Centre de documentation
scientifique

Dépouillements

3D change detection – Approaches and applications / Rongjun Qin in ISPRS Journal of photogrammetry and remote sensing, vol 122 (December 2016)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 122 (December 2016) . - pp 41 – 56 Titre : 3D change detection – Approaches and applications Type de document : Article/Communication Auteurs : Rongjun Qin, Auteur ; Jiaojiao Tian, Auteur ; Peter Reinartz, Auteur Année de publication : 2016 Article en page(s) : pp 41 – 56 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] détection de changement [Termes IGN] données localisées 3D [Termes IGN] précision des données [Termes IGN] semis de points [Termes IGN] taxinomie [Termes IGN] voxel Résumé : (Auteur) Due to the unprecedented technology development of sensors, platforms and algorithms for 3D data acquisition and generation, 3D spaceborne, airborne and close-range data, in the form of image based, Light Detection and Ranging (LiDAR) based point clouds, Digital Elevation Models (DEM) and 3D city models, become more accessible than ever before. Change detection (CD) or time-series data analysis in 3D has gained great attention due to its capability of providing volumetric dynamics to facilitate more applications and provide more accurate results. The state-of-the-art CD reviews aim to provide a comprehensive synthesis and to simplify the taxonomy of the traditional remote sensing CD techniques, which mainly sit within the boundary of 2D image/spectrum analysis, largely ignoring the particularities of 3D aspects of the data. The inclusion of 3D data for change detection (termed 3D CD), not only provides a source with different modality for analysis, but also transcends the border of traditional top-view 2D pixel/object-based analysis to highly detailed, oblique view or voxel-based geometric analysis. This paper reviews the recent developments and applications of 3D CD using remote sensing and close-range data, in support of both academia and industry researchers who seek for solutions in detecting and analyzing 3D dynamics of various objects of interest. We first describe the general considerations of 3D CD problems in different processing stages and identify CD types based on the information used, being the geometric comparison and geometric-spectral analysis. We then summarize relevant works and practices in urban, environment, ecology and civil applications, etc. Given the broad spectrum of applications and different types of 3D data, we discuss important issues in 3D CD methods. Finally, we present concluding remarks in algorithmic aspects of 3D CD. Numéro de notice : A2016--020 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2016.09.013 En ligne : http://dx.doi.org/10.1016/j.isprsjprs.2016.09.013 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=83882 [article]

Examining view angle effects on leaf N estimation in wheat using field reflectance spectroscopy / Xiao Song in ISPRS Journal of photogrammetry and remote sensing, vol 122 (December 2016)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 122 (December 2016) . - pp 57 – 67 Titre : Examining view angle effects on leaf N estimation in wheat using field reflectance spectroscopy Type de document : Article/Communication Auteurs : Xiao Song, Auteur ; Wei Feng, Auteur ; Li He, Auteur ; et al., Auteur Année de publication : 2016 Article en page(s) : pp 57 – 67 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] angle de visée [Termes IGN] Canada [Termes IGN] Chine [Termes IGN] feuille (végétation) [Termes IGN] indice de végétation [Termes IGN] spectromètre imageur [Termes IGN] teneur en azote Résumé : (Auteur) Real-time, nondestructive monitoring of crop nitrogen (N) status is a critical factor for precision N management during wheat production. Over a 3-year period, we analyzed different wheat cultivars grown under different experimental conditions in China and Canada and studied the effects of viewing angle on the relationships between various vegetation indices (VIs) and leaf nitrogen concentration (LNC) using hyperspectral data from 11 field experiments. The objective was to improve the prediction accuracy by minimizing the effects of viewing angle on LNC estimation to construct a novel vegetation index (VI) for use under different experimental conditions. We examined the stability of previously reported optimum VIs obtained from 13 traditional indices for estimating LNC at 13 viewing zenith angles (VZAs) in the solar principal plane (SPP). Backscattering direction showed better index performance than forward scattering direction. Red-edge VIs including modified normalized difference vegetation index (mND705), ratio index within the red edge region (RI-1dB) and normalized difference red edge index (NDRE) were highly correlated with LNC, as confirmed by high R2 determination coefficients. However, these common VIs tended to saturation, as the relationships strongly depended on experimental conditions. To overcome the influence of VZA on VIs, the chlorophyll- and LNC-sensitive NDRE index was divided by the floating-position water band index (FWBI) to generate the integrated narrow-band vegetation index. The highest correlation between the novel NDRE/FWBI parameter and LNC (R2 = 0.852) occurred at −10°, while the lowest correlation (R2 = 0.745) occurred at 60°. NDRE/FWBI was more highly correlated with LNC than existing commonly used VIs at an identical viewing zenith angle. Upon further analysis of angle combinations, our novel VI exhibited the best performance, with the best prediction accuracy at 0° to −20° (R2 = 0.838, RMSE = 0.360) and relatively good accuracy at 0° to −30° (R2 = 0.835, RMSE = 0.366). As it is possible to monitor plant N status over a wide range of angles using portable spectrometers, viewing angles of as much as 0° to −30° are common. Consequently, we developed a united model across angles of 0° to −30° to reduce the effects of viewing angle on LNC prediction in wheat. The proposed combined NDRE/FWBI parameter, designated the wide-angle-adaptability nitrogen index (WANI), is superior for estimating LNC in wheat on a regional scale in China and Canada. Numéro de notice : A2016--021 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2016.10.002 En ligne : http://dx.doi.org/10.1016/j.isprsjprs.2016.10.002 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=83884 [article]

Extracting building patterns with multilevel graph partition and building grouping / Shihong Du in ISPRS Journal of photogrammetry and remote sensing, vol 122 (December 2016)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 122 (December 2016) . - pp 81 – 96 Titre : Extracting building patterns with multilevel graph partition and building grouping Type de document : Article/Communication Auteurs : Shihong Du, Auteur ; Liqun Luo, Auteur ; Kai Cao, Auteur ; Mi Shu, Auteur Année de publication : 2016 Article en page(s) : pp 81 – 96 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Photogrammétrie numérique [Termes IGN] extraction automatique [Termes IGN] figure géométrique [Termes IGN] graphe [Termes IGN] partition des données [Termes IGN] paysage urbain [Termes IGN] reconstruction 2D du bâti Résumé : (Auteur) Building patterns are crucial for urban landscape evaluation, social analyses and multiscale spatial data automatic production. Although many studies have been conducted, there is still lack of satisfying results due to the incomplete typology of building patterns and the ineffective extraction methods. This study aims at providing a typology with four types of building patterns (e.g., collinear patterns, curvilinear patterns, parallel and perpendicular groups, and grid patterns) and presenting four integrated strategies for extracting these patterns effectively and efficiently. First, the multilevel graph partition method is utilized to generate globally optimal building clusters considering area, shape and visual distance similarities. In this step, the weights of similarity measurements are automatically estimated using Relief-F algorithm instead of manual selection, thus building clusters with high quality can be obtained. Second, based on the clusters produced in the first step, the extraction strategies group the buildings from each cluster into patterns according to the criteria of proximity, continuity and directionality. The proposed methods are tested using three datasets. The experimental results indicate that the proposed methods can produce satisfying results, and demonstrate that the F-Histogram model is better than the two widely used models (i.e., centroid model and the Voronoi graph) to represent relative directions for building patterns extraction. Numéro de notice : A2016--022 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2016.10.001 En ligne : http://dx.doi.org/10.1016/j.isprsjprs.2016.10.001 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=83885 [article]

A robust background regression based score estimation algorithm for hyperspectral anomaly detection / Zhao Rui in ISPRS Journal of photogrammetry and remote sensing, vol 122 (December 2016)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 122 (December 2016) . - pp 126 – 144 Titre : A robust background regression based score estimation algorithm for hyperspectral anomaly detection Type de document : Article/Communication Auteurs : Zhao Rui, Auteur ; Bo Du, Auteur ; Liangpei Zhang, Auteur ; Lefei Zhang, Auteur Année de publication : 2016 Article en page(s) : pp 126 – 144 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] détection d'anomalie [Termes IGN] image hyperspectrale [Termes IGN] régression Résumé : (Auteur) Anomaly detection has become a hot topic in the hyperspectral image analysis and processing fields in recent years. The most important issue for hyperspectral anomaly detection is the background estimation and suppression. Unreasonable or non-robust background estimation usually leads to unsatisfactory anomaly detection results. Furthermore, the inherent nonlinearity of hyperspectral images may cover up the intrinsic data structure in the anomaly detection. In order to implement robust background estimation, as well as to explore the intrinsic data structure of the hyperspectral image, we propose a robust background regression based score estimation algorithm (RBRSE) for hyperspectral anomaly detection. The Robust Background Regression (RBR) is actually a label assignment procedure which segments the hyperspectral data into a robust background dataset and a potential anomaly dataset with an intersection boundary. In the RBR, a kernel expansion technique, which explores the nonlinear structure of the hyperspectral data in a reproducing kernel Hilbert space, is utilized to formulate the data as a density feature representation. A minimum squared loss relationship is constructed between the data density feature and the corresponding assigned labels of the hyperspectral data, to formulate the foundation of the regression. Furthermore, a manifold regularization term which explores the manifold smoothness of the hyperspectral data, and a maximization term of the robust background average density, which suppresses the bias caused by the potential anomalies, are jointly appended in the RBR procedure. After this, a paired-dataset based k-nn score estimation method is undertaken on the robust background and potential anomaly datasets, to implement the detection output. The experimental results show that RBRSE achieves superior ROC curves, AUC values, and background-anomaly separation than some of the other state-of-the-art anomaly detection methods, and is easy to implement in practice. Numéro de notice : A2016--023 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2016.10.006 En ligne : http://dx.doi.org/10.1016/j.isprsjprs.2016.10.006 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=83886 [article]

MRF-based segmentation and unsupervised classification for building and road detection in peri-urban areas of high-resolution satellite images / Ilias Grinias in ISPRS Journal of photogrammetry and remote sensing, vol 122 (December 2016)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 122 (December 2016) . - pp 145 - 166 Titre : MRF-based segmentation and unsupervised classification for building and road detection in peri-urban areas of high-resolution satellite images Type de document : Article/Communication Auteurs : Ilias Grinias, Auteur ; Costas Panagiotakis, Auteur ; Georgios Tziritas, Auteur Année de publication : 2016 Article en page(s) : pp 145 - 166 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Photogrammétrie numérique [Termes IGN] analyse de données [Termes IGN] classification non dirigée [Termes IGN] classification par forêts d'arbres décisionnels [Termes IGN] classification par maximum de vraisemblance [Termes IGN] discrétisation [Termes IGN] données vectorielles [Termes IGN] image satellite [Termes IGN] réseau routier [Termes IGN] segmentation d'image Résumé : (Auteur) We present in this article a new method on unsupervised semantic parsing and structure recognition in peri-urban areas using satellite images. The automatic “building” and “road” detection is based on regions extracted by an unsupervised segmentation method. We propose a novel segmentation algorithm based on a Markov random field model and we give an extensive data analysis for determining relevant features for the classification problem. The novelty of the segmentation algorithm lies on the class-driven vector data quantization and clustering and the estimation of the likelihoods given the resulting clusters. We have evaluated the reachability of a good classification rate using the Random Forest method. We found that, with a limited number of features, among them some new defined in this article, we can obtain good classification performance. Our main contribution lies again on the data analysis and the estimation of likelihoods. Finally, we propose a new method for completing the road network exploiting its connectivity, and the local and global properties of the road network. Numéro de notice : A2016--024 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2016.10.010 En ligne : http://dx.doi.org/10.1016/j.isprsjprs.2016.10.010 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=83887 [article]