N. Champion, Emilie Le-Hir, S. Massera, Nicolas Bellaiche
{"title":"Automatic production of large-scale cloud-free orthomosaics from multitemporal satellite images","authors":"N. Champion, Emilie Le-Hir, S. Massera, Nicolas Bellaiche","doi":"10.1109/Multi-Temp.2017.8035214","DOIUrl":"https://doi.org/10.1109/Multi-Temp.2017.8035214","url":null,"abstract":"The main goal of this paper is to present the automatic pipeline designed at IGN-France to produce automatic large-scale cloud-free orthomosaics from multiple Spot 6/7 and Pléiades-HR satellite images. Our pipeline is composed of three steps: the radiometric harmonisation of satellite images, the automatic production of cloud masks and the stitching procedure. Our evaluation shows that our pipeline is capable to remove all clouds in a given scene and produce seamless orthomosaics.","PeriodicalId":259042,"journal":{"name":"2017 9th International Workshop on the Analysis of Multitemporal Remote Sensing Images (MultiTemp)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125209446","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
L. Bruzzone, F. Bovolo, C. Paris, Yady Tatiana Solano Correa, M. Zanetti, D. Fernández-Prieto
{"title":"Analysis of multitemporal Sentinel-2 images in the framework of the ESA Scientific Exploitation of Operational Missions","authors":"L. Bruzzone, F. Bovolo, C. Paris, Yady Tatiana Solano Correa, M. Zanetti, D. Fernández-Prieto","doi":"10.1109/Multi-Temp.2017.8035230","DOIUrl":"https://doi.org/10.1109/Multi-Temp.2017.8035230","url":null,"abstract":"This paper focuses on the scientific preliminary results of the project “S2-4Sci Land and Water - Multitemporal Analysis” funded by the European Space Agency (ESA) in the framework of the Scientific Exploitation of Operational Missions (SEOM). The aim of the project is the development of advanced multitemporal methods tailored on the specific properties of S2 images. The Sentinel-2 (S2) constellation has a huge potential for multitemporal analysis, due to the increased geometrical resolution, the novel spectral capabilities, a swath width of 290Km and the short revisit time. Three main applications and methodological areas are investigated: i) land-cover maps updating, ii) land-cover change detection, and iii) time series analysis. The proposed approaches are briefly described and preliminary results obtained on S2 images are discussed.","PeriodicalId":259042,"journal":{"name":"2017 9th International Workshop on the Analysis of Multitemporal Remote Sensing Images (MultiTemp)","volume":"176 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122103628","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Image representation alternatives for the analysis of satellite image time series","authors":"C. Dumitru, G. Schwarz, M. Datcu","doi":"10.1109/Multi-Temp.2017.8035211","DOIUrl":"https://doi.org/10.1109/Multi-Temp.2017.8035211","url":null,"abstract":"Current satellite images and image time series provide us with detailed information about the state of our planet as well as about our technical infrastructure and human activities. These images allow us to learn more about local, regional, and global phenomena and events, including - if interpreted properly - their causes and effects. In particular, image time series provide specific information about the dynamics of many processes implicitly contained in our images that need to be unearthed and investigated in detail. A traditional approach towards this aim is to start with pixel-level or patch-level data analysis for pixel-based image analysis, followed, if necessary, by subsequent feature extraction, clustering, classification and semantic labelling in order to generate various types of change maps on different representation levels. The classification step can be supported by interactive human intervention, or by automated machine learning strategies to identify higher level objects and their spatial and temporal relationships. The detected relationships can then be formulated as parameterized rule sets that create higher-level descriptor sets of the content of the selected images, and of additional external data such as thematic maps or typical dynamics descriptions. As an innovative extension of this traditional concept, we propose a highly automated approach for application-adapted image content exploration and knowledge extraction. The reason for this strategy is the additional amount and the precision of semantic relationships and details that we can assign to an image time series once we know the final application field and how to embed and access image content within knowledge graphs.","PeriodicalId":259042,"journal":{"name":"2017 9th International Workshop on the Analysis of Multitemporal Remote Sensing Images (MultiTemp)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128869938","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ahmed Alboabidallah, Johnson Martin, S. Lavender, Victor Abbott
{"title":"Using Landsat-8 and Sentinel-1 data for Above Ground Biomass assessment in the Tamar valley and Dartmoor","authors":"Ahmed Alboabidallah, Johnson Martin, S. Lavender, Victor Abbott","doi":"10.1109/Multi-Temp.2017.8035247","DOIUrl":"https://doi.org/10.1109/Multi-Temp.2017.8035247","url":null,"abstract":"The availability of a new generation of freely distributed Earth Observation (EO) data represents an opportunity for an affordable assessment of Above-Ground Biomass (AGB). The aim of this study is to design a new system that supports the two dimensional information provided by optical EO data with height differences derived from Sentinel-1 Radar data. The applied system combines pixel based data processing including deriving the normalized difference vegetation index (NDVI) and the NDVI multi-temporal range (NDVIR) from Landsat-8, and interferometry based Local Heights range (LHR) analysis from Sentinel-1 data, with an object based biomass assessment regression algorithm. An ANOVA analysis was applied to test the correlation strength between different data and field above-ground biomass, which showed an effective correlation of Landsat-8's band 4 (near infra-red), NDVI, and Sentinel-1 height. Multi-temporal NDVI range shows a lower significant and be excluded in the final regression. The results of AGB calculations show a significantly higher correlation with AGB, R2=0.80 compared to R2=0.71 when conventional systems applied to the same datasets.","PeriodicalId":259042,"journal":{"name":"2017 9th International Workshop on the Analysis of Multitemporal Remote Sensing Images (MultiTemp)","volume":"228 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133670530","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ewa Kukawska, S. Lewinski, M. Krupiński, Radoslaw Malinowski, A. Nowakowski, M. Rybicki, A. Kotarba
{"title":"Multitemporal Sentinel-2 data - remarks and observations","authors":"Ewa Kukawska, S. Lewinski, M. Krupiński, Radoslaw Malinowski, A. Nowakowski, M. Rybicki, A. Kotarba","doi":"10.1109/Multi-Temp.2017.8035212","DOIUrl":"https://doi.org/10.1109/Multi-Temp.2017.8035212","url":null,"abstract":"All the pre-processing algorithms are being improved constantly. The biggest challenge for the multitemporal analysis is to deal with errors caused directly by the chain of pre-processing of raw Sentinel-2 data to the level L1C - misregistration of pixels. Another problem to overcome while aggregating a series of classifications is the incorrect mask of clouds over artificial structures resulting from atmospheric correction performed with Sen2Cor software. Presented errors have direct influence on the overall accuracy of classifications performed in S2GLC project which are going to be implemented as a fully automatic process.","PeriodicalId":259042,"journal":{"name":"2017 9th International Workshop on the Analysis of Multitemporal Remote Sensing Images (MultiTemp)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128178799","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
J. Claessen, B. Martens, N. Verhoest, A. Molini, D. Miralles
{"title":"Global climatic drivers of vegetation based on wavelet analysis","authors":"J. Claessen, B. Martens, N. Verhoest, A. Molini, D. Miralles","doi":"10.1109/Multi-Temp.2017.8035207","DOIUrl":"https://doi.org/10.1109/Multi-Temp.2017.8035207","url":null,"abstract":"Cross-correlations provide a useful technique to analyse the similarities between vegetation indices and time series of climatic variables. However, correlation analyses are not sufficient to unveil changes in the co-variability of vegetation and climate as a function of time or for different temporal scales. Here, we introduce the use of wavelet coherence to evaluate the relationship between vegetation and its climate drivers, aiming to reveal how this relation has changed globally during the period 1984–2007. We diagnose vegetation through the use of Normalised Difference Vegetation Index (NDVI), Leaf Area Index (LAI) and Vegetation Optical Depth (VOD), while precipitation, air temperature and incoming radiation are considered as separate climatic drivers. Our results indicate that the wavelet coherence analysis can be used to disentangle the contrasting response of global ecosystems to their climatic environment. Our global maps of mean wavelet coherence, align with literature-reported areas of preferential water and energy stress. Based on these global maps, some areas of interest are selected for which a detailed spectral analysis of the time series is performed. Initial results indicate a clear discrepancy in the climatic response of different vegetation diagnostics over grasslands and woody regions.","PeriodicalId":259042,"journal":{"name":"2017 9th International Workshop on the Analysis of Multitemporal Remote Sensing Images (MultiTemp)","volume":"43 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120806282","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Unsupervised change detection of remote sensing images using superpixel segmentation and variational Gaussian mixture model","authors":"Gang Yang, Hengchao Li, Chiu-Yu Liu","doi":"10.1109/Multi-Temp.2017.8035197","DOIUrl":"https://doi.org/10.1109/Multi-Temp.2017.8035197","url":null,"abstract":"In this paper, we propose a novel unsupervised change detection approach for multitemporal remote sensing (RS) images based on superpixel segmentation and variational Gaussian mixture model (GMM). Firstly, the generated difference image is segmented into multiple superpixels using entropy rate superpixel (ERS) segmentation, which allows for the spatial contextual information to be taken into account in change detection. As such, we utilize the GMM to model the distribution of these superpixels, and assign each superpixel to one component using variational inference (VI) algorithm. Subsequently, according to mean square error (MSE) criterion, the resulting clusters are further grouped into two classes, respectively representing the changed class and unchanged class. As a consequence, we can achieve the change mask (CM) by assigning the superpixels (and its pixels) to the corresponding classes. Experimental results demonstrate the effectiveness of the proposed method with two real multitemporal RS images.","PeriodicalId":259042,"journal":{"name":"2017 9th International Workshop on the Analysis of Multitemporal Remote Sensing Images (MultiTemp)","volume":"277 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132096566","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Charlotte Pelletier, S. Valero, J. Inglada, G. Dedieu, N. Champion
{"title":"Filtering mislabeled data for improving time series classification","authors":"Charlotte Pelletier, S. Valero, J. Inglada, G. Dedieu, N. Champion","doi":"10.1109/Multi-Temp.2017.8035217","DOIUrl":"https://doi.org/10.1109/Multi-Temp.2017.8035217","url":null,"abstract":"The supervised classification of optical image time series allow the production of accurate land cover maps over large areas. However, the precision yielded by learning algorithms strongly depends on the quality of the reference data. The reference databases covering a large geographical area usually contain noisy data with an important number of mislabeled instances. These labeling errors result in longer training time, less accurate classifiers, and ultimately poorer results. To address this issue, we proposed a new iterative learning framework that removes mislabeled data from the training set. Specifically, a preliminary outlier rejection procedure based on the well-known Random Forest algorithm is proposed. The presented strategy is tested with the classification of Sentinel-2 image time series acquired on 2016 by using an out-of-date reference dataset collected on 2014.","PeriodicalId":259042,"journal":{"name":"2017 9th International Workshop on the Analysis of Multitemporal Remote Sensing Images (MultiTemp)","volume":"235 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132401804","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Lava emplacement mapping with SAR and optical satellite data","authors":"C. Bignami, S. Amici, M. Chini","doi":"10.1109/Multi-Temp.2017.8035218","DOIUrl":"https://doi.org/10.1109/Multi-Temp.2017.8035218","url":null,"abstract":"In this paper, we exploited satellite remote sensing data, acquired by SAR and optical sensors to map the lava emplacement during the eruption of Pico do Fogo volcano, in Cape Verde. The eruption took place in November 2014, and lasted for about 2 months. The event was imaged by several satellite missions. In particular, the ESA Sentinel-1A platform operated in that area, collecting several images with its novel acquisition mode, the so-called TOPSAR. SAR images have been processed to extract changes automatically and to infer the advancement of the lava emitted from November 23, 2014 to January 2017, by using an adaptive parametric thresholding and a hierarchical split based approach. This automatic procedure allowed mapping the evolution of the lava coverage. The results obtained thanks to this method were compared to the ones derived by using the optical images collected by Landsat-8 and EO-1 optical sensors.","PeriodicalId":259042,"journal":{"name":"2017 9th International Workshop on the Analysis of Multitemporal Remote Sensing Images (MultiTemp)","volume":"210 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113977857","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
J. M. Delgado, G. Sabatino, Roberto Cuccu, G. Rivolta, R. Pelich, P. Matgen, M. Chini, M. Marconcini
{"title":"Support for Multi-temporal and Multi-mission data processing: The ESA Research and Service Support","authors":"J. M. Delgado, G. Sabatino, Roberto Cuccu, G. Rivolta, R. Pelich, P. Matgen, M. Chini, M. Marconcini","doi":"10.1109/Multi-Temp.2017.8035241","DOIUrl":"https://doi.org/10.1109/Multi-Temp.2017.8035241","url":null,"abstract":"The ESA Research and Service Support (RSS) offers services to enable the Earth Observation (EO) data exploitation. RSS users are Principal Investigators, institutions and SMEs needing support to progress in their research and/or development activity. For these EO data users it is nowadays becoming more and more important the exploitation of data time series from historical ESA missions combined with the new Sentinel data. In order to provide support to the EO user community interested in the exploitation of long time series of data, the ESA RSS makes available ad-hoc support services that can be easily tailored on the user needs.","PeriodicalId":259042,"journal":{"name":"2017 9th International Workshop on the Analysis of Multitemporal Remote Sensing Images (MultiTemp)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124816505","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}