Centre de documentation
scientifique

Land use/land cover mapping from airborne hyperspectral images with machine learning algorithms and contextual information / Ozlem Akar in Geocarto international, vol 37 n° 22 ([10/10/2022])  

Public [article]  inGeocarto international > vol 37 n° 22 [10/10/2022] . - pp 6643 - 6670 Titre : Land use/land cover mapping from airborne hyperspectral images with machine learning algorithms and contextual information Type de document : Article/Communication Auteurs : Ozlem Akar, Auteur ; Esra Tunc Gormus, Auteur Année de publication : 2022 Article en page(s) : pp 6643 - 6670 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] carte d'occupation du sol [Termes IGN] carte de la végétation [Termes IGN] classification orientée objet [Termes IGN] classification par forêts d'arbres décisionnels [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] filtre de Gabor [Termes IGN] image hyperspectrale [Termes IGN] matrice de co-occurrence [Termes IGN] niveau de gris (image) [Termes IGN] texture d'image [Termes IGN] transformation en ondelettes [Termes IGN] Turquie Résumé : (auteur) Land use and Land cover (LULC) mapping is one of the most important application areas of remote sensing which requires both spectral and spatial resolutions in order to decrease the spectral ambiguity of different land cover types. Airborne hyperspectral images are among those data which perfectly suits to that kind of applications because of their high number of spectral bands and the ability to see small details on the field. As this technology has newly developed, most of the image processing methods are for the medium resolution sensors and they are not capable of dealing with high resolution images. Therefore, in this study a new framework is proposed to improve the classification accuracy of land use/cover mapping applications and to achieve a greater reliability in the process of mapping land use map using high resolution hyperspectral image data. In order to achieve it, spatial information is incorporated together with spectral information by exploiting feature extraction methods like Grey Level Co-occurrence Matrix (GLCM), Gabor and Morphological Attribute Profile (MAP) on dimensionally reduced image with highest accuracy. Then, machine learning algorithms like Random Forest (RF) and Support Vector Machine (SVM) are used to investigate the contribution of texture information in the classification of high resolution hyperspectral images. In addition to that, further analysis is conducted with object based RF classification to investigate the contribution of contextual information. Finally, overall accuracy, producer’s/user’s accuracy, the quantity and allocation based disagreements and location and quantity based kappa agreements are calculated together with McNemar tests for the accuracy assessment. According to our results, proposed framework which incorporates Gabor texture information and exploits Discrete Wavelet Transform based dimensionality reduction method increase the overall classification accuracy up to 9%. Amongst individual classes, Gabor features boosted classification accuracies of all the classes (soil, road, vegetation, building and shadow) to 7%, 6%, 6%, 8%, 9%, and 24% respectively with producer’s accuracy. Besides, 17% and 10% increase obtained in user’s accuracy with MAP (area) feature in classifying road and shadow classes respectively. Moreover, when the object based classification is conducted, it is seen that the OA of pixel based classification is increased further by 1.07%. An increase between 2% and 4% is achieved with producer’s accuracy in soil, vegetation and building classes and an increase between 1% and 3% is achieved by user’s accuracy in soil, road, vegetation and shadow classes. In the end, accurate LULC map is produced with object based RF classification of gabor features added airborne hyperspectral image which is dimensionally reduced with DWT method. Numéro de notice : A2022-729 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2021.1944453 Date de publication en ligne : 09/11/2021 En ligne : https://doi.org/10.1080/10106049.2021.1944453 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101675 [article]

Crowdsourcing-based application to solve the problem of insufficient training data in deep learning-based classification of satellite images / Ekrem Saralioglu in Geocarto international, vol 37 n° 18 ([01/09/2022])  

Public [article]  inGeocarto international > vol 37 n° 18 [01/09/2022] . - pp 5433 - 5452 Titre : Crowdsourcing-based application to solve the problem of insufficient training data in deep learning-based classification of satellite images Type de document : Article/Communication Auteurs : Ekrem Saralioglu, Auteur ; Oguz Gungor, Auteur Année de publication : 2022 Article en page(s) : pp 5433 - 5452 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] acquisition d'images [Termes IGN] apprentissage profond [Termes IGN] approche participative [Termes IGN] classification dirigée [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] couleur (variable spectrale) [Termes IGN] données d'entrainement (apprentissage automatique) [Termes IGN] étiquette [Termes IGN] image multibande [Termes IGN] OpenStreetMap [Termes IGN] pixel [Termes IGN] plateforme collaborative [Termes IGN] texture d'image [Termes IGN] Worldview Résumé : (auteur) In order to solve insufficient training data problem in remote sensing, a web platform was created so that registered users can generate labeled data for various classes in a dynamic structure. Users were asked to select representative pixel groups for the forest, hazelnut, shadow, soil, tea, and building classes with the polygon tool, and then assign a class label corresponding to each created polygon thanks to the help document displaying descriptive information regarding the locations, colors, textures and distributions of the classes in the image. Crowdsourcing was again used to test the accuracy of the tagged data produced by crowdsourcing. The created data set was overlaid with the original WV-2 image, and the correctness of the labels ​​of the polygons was once visually verified. Finally, the WV-2 image, consisting of 40 patches, was classified with CNN and an average of over 95% accuracy was achieved. Numéro de notice : A2022-702 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2021.1917006 Date de publication en ligne : 26/05/2021 En ligne : https://doi.org/10.1080/10106049.2021.1917006 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101561 [article]

Discontinuity interpretation and identification of potential rockfalls for high-steep slopes based on UAV nap-of-the-object photogrammetry / Wei Wang in Computers & geosciences, vol 166 (September 2022)  

Public [article]  inComputers & geosciences > vol 166 (September 2022) . - n° 105191 Titre : Discontinuity interpretation and identification of potential rockfalls for high-steep slopes based on UAV nap-of-the-object photogrammetry Type de document : Article/Communication Auteurs : Wei Wang ; Wenbo Zhao, Auteur ; Bo Chai, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 105191 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Photogrammétrie numérique [Termes IGN] Chine [Termes IGN] discontinuité [Termes IGN] éboulement [Termes IGN] extraction de données [Termes IGN] front rocheux [Termes IGN] image à haute résolution [Termes IGN] image captée par drone [Termes IGN] matrice [Termes IGN] pente [Termes IGN] photogrammétrie aérienne [Termes IGN] profondeur [Termes IGN] risque naturel [Termes IGN] semis de points [Termes IGN] texture d'image Résumé : (auteur) Discontinuity extraction and interpretation of fractured masses is of high importance when analyzing rock slope stability. Regarding high-steep slopes, which are areas that are difficult to reach, traditional methods to obtain discontinuities, such as the sample window method (SWM), are unlikely to be implemented, resulting in challenges for the identification of potential rockfalls. With the development of the unmanned ariel vehicle (UAV) technology, discontinuity extraction can overcome by noncontact photogrammetry. However, there is still a lack of comprehensive and practical solutions to fulfill rockfall identification from field investigation to in-door analysis. For this purpose, a practical case study was carried out in Wanzhou, Chongqing, China, where a 400 m vertical rock slope prone to rockfall was collected as a typical example. The centimeter-level 3D Textured Digital Outcrop Model (TDOM) and dense Point Cloud (PC) were established using high-resolution photos acquired by nap-of-the-object photogrammetry. The discontinuity of the fractured mass was interpreted by fully taking advantage of both 2D images (texture information-dominated) and 3D PCs (depth information-dominated). Furthermore, a new parameter rock cavity rate (RCR) and the corresponding semiautomatic extraction method based on point clouds are proposed. Subsequently, the possibility of various failure modes and their joint combinations were determined by kinematic analysis. Finally, the rock slope stability was determined using a matrix that considers the slope mass rating (SMR) value and the parameter RCR. The proposed process flow and relevant techniques in this study provide an operable and practical solution for further application regarding discontinuity interpretation and potential rockfall identification on high-steep slopes. Numéro de notice : A2022-655 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1016/j.cageo.2022.105191 Date de publication en ligne : 08/07/2022 En ligne : https://doi.org/10.1016/j.cageo.2022.105191 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101504 [article]

Effective CBIR based on hybrid image features and multilevel approach / D. Latha in Multimedia tools and applications, vol 81 n° 20 (August 2022)  

Public [article]  inMultimedia tools and applications > vol 81 n° 20 (August 2022) . - pp Titre : Effective CBIR based on hybrid image features and multilevel approach Type de document : Article/Communication Auteurs : D. Latha, Auteur ; A. Geetha, Auteur Année de publication : 2022 Article en page(s) : pp Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] base de données d'images [Termes IGN] écart type [Termes IGN] espace colorimétrique [Termes IGN] image en couleur [Termes IGN] image RVB [Termes IGN] matrice de co-occurrence [Termes IGN] motif binaire local [Termes IGN] niveau de gris (image) [Termes IGN] observation multiniveaux [Termes IGN] recherche d'image basée sur le contenu [Termes IGN] saturation de la couleur [Termes IGN] texture d'image [Termes IGN] transformation intensité-teinte-saturation Résumé : (auteur) Content based image retrieval (CBIR) process can retrieve images by matching its feature set values. The proposed novel CBIR methodology called Effective CBIR based on hybrid image features and multilevel approach (CBIR_LTP_GLCM) integrates the hybrid features such as color features and texture features, along with multilevel approach. The color features such as mean and standard deviation are adopted in the proposed method to represent the global color properties of an image. This method manipulates the color input-image by processing the Hue, Saturation and Value channels of the HSV color space. This novel work is enriched with the image feature derived from Local Ternary Pattern (LTP) in addition with GLCM. So, the proposed method CBIR_LTP_GLCM is potentially charged with meaningful modifications travelling with color image manipulation and extended image retrieval accuracy with the aid of multilevel approach. The proposed methodology is experimentally compared with the existing recent CBIR versions by using the standard database such as Corel-1 k, and a user contributed database named DB_VEG. Numéro de notice : A2022-291 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1007/s11042-022-12588-7 Date de publication en ligne : 30/03/2022 En ligne : https://doi.org/10.1007/s11042-022-12588-7 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100337 [article]

Discriminative information restoration and extraction for weakly supervised low-resolution fine-grained image recognition / Tiantian Yan in Pattern recognition, vol 127 (July 2022)  

Public [article]  inPattern recognition > vol 127 (July 2022) . - n° 108629 Titre : Discriminative information restoration and extraction for weakly supervised low-resolution fine-grained image recognition Type de document : Article/Communication Auteurs : Tiantian Yan, Auteur ; Jian Shi, Auteur ; Haojie Li, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 108629 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse discriminante [Termes IGN] arbre aléatoire minimum [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] extraction de données [Termes IGN] granularité d'image [Termes IGN] image à basse résolution [Termes IGN] image à haute résolution [Termes IGN] relation sémantique [Termes IGN] texture d'image Résumé : (auteur) The existing methods of fine-grained image recognition mainly devote to learning subtle yet discriminative features from the high-resolution input. However, their performance deteriorates significantly when they are used for low quality images because a lot of discriminative details of images are missing. We propose a discriminative information restoration and extraction network, termed as DRE-Net, to address the problem of low-resolution fine-grained image recognition, which has widespread application potential, such as shelf auditing and surveillance scenarios. DRE-Net is the first framework for weakly supervised low-resolution fine-grained image recognition and consists of two sub-networks: (1) fine-grained discriminative information restoration sub-network (FDR) and (2) recognition sub-network with the semantic relation distillation loss (SRD-loss). The first module utilizes the structural characteristic of minimum spanning tree (MST) to establish context information for each pixel by employing the spatial structures between each pixel and other pixels, which can help FDR focus on and restore the critical texture details. The second module employs the SRD-loss to calibrate recognition sub-network by transferring the correct relationships between every two pixels on the feature map. Meanwhile the SRD-loss can further prompt the FDR to recover reliable and accurate fine-grained details and guide the recognition sub-network to perceive the discriminative features from the correct relationships. Extensive experiments on three benchmark datasets and one retail product dataset demonstrate the effectiveness of our proposed framework. Numéro de notice : A2022-555 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1016/j.patcog.2022.108629 Date de publication en ligne : 06/03/2022 En ligne : https://doi.org/10.1016/j.patcog.2022.108629 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101168 [article]

GANmapper: geographical data translation / Abraham Noah Wu in International journal of geographical information science IJGIS, vol 36 n° 7 (juillet 2022)  

Permalink

A dual-generator translation network fusing texture and structure features for SAR and optical image matching / Han Nie in Remote sensing, Vol 14 n° 12 (June-2 2022)  

Permalink

Apprentissage profond pour l'imagerie SAR : du débruitage à l'interprétation de scène / Emanuele Dalsasso (2022)  

Permalink

Multigranularity multiclass-layer Markov random field model for semantic segmentation of remote sensing images / Chen Zheng in IEEE Transactions on geoscience and remote sensing, vol 59 n° 12 (December 2021)  

Permalink

Multi-objective CNN-based algorithm for SAR despeckling / Sergio Vitale in IEEE Transactions on geoscience and remote sensing, vol 59 n° 11 (November 2021)  

Permalink

Semi-automatic extraction of rural roads under the constraint of combined geometric and texture features / Hai Tan in ISPRS International journal of geo-information, vol 10 n° 11 (November 2021)  

Permalink

Superpixel-based regional-scale grassland community classification using genetic programming with Sentinel-1 SAR and Sentinel-2 multispectral images / Zhenjiang Wu in Remote sensing, vol 13 n° 20 (October-2 2021)  

Permalink

A feature based change detection approach using multi-scale orientation for multi-temporal SAR images / R. Vijaya Geetha in European journal of remote sensing, vol 54 sup 2 (2021)  

Permalink

Recognition of crevasses with high-resolution digital elevation models: Application of geomorphometric modeling and texture analysis / Olga T. Ishalina in Transactions in GIS, vol 25 n° 5 (October 2021)  

Permalink

Digital camera calibration for cultural heritage documentation: the case study of a mass digitization project of religious monuments in Cyprus / Evagoras Evagorou in European journal of remote sensing, vol 54 sup 1 (2021)  

Permalink