenging application for deep learning networks, which involve calculations of the spatial convolution between images. Moreover, insufficient ground truth data exist to construct a balanced training data set, and the deformation signals are slower and more localized than in previous applications. We propose three enhancement methods to tackle these problems: 1) spatial interpolation with modified matrix completion; 2) a synthetic training data set based on the characteristics of the real U.K. velocity map; and 3) enhanced overwrapping techniques. Using velocity maps spanning 2015–2019, our framework detects several areas of coal mining subsidence, uplift due to dewatering, slate quarries, landslides, and tunnel engineering works. The results demonstrate the potential applicability of the proposed framework to the development of automated ground motion analysis systems. Numéro de notice : A2021-283 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s12518-020-00323-6 date de publication en ligne : 31/08/2020 En ligne : https://doi.org/10.1007/s12518-020-00323-6 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97391 [article]

Extraction of sea ice cover by Sentinel-1 SAR based on support vector machine with unsupervised generation of training data / Xiao-Ming Li in IEEE Transactions on geoscience and remote sensing, vol 59 n° 4 (April 2021)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 59 n° 4 (April 2021) . - pp 3040 - 3053 Titre : Extraction of sea ice cover by Sentinel-1 SAR based on support vector machine with unsupervised generation of training data Type de document : Article/Communication Auteurs : Xiao-Ming Li, Auteur ; Yan Sun, Auteur ; Qiang Zhang, Auteur Année de publication : 2021 Article en page(s) : pp 3040 - 3053 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications [Termes descripteurs IGN] Arctique, océan [Termes descripteurs IGN] classification non dirigée [Termes descripteurs IGN] classification par séparateurs à vaste marge [Termes descripteurs IGN] données d'apprentissage [Termes descripteurs IGN] entropie [Termes descripteurs IGN] extraction de traits caractéristiques [Termes descripteurs IGN] glace de mer [Termes descripteurs IGN] image radar moirée [Termes descripteurs IGN] image Sentinel-SAR [Termes descripteurs IGN] matrice de co-occurrence [Termes descripteurs IGN] niveau de gris (image) [Termes descripteurs IGN] polarisation croisée [Termes descripteurs IGN] rétrodiffusion [Termes descripteurs IGN] texture Résumé : (auteur) In this article, we focus on developing a novel method to extract sea ice cover (i.e., discrimination/classification of sea ice and open water) using Sentinel-1 (S1) cross-polarization [vertical–horizontal (VH) or horizontal–vertical (HV)] data in extra-wide (EW) swath mode based on the support vector machine (SVM) method. The classification basis includes the S1 radar backscatter and texture features, which are calculated from S1 data using the gray level co-occurrence matrix (GLCM). Different from previous methods where appropriate samples are manually selected to train the SVM to classify sea ice and open water, we proposed a method of unsupervised generation of the training samples based on two GLCM texture features, i.e., entropy and homogeneity, that have contrasting characteristics on sea ice and open water. We eliminate the most uncertainty of selecting training samples in machine learning and achieve automatic classification of sea ice and open water by using S1 EW data. The comparisons based on a few cases show good agreements between the synthetic aperture radar (SAR)-derived sea ice cover using the proposed method and visual inspections, of which the accuracy reaches approximately 90%–95%. Besides this, compared with the analyzed sea ice cover data Ice Mapping System (IMS) based on 728 S1 EW images, the accuracy of the extracted sea ice cover by using S1 data is more than 80%. Numéro de notice : A2021-284 Affiliation des auteurs : non IGN Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2020.3007789 date de publication en ligne : 20/07/2020 En ligne : https://doi.org/10.1109/TGRS.2020.3007789 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97392 [article]

Rotation-invariant feature learning in VHR optical remote sensing images via nested siamese structure with double center loss / Ruoqiao Jiang in IEEE Transactions on geoscience and remote sensing, vol 59 n° 4 (April 2021)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 59 n° 4 (April 2021) . - pp 3326 - 3337 Titre : Rotation-invariant feature learning in VHR optical remote sensing images via nested siamese structure with double center loss Type de document : Article/Communication Auteurs : Ruoqiao Jiang, Auteur ; Shaohui Mei, Auteur ; Mingyang Ma, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 3326 - 3337 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] détection d'objet [Termes descripteurs IGN] données d'apprentissage [Termes descripteurs IGN] échantillon [Termes descripteurs IGN] extraction de traits caractéristiques [Termes descripteurs IGN] image à très haute résolution [Termes descripteurs IGN] invariant [Termes descripteurs IGN] réseau neuronal siamois [Termes descripteurs IGN] rotation Résumé : (auteur) Rotation-invariant features are of great importance for object detection and image classification in very-high-resolution (VHR) optical remote sensing images. Though multibranch convolutional neural network (mCNN) has been demonstrated to be very effective for rotation-invariant feature learning, how to effectively train such a network is still an open problem. In this article, a nested Siamese structure (NSS) is proposed for training the mCNN to learn effective rotation-invariant features, which consists of an inner Siamese structure to enhance intraclass cohesion and an outer Siamese structure to enlarge interclass margin. Moreover, a double center loss (DCL) function, in which training samples from the same class are mapped closer to each other while those from different classes are mapped far away to each other, is proposed to train the proposed NSS even with a small amount of training samples. Experimental results over three benchmark data sets demonstrate that the proposed NSS trained by DCL is very effective to encounter rotation varieties when learning features for image classification and outperforms several state-of-the-art rotation-invariant feature learning algorithms even when a small amount of training samples are available. Numéro de notice : A2021-286 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2020.3021283 date de publication en ligne : 18/07/2020 En ligne : https://doi.org/10.1109/TGRS.2020.3021283 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97395 [article]

Anti-cross validation technique for constructing and boosting random subspace neural network ensembles for hyperspectral image classification / Laxmi Narayana Eeti in Geocarto international, vol 36 n° 6 ([30/03/2021])  

Public [article]  inGeocarto international > vol 36 n° 6 [30/03/2021] . - pp 676 - 697 Titre : Anti-cross validation technique for constructing and boosting random subspace neural network ensembles for hyperspectral image classification Type de document : Article/Communication Auteurs : Laxmi Narayana Eeti, Auteur ; Krishna Mohan Buddhiraju, Auteur Année de publication : 2021 Article en page(s) : pp 676 - 697 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes descripteurs IGN] classification par forêts aléatoires [Termes descripteurs IGN] classification par réseau neuronal [Termes descripteurs IGN] données d'apprentissage [Termes descripteurs IGN] données multisources [Termes descripteurs IGN] image hyperspectrale [Termes descripteurs IGN] jeu de données [Termes descripteurs IGN] précision de la classification Résumé : (Auteur) Achieving high classification accuracy is vital in reliable information extraction from images. Single classifiers and existing ensemble methods suffer from data dimensionality, insufficient ground truth information and lack in defining optimal feature selection. This article presents a novel idea for constructing component classifiers that boost random subspace ensemble method in improving its classification performance. It is achieved through sub-optimal training of component classifiers through interference in training process during validation error evaluation. The new approach allows to enforce different class errors among component classifiers, besides improving individual class accuracy. This article demonstrates effectiveness of the anti-cross validation approach using three classical hyperspectral Image (HSI) datasets with significant improvement in classification accuracies from 3 to 10% with the proposed approach. Numéro de notice : A2021-292 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2019.1618926 date de publication en ligne : 03/06/2019 En ligne : https://doi.org/10.1080/10106049.2019.1618926 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97338 [article]

Detection of subpixel targets on hyperspectral remote sensing imagery based on background endmember extraction / Xiaorui Song in IEEE Transactions on geoscience and remote sensing, Vol 59 n° 3 (March 2021)  

Permalink

Dynamic human body reconstruction and motion tracking with low-cost depth cameras / Kangkan Wang in The Visual Computer, vol 37 n° 3 (March 2021)  

Permalink

Connecting images through time and sources: Introducing low-data, heterogeneous instance retrieval / Dimitri Gominski (2021)  

Permalink

CSVM architectures for pixel-wise object detection in high-resolution remote sensing images / Youyou Li in IEEE Transactions on geoscience and remote sensing, vol 58 n° 9 (September 2020)  

Permalink

SemCity Toulouse: a benchmark for building instance segmentation in satellite images / Ribana Roscher in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, V-5 (August 2020)  

Permalink

Ensemble learning for hyperspectral image classification using tangent collaborative representation / Hongjun Su in IEEE Transactions on geoscience and remote sensing, vol 58 n° 6 (June 2020)  

Permalink

Knowledge graphs and big data processing / Valentina Janev (2020)  

Permalink

Deep learning for conifer/deciduous classification of airborne LiDAR 3D point clouds representing individual trees / Hamid Hamraz in ISPRS Journal of photogrammetry and remote sensing, Vol 158 (December 2019)  

Permalink

Using a U-net convolutional neural network to map woody vegetation extent from high resolution satellite imagery across Queensland, Australia / Neil Flood in International journal of applied Earth observation and geoinformation, vol 82 (October 2019)  

Permalink

RoofN3D: a database for 3D building reconstruction with deep learning / Andreas Wichmann in Photogrammetric Engineering & Remote Sensing, PERS, vol 85 n° 6 (June 2019)  

Permalink