Centre dedocumentation
scientifique

Improved depth estimation for occlusion scenes using a light-field camera / Changkun Yang in Photogrammetric Engineering & Remote Sensing, PERS, vol 86 n° 7 (July 2020)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 86 n° 7 (July 2020) . - pp 443-456 Titre : Improved depth estimation for occlusion scenes using a light-field camera Type de document : Article/Communication Auteurs : Changkun Yang, Auteur ; Zhaoqin Liu, Auteur ; Kaichang Di, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 443-456 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes descripteurs IGN] approche pixel [Termes descripteurs IGN] chambre de prise de vue numérique [Termes descripteurs IGN] détection de partie cachée [Termes descripteurs IGN] disparité [Termes descripteurs IGN] effet de profondeur cinétique [Termes descripteurs IGN] lentille [Termes descripteurs IGN] méthode de centrage [Termes descripteurs IGN] rayonnement lumineux [Termes descripteurs IGN] reconstruction 3D Résumé : (Auteur) With the development of light-field imaging technology, depth estimation using light-field cameras has become a hot topic in recent years. Even through many algorithms have achieved good performance for depth estimation using light-field cameras, removing the influence of occlusion, especially multi-occlusion, is still a challenging task. The photo-consistency assumption does not hold in the presence of occlusions, which makes most depth estimation of light-field imaging unreliable. In this article, a novel method to handle complex occlusion in depth estimation of light-field imaging is proposed. The method can effectively identify occluded pixels using a refocusing algorithm, accurately select unoccluded views using the adaptive unoccluded-view identification algorithm, and then improve the depth estimation by computing the cost volumes in the unoccluded views. Experimental results demonstrate the advantages of our proposed algorithm compared with conventional state-of-the art algorithms on both synthetic and real light-field data sets. Numéro de notice : A2020-383 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.14358/PERS.86.7.443 date de publication en ligne : 01/07/2020 En ligne : https://doi.org/10.14358/PERS.86.7.443 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95430 [article]

Improved algorithms for the measurement of total precipitable water and cloud liquid water from SARAL microwave radiometer observations / Rajput Neha Mangalsinh in Marine geodesy, vol 42 n° 4 (July 2019)  

Public [article]  inMarine geodesy > vol 42 n° 4 (July 2019) . - pp 367 - 381 Titre : Improved algorithms for the measurement of total precipitable water and cloud liquid water from SARAL microwave radiometer observations Type de document : Article/Communication Auteurs : Rajput Neha Mangalsinh, Auteur ; Atul Kumar Varma, Auteur Année de publication : 2019 Article en page(s) : pp 367 - 381 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications [Termes descripteurs IGN] cryosphère [Termes descripteurs IGN] données altimétriques [Termes descripteurs IGN] hauteurs de mer [Termes descripteurs IGN] image GPM [Termes descripteurs IGN] image SSMIS [Termes descripteurs IGN] image TRMM-MI [Termes descripteurs IGN] nuage [Termes descripteurs IGN] précipitation [Termes descripteurs IGN] radiomètre à hyperfréquence [Termes descripteurs IGN] température de luminance [Termes descripteurs IGN] vapeur d'eau Résumé : (auteur) SARAL carried onboard a radar altimeter that provides very precise measurements of the sea surface height (SSH). Like other altimetric missions, SARAL carries a passive microwave radiometer (PMR) for wet tropospheric correction to SSH. In the present study, new algorithms are developed for the retrieval of cloud liquid water (CLW) and total precipitable water vapor (TPW) over the global oceans from PMR measurements of the brightness temperatures. A radiative transfer and genetic algorithm based retrieval scheme is proposed for the estimation of CLW and TPW from SARAL PMR. The comparisons of CLW from PMR with independent measurements from GPM-GMI and SSMIS within and outside ±40° latitudes show correlation (R) of 0.86 and 0.83, bias of 0.7 and −3.61 mg/cm2, and root mean square error (RMSE) of 8.42 and 8.07 mg/cm2, respectively. Similarly, TPW from PMR with GPM-GMI and SSMIS show R of 0.99 and 0.98, bias of −0.04 and −0.03 g/cm2 and RMSE of 0.17 and 0.17 g/cm2, respectively. The retrieval accuracy of CLW and TPW from the new algorithms is compared with these parameters provided in the SARAL geophysical data records as finished products, which showed substantial improvement in the quality of the parameters from the new algorithm. Numéro de notice : A2019-282 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/01490419.2019.1624662 date de publication en ligne : 12/06/2019 En ligne : https://doi.org/10.1080/01490419.2019.1624662 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93116 [article]

Evaluating metrics derived from Landsat 8 OLI imagery to map crop cover / Rei Sonobe in Geocarto international, vol 34 n° 8 ([15/06/2019])  

Public [article]  inGeocarto international > vol 34 n° 8 [15/06/2019] . - pp 839 - 855 Titre : Evaluating metrics derived from Landsat 8 OLI imagery to map crop cover Type de document : Article/Communication Auteurs : Rei Sonobe, Auteur ; Yuki Yamaya, Auteur ; Hiroshi Tani, Auteur ; Xiufeng Wang, Auteur ; et al., Auteur Année de publication : 2019 Article en page(s) : pp 839 - 855 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes descripteurs IGN] carte d'occupation du sol [Termes descripteurs IGN] classification et arbre de régression [Termes descripteurs IGN] classification par forêts aléatoires [Termes descripteurs IGN] image Landsat-8 [Termes descripteurs IGN] image Landsat-OLI [Termes descripteurs IGN] rayonnement lumineux [Termes descripteurs IGN] rayonnement proche infrarouge [Termes descripteurs IGN] réflectance végétale [Termes descripteurs IGN] signature spectrale [Termes descripteurs IGN] surface cultivée Résumé : (auteur) Developing techniques are required to generate agricultural land cover maps to monitor agricultural fields. Landsat 8 Operational Land Imager (OLI) offers reflectance data over the visible to shortwave-infrared range. OLI offers several advantages, such as adequate spatial and spectral resolution, and 16 day repeat coverage, furthermore, spectral indices derived from Landsat 8 OLI possess great potential for evaluating the status of vegetation. Additionally, classification algorithms are essential for generating accurate maps. Recently, multi-Grained Cascade Forest, which is also called deep forest, was proposed, and it was shown to give highly competitive performance for classification. However, the ability of this algorithm to generate crop maps with satellite data had not yet been evaluated. In this study, the reflectance at 7 bands and 57 spectral indices calculated from Landsat 8 OLI data were evaluated for its potential for crop type identification. Numéro de notice : A2019-514 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2018.1425739 date de publication en ligne : 19/01/2018 En ligne : https://doi.org/10.1080/10106049.2018.1425739 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93823 [article]

Improving the spatial bias correction algorithm in SMOS image reconstruction processor : validation of soil moisture retrievals with in situ data / Ali Khazaal in IEEE Transactions on geoscience and remote sensing, vol 57 n° 1 (January 2019)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 57 n° 1 (January 2019) . - pp 277 - 290 Titre : Improving the spatial bias correction algorithm in SMOS image reconstruction processor : validation of soil moisture retrievals with in situ data Type de document : Article/Communication Auteurs : Ali Khazaal, Auteur ; Philippe Richaume, Auteur ; François Cabot, Auteur ; Eric Anterrieu, Auteur ; Arnaud Mialon, Auteur ; Yann H. Kerr, Auteur Année de publication : 2019 Article en page(s) : pp 277 - 290 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications [Termes descripteurs IGN] correction d'image [Termes descripteurs IGN] erreur systématique [Termes descripteurs IGN] humidité du sol [Termes descripteurs IGN] image SMOS [Termes descripteurs IGN] résidu [Termes descripteurs IGN] télédétection en hyperfréquence [Termes descripteurs IGN] température de luminance Résumé : (Auteur) SMOS is a space mission led by the European Space Agency and designed to provide global maps of Soil Moisture and Ocean salinity, two important geophysical parameters for understanding the water cycle variations and climate change. The SMOS payload is a 2-D interferometer operating at L-band that consists of 69 elementary antennas located along a Y-shaped structure. Important spatial biases persist in the retrieved brightness temperature (BT) images mainly due to the phenomenon of aliasing inside the field of view of SMOS but also due to the Gibbs oscillations near land/ocean transitions. To minimize these biases, a differential image reconstruction algorithm is used in the operational processor that reduces the contrast of the image to be retrieved. To do that, the contribution of a constant artificial temperature map is removed from the measurements prior to reconstruction and then added back after the reconstruction. In this paper, we show that strong residual biases are still present in the retrieved images. To reduce them, we propose to improve the bias correction algorithm by using a more realistic artificial temperature scene based on separating the land and ocean regions and assigning a constant temperature over land and a Fresnel BT model over the ocean. The artificial scene is also improved by means of representing each pixel by its water fraction percentage to smooth the land/ocean transitions. The improved algorithm is validated over the ocean by comparing the retrieved temperatures to a forward geophysical model but also over land by comparing the retrieved soil moisture to in situ measurements. Numéro de notice : A2019-106 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2018.2853619 date de publication en ligne : 09/08/2018 En ligne : https://doi.org/10.1109/TGRS.2018.2853619 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=92412 [article]

Machine learning for image segmentation / Kaiwen Chang (2019)  

Public contenu dans HAL Hyper articles en ligne / Centre pour la Communication Scientifique Directe CCSD (2000)   Titre : Machine learning for image segmentation Type de document : Thèse/HDR Auteurs : Kaiwen Chang, Auteur ; Jesus Angulo lopez, Directeur de thèse ; Bruno Figliuzzi, Directeur de thèse Editeur : Paris : Université Paris Sciences et Lettres Année de publication : 2019 Importance : 155 p. Format : 21 x 30 cm Note générale : bibliographie Thèse de Doctorat de l'Université PSL, Spécialité : Morphologie Mathématique Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes descripteurs IGN] algorithme de superpixels [Termes descripteurs IGN] apprentissage automatique [Termes descripteurs IGN] base de données d'images [Termes descripteurs IGN] graphe [Termes descripteurs IGN] morphologie mathématique [Termes descripteurs IGN] optique géométrique [Termes descripteurs IGN] rayonnement lumineux [Termes descripteurs IGN] segmentation d'image [Termes descripteurs IGN] segmentation par graphes d'adjacence de régions [Termes descripteurs IGN] superpixel Résumé : (auteur) In this PhD thesis, our aim is to establish a general methodology for performing the segmentation of a dataset constituted of similar images with only a few annotated images as training examples. This methodology is directly intended to be applied to images gathered in Earth observation or materials science applications, for which there is not enough annotated examples to train state-of-the-art deep learning based segmentation algorithms. The proposed methodology starts from a superpixel partition of the image and gradually merges the initial regions until anactual segmentation is obtained. The two main contributions described in this PhD thesis are the development of a new superpixel algorithm which makes use of the Eikonal equation, and the development of a superpixel merging algorithm steaming from the adaption of the Eikonal equation to the setting of graphs. The superpixels merging approach makes use of a region adjacency graph computed from the superpixel partition. The edges are weighted by a dissimilarity measure learned by a machine learning algorithm from low-level cues computed on the superpixels. In terms of application, our approach to image segmentation is finally evaluated on the SWIMSEG dataset, a dataset which contains sky cloud images. On this dataset, using only a limited amount of images for training our algorithm, we were able to obtain segmentation results similar to the ones obtained with state-of-the-art algorithms. Note de contenu : 1- Introduction 2- Fast marching based superpixels 3- Hierarchical segmentation based on wavelet decomposition 4- Learning similarities between regions 5- Region merging 6- Application Conclusion and perspectives Numéro de notice : 25837 Thématique : IMAGERIE Nature : Thèse française Note de thèse : Thèse de Doctorat : Spécialité : Morphologie Mathématique : Paris : 2019 Organisme de stage : Centre de Morphologie Mathématique (Mines ParisTech) En ligne : http://www.theses.fr/2019PSLEM058 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95191

EMVS : Event-based Multi-View Stereo : 3D reconstruction with an event camera in real-time / Henri Rebecq in International journal of computer vision, vol 126 n° 12 (December 2018)  

Permalink

Visible + Near Infrared spectroscopy as taxonomic tool for identifying birch species / Mulualem Tigabu in Silva fennica, vol 52 n° 4 (September 2018)  

Permalink

Wind loads and competition for light sculpt trees into self-similar structures / Christophe Eloy in Nature communications, vol 8 (2017)  

Permalink

Forestry applications of UAVs in Europe: a review / Chiara Torresan in International Journal of Remote Sensing IJRS, vol 38 n° 8-10 (April 2017)  

Permalink

Télédétection pour l'observation des surfaces continentales, Volume 3. Observation des surfaces continentales par télédétection 1 / Nicolas Baghdadi (2017)

Permalink

Vegetation effects modeling in soil moisture retrieval using MSVI / Mina Moradizadeh in Photogrammetric Engineering & Remote Sensing, PERS, vol 82 n° 10 (October 2016)  

Permalink

Hybrid online mobile laser scanner calibration through image alignment by mutual information / Mourad Miled in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, III-1 (July 2016)  

Permalink

Nighttime-lights-derived fossil fuel carbon dioxide emission maps and their limitations / Naizhuo Zhao in Photogrammetric Engineering & Remote Sensing, PERS, vol 81 n° 12 (December 2015)

Permalink

An unsupervised urban change detection procedure by using luminance and saturation for multispectral remotely sensed images / Su Ye in Photogrammetric Engineering & Remote Sensing, PERS, vol 81 n° 8 (August 2015)

Permalink

A physics-based unmixing method to estimate subpixel temperatures on mixed pixels / Manuel Cubero-Castan in IEEE Transactions on geoscience and remote sensing, vol 53 n° 4 (April 2015)  

Permalink