Centre de documentation
scientifique

Dépouillements

Spectral Interference of Heavy Metal Contamination on Spectral Signals of Moisture Content for Heavy Metal Contaminated Soils / Haein Shin in IEEE Transactions on geoscience and remote sensing, vol 58 n° 4 (April 2020)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 58 n° 4 (April 2020) . - pp 2266 - 2275 Titre : Spectral Interference of Heavy Metal Contamination on Spectral Signals of Moisture Content for Heavy Metal Contaminated Soils Type de document : Article/Communication Auteurs : Haein Shin, Auteur ; Jaehyung Yu, Auteur ; Lei Wang, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 2266 - 2275 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] arsenic [Termes IGN] bande spectrale [Termes IGN] bruit blanc [Termes IGN] contamination [Termes IGN] cuivre [Termes IGN] dégradation du signal [Termes IGN] échantillonnage [Termes IGN] humidité du sol [Termes IGN] interférence [Termes IGN] métal lourd [Termes IGN] modèle de régression [Termes IGN] plomb [Termes IGN] pollution des sols [Termes IGN] signature spectrale Résumé : (auteur) This article examined the spectral interference by heavy metal on the spectral signal of moisture content of heavy metal contaminated soils. Soil samples were collected from an abandoned mine area, and the chemical analysis revealed extremely high contamination amount of copper (Cu), zinc (Zn), arsenic (As), cadmium (Cd), and lead (Pb). The mineralogical analysis showed that the spectral signature of the heavy metal contaminated soils was manifested by secondary minerals. Water content suppressed the spectral reflectance of the soil samples but increased the absorption depths. Although a regression model can predict moisture content using the magnitude of the water absorption feature, the accuracy was much lower when the heavy metal concentration was extremely high. It indicates that geochemical reactions between the heavy metal cation and iron oxide/clay minerals may have affected the spectral responses of the contaminated soils at the water absorption bands. Our model also showed that there was a shift of the absorption features of moisture content if the heavy metal contamination level went up. Unlike normal soils, the absorption features of clay minerals and ferric iron were not able to accurately predict moisture in highly contaminated soils. Given the fact that the spectral bands selected in this article were associated with water absorption, the findings from this article may only be useful to a drone-based low-altitude remote sensing of soil moisture content. Numéro de notice : A2020-193 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2019.2946297 Date de publication en ligne : 31/10/2019 En ligne : https://doi.org/10.1109/TGRS.2019.2946297 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94860 [article]

Multiscale Intensity Propagation to Remove Multiplicative Stripe Noise From Remote Sensing Images / Hao Cui in IEEE Transactions on geoscience and remote sensing, vol 58 n° 4 (April 2020)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 58 n° 4 (April 2020) . - pp 2308 - 2323 Titre : Multiscale Intensity Propagation to Remove Multiplicative Stripe Noise From Remote Sensing Images Type de document : Article/Communication Auteurs : Hao Cui, Auteur ; Peng Jia, Auteur ; Guo Zhang, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 2308 - 2323 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse des correspondances [Termes IGN] bande spectrale [Termes IGN] capteur à balayage [Termes IGN] correction d'image [Termes IGN] dégradation d'image [Termes IGN] délignage [Termes IGN] filtrage du bruit [Termes IGN] filtrage du rayonnement [Termes IGN] image hyperspectrale [Termes IGN] intensité lumineuse [Termes IGN] itération [Termes IGN] méthode robuste [Termes IGN] pollution acoustique Résumé : (auteur) Sensor instability, dark currents, and other factors often cause stripe noise corruption in hyperspectral remote sensing images and severely limit their application in practical purposes. Previous studies have proposed numerous destriping algorithms that have yielded impressive results. Although most destriping algorithms are based on the premise of additive noise, a few studies have focused directly on multiplicative stripe noise. This article fully analyzes the characteristics of the stripe noise of OHS-01 images and proposes a multiplicative stripe noise removal method. Specifically, stripe noise is tackled by performing radiometric normalization of different columns in the image. First, the relative gain coefficients of adjacent columns are separated based on prior knowledge. Second, the local relative intensity correspondence of the image columns are established by means of intensity propagation, intensity connection, and so on. Finally, the above-mentioned process is iterated in multiscale space, and the accumulated gain correction coefficient maps were used to correct the radiation of the original image. The results of extensive experiments on simulated and real remote sensing image data demonstrate that the proposed method can, in most cases, yield desirable results. In certain cases, the results are even better, visually, and quantitatively, than those obtained using classical algorithms. Moreover, the proposed method has high robustness and efficiency. Thus, it can conform to the requirements of engineering applications. Numéro de notice : A2020-194 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2019.2947599 Date de publication en ligne : 12/11/2019 En ligne : https://doi.org/10.1109/TGRS.2019.2947599 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94861 [article]

What, where, and how to transfer in SAR target recognition based on deep CNNs / Zhongling Huang in IEEE Transactions on geoscience and remote sensing, vol 58 n° 4 (April 2020)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 58 n° 4 (April 2020) . - pp 2324 - 2336 Titre : What, where, and how to transfer in SAR target recognition based on deep CNNs Type de document : Article/Communication Auteurs : Zhongling Huang, Auteur ; Zongxu Pan, Auteur ; Bin Lei, Auteur Année de publication : 2020 Article en page(s) : pp 2324 - 2336 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image mixte [Termes IGN] apprentissage profond [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] détection de cible [Termes IGN] données multisources [Termes IGN] image optique [Termes IGN] image radar moirée [Termes IGN] source de données [Termes IGN] transmission de données Résumé : (auteur) Deep convolutional neural networks (DCNNs) have attracted much attention in remote sensing recently. Compared with the large-scale annotated data set in natural images, the lack of labeled data in remote sensing becomes an obstacle to train a deep network very well, especially in synthetic aperture radar (SAR) image interpretation. Transfer learning provides an effective way to solve this problem by borrowing knowledge from the source task to the target task. In optical remote sensing application, a prevalent mechanism is to fine-tune on an existing model pretrained with a large-scale natural image data set, such as ImageNet. However, this scheme does not achieve satisfactory performance for SAR applications because of the prominent discrepancy between SAR and optical images. In this article, we attempt to discuss three issues that are seldom studied before in detail: 1) what network and source tasks are better to transfer to SAR targets; 2) in which layer are transferred features more generic to SAR targets; and 3) how to transfer effectively to SAR targets recognition. Based on the analysis, a transitive transfer method via multisource data with domain adaptation is proposed in this article to decrease the discrepancy between the source data and SAR targets. Several experiments are conducted on OpenSARShip. The results indicate that the universal conclusions about transfer learning in natural images cannot be completely applied to SAR targets, and the analysis of what and where to transfer in SAR target recognition is helpful to decide how to transfer more effectively. Numéro de notice : A2020-195 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2019.2947634 Date de publication en ligne : 20/11/2019 En ligne : https://doi.org/10.1109/TGRS.2019.2947634 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94863 [article]

Adaptive Statistical Superpixel Merging With Edge Penalty for PolSAR Image Segmentation / Deliang Xiang in IEEE Transactions on geoscience and remote sensing, vol 58 n° 4 (April 2020)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 58 n° 4 (April 2020) . - pp 2412 - 2429 Titre : Adaptive Statistical Superpixel Merging With Edge Penalty for PolSAR Image Segmentation Type de document : Article/Communication Auteurs : Deliang Xiang, Auteur ; Wei Wang, Auteur ; Tao Tang, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 2412 - 2429 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications [Termes IGN] chatoiement [Termes IGN] contour [Termes IGN] fusion de données [Termes IGN] image radar [Termes IGN] polarimétrie radar [Termes IGN] radar à antenne synthétique [Termes IGN] segmentation d'image [Termes IGN] superpixel [Termes IGN] vision par ordinateur Résumé : (auteur) This article proposes an efficient and adaptive statistical superpixel merging approach with edge penalty for polarimetric synthetic aperture radar (PolSAR) image segmentation. Based on the initial superpixel over-segmentation result obtained by our previously proposed adaptive polarimetric superpixel generation algorithm (Pol-ASLIC), this work achieves efficient and accurate PolSAR image segmentation by merging superpixels using the statistical region merging (SRM) framework. This article proposes to define a new dissimilarity measure between superpixels, which takes the edge penalty into consideration, leading to a reasonable and accurate merging order for superpixel pairs. With regard to the merging predicate of superpixels, a polarimetric homogeneity measurement (HoM) is used to define the merging threshold, making the merging predicate and merging threshold adaptive to the PolSAR image content. Experimental results on three airborne and one spaceborne PolSAR data sets demonstrate that the proposed approach can effectively improve the computation efficiency and segmentation accuracy in comparison with state-of-the-art merging-based methods for PolSAR data. More importantly, the proposed approach is free of parameters and easy to use. Numéro de notice : A2020-196 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2019.2949066 Date de publication en ligne : 14/11/2019 En ligne : https://doi.org/10.1109/TGRS.2019.2949066 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94864 [article]

Multichannel Pulse-Coupled Neural Network-Based Hyperspectral Image Visualization / Puhong Duan in IEEE Transactions on geoscience and remote sensing, vol 58 n° 4 (April 2020)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 58 n° 4 (April 2020) . - pp 2444 - 2456 Titre : Multichannel Pulse-Coupled Neural Network-Based Hyperspectral Image Visualization Type de document : Article/Communication Auteurs : Puhong Duan, Auteur ; Xudong Kang, Auteur ; Shutao Li, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 2444 - 2456 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse d'image numérique [Termes IGN] analyse multibande [Termes IGN] chromatopsie [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] cohérence des couleurs [Termes IGN] image en couleur composée [Termes IGN] image hyperspectrale [Termes IGN] image RVB [Termes IGN] synthèse trichromatique [Termes IGN] visualisation de données Résumé : (auteur) Hyperspectral Image (HSI) visualization, which aims at displaying as much material information of original images as possible on a trichromatic monitor with natural color, plays an important role in image interpretation and analysis. However, most of the HSI visualization methods only focus on presenting the detail information of a scene without providing natural colors and distinguishing land covers with similar colors. In order to address this problem, this article proposes a multichannel pulse-coupled neural network (MPCNN)-based HSI visualization method, which consists of the following steps. First, the MPCNN is proposed and explored to fuse the original HSI so as to obtain a fused band with rich spatial details. Then, a color mapping scheme is proposed to determine the weights of red, green, and blue (RGB) channels. Finally, the weighted RGB channels are stacked together for visualization. Experiments performed on four hyperspectral data sets demonstrate that the proposed method not only displays the HSI with nature colors but also improves the details in the image. The effectiveness of the proposed method is demonstrated in terms of both visual effect and objective indexes. Numéro de notice : A2020-197 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2019.2949427 Date de publication en ligne : 20/11/2019 En ligne : https://doi.org/10.1109/TGRS.2019.2949427 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94867 [article]

A Fusion Approach for Water Area Classification Using Visible, Near Infrared and Synthetic Aperture Radar for South Asian Conditions / Shahryar K. Ahmad in IEEE Transactions on geoscience and remote sensing, vol 58 n° 4 (April 2020)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 58 n° 4 (April 2020) . - pp 2471 - 2480 Titre : A Fusion Approach for Water Area Classification Using Visible, Near Infrared and Synthetic Aperture Radar for South Asian Conditions Type de document : Article/Communication Auteurs : Shahryar K. Ahmad, Auteur ; Faisal Hossain, Auteur ; Hisham Eldardiry, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 2471 - 2480 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] Bangladesh [Termes IGN] climat tropical [Termes IGN] eau de surface [Termes IGN] fusion d'images [Termes IGN] image Landsat-8 [Termes IGN] image PlanetScope [Termes IGN] image proche infrarouge [Termes IGN] image Sentinel-MSI [Termes IGN] image Sentinel-SAR [Termes IGN] plan d'eau [Termes IGN] radar à antenne synthétique [Termes IGN] reconnaissance de surface [Termes IGN] surveillance hydrologique [Termes IGN] télédétection spatiale [Termes IGN] zone humide Résumé : (auteur) Consistent estimation of water surface area from remote sensing remains challenging in regions such as South Asia with vegetation, mountainous topography, and persistent monsoonal cloud cover. High-resolution optical imagery, which is often used for global inundation mapping, is highly impacted by clouds, while synthetic aperture radar (SAR) imagery is not impacted by clouds and is affected by both topographic layover and vegetation. Here, we compare and contrast inundation extent measurements from visible (Landsat-8 and Sentinel-2) and SAR (Sentinel-1) imagery. Each data type (wavelength) has complementary strengths and weaknesses which were gauged separately over selected water bodies in Bangladesh. High-resolution cloud-free PlanetScope imagery at 3-m resolution was used as a reference to check the accuracy of each technique and data type. Next, the optical and radar images were fused for a rule-based water area classification algorithm to derive the optimal decision for the water mask. Results indicate that the fusion approach can improve the overall accuracy by up to 3.8%, 18.2%, and 8.3% during the wet season over using the individual products of Landsat8, Sentinel-1, and Sentinel-2, respectively, at three sites, while providing increased observational frequency. The fusion-derived products resulted in overall accuracy ranging from 85.8% to 98.7% and Kappa coefficient varying from 0.61 to 0.83. The proposed SAR-visible fusion technique has potential for improving satellite-based surface water monitoring and storage changes, especially for smaller water bodies in humid tropical climate of South Asia. Numéro de notice : A2020-198 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2019.2950705 Date de publication en ligne : 19/11/2019 En ligne : https://doi.org/10.1109/TGRS.2019.2950705 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94868 [article]

A Single Model CNN for Hyperspectral Image Denoising / Alessandro Maffei in IEEE Transactions on geoscience and remote sensing, vol 58 n° 4 (April 2020)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 58 n° 4 (April 2020) . - pp 2516 - 2529 Titre : A Single Model CNN for Hyperspectral Image Denoising Type de document : Article/Communication Auteurs : Alessandro Maffei, Auteur ; Juan Mario Haut, Auteur ; Mercedes Eugenia Paoletti, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 2516 - 2529 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage profond [Termes IGN] bande spectrale [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] filtrage d'information [Termes IGN] filtrage du bruit [Termes IGN] image hyperspectrale [Termes IGN] information géographique [Termes IGN] signature spectrale Résumé : (auteur) Denoising is a common preprocessing step prior to the analysis and interpretation of hyperspectral images (HSIs). However, the vast majority of methods typically adopted for HSI denoising exploit architectures originally developed for grayscale or RGB images, exhibiting limitations when processing high-dimensional HSI data cubes. In particular, traditional methods do not take into account the high spectral correlation between adjacent bands in HSIs, which leads to unsatisfactory denoising performance as the rich spectral information present in HSIs is not fully exploited. To overcome this limitation, this article considers deep learning models—such as convolutional neural networks (CNNs)—to perform spectral–spatial HSI denoising. The proposed model, called HSI single denoising CNN (HSI-SDeCNN), efficiently takes into consideration both the spatial and spectral information contained in HSIs. Experimental results on both synthetic and real data demonstrate that the proposed HSI-SDeCNN outperforms other state-of-the-art HSI denoising methods. Source code: https://github.com/mhaut/HSI-SDeCNN Numéro de notice : A2020-199 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2019.2952062 Date de publication en ligne : 26/11/2020 En ligne : https://doi.org/10.1109/TGRS.2019.2952062 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94869 [article]