Pub Date : 2011-07-12DOI: 10.1109/MULTI-TEMP.2011.6005064
B. Aiazzi, L. Alparone, S. Baronti, A. Garzelli, C. Zoppetti
Automated change analysis of multi-temporal SAR images is a challenging task due to the inherent noisiness of SAR imagery and the variability of the backscattering coefficient to the acquisition angle. Several methods have been proposed in the literature to improve the change detection performances with respect to the classical method based on the Log-Ratio operator. In this paper a pixel change feature is proposed and tested on true Cosmo-SkyMed detected images for damage assessment applications. The method does not require any despeckling pre-processing and is robust both to the acquisition noise and to possible variation of the acquisition angle in the two observations.
{"title":"A robust change detection feature for Cosmo-SkyMed detected SAR images","authors":"B. Aiazzi, L. Alparone, S. Baronti, A. Garzelli, C. Zoppetti","doi":"10.1109/MULTI-TEMP.2011.6005064","DOIUrl":"https://doi.org/10.1109/MULTI-TEMP.2011.6005064","url":null,"abstract":"Automated change analysis of multi-temporal SAR images is a challenging task due to the inherent noisiness of SAR imagery and the variability of the backscattering coefficient to the acquisition angle. Several methods have been proposed in the literature to improve the change detection performances with respect to the classical method based on the Log-Ratio operator. In this paper a pixel change feature is proposed and tested on true Cosmo-SkyMed detected images for damage assessment applications. The method does not require any despeckling pre-processing and is robust both to the acquisition noise and to possible variation of the acquisition angle in the two observations.","PeriodicalId":254778,"journal":{"name":"2011 6th International Workshop on the Analysis of Multi-temporal Remote Sensing Images (Multi-Temp)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129519988","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}
Pub Date : 2011-07-12DOI: 10.1109/MULTI-TEMP.2011.6005057
G. Castilla, A. Ram, J. Linke, G. McDermid
Monitoring landscape change is a requisite for sustainable development that should be achievable through the analysis of multitemporal satellite imagery. However, the development of effective methods to analyze these data in a consistent and reliable way is still a challenging issue that demands new approaches. Here we demonstrate the use of a recently developed change detection tool (the Landcover Change Mapper, LCM) for creating a multi-annual disturbance inventory spanning five years in a 10,000 km2 forested area in west-central Alberta, Canada.
{"title":"Semi-automated generation of a multi-temporal forest depletion layer with the Landcover Change Mapper (LCM)","authors":"G. Castilla, A. Ram, J. Linke, G. McDermid","doi":"10.1109/MULTI-TEMP.2011.6005057","DOIUrl":"https://doi.org/10.1109/MULTI-TEMP.2011.6005057","url":null,"abstract":"Monitoring landscape change is a requisite for sustainable development that should be achievable through the analysis of multitemporal satellite imagery. However, the development of effective methods to analyze these data in a consistent and reliable way is still a challenging issue that demands new approaches. Here we demonstrate the use of a recently developed change detection tool (the Landcover Change Mapper, LCM) for creating a multi-annual disturbance inventory spanning five years in a 10,000 km2 forested area in west-central Alberta, Canada.","PeriodicalId":254778,"journal":{"name":"2011 6th International Workshop on the Analysis of Multi-temporal Remote Sensing Images (Multi-Temp)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125636048","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}
Pub Date : 2011-07-12DOI: 10.1109/MULTI-TEMP.2011.6005079
G. Castilla, G. McDermid
Unfortunately, many GIS layers depicting transportation networks do not provide information on the construction year of each line segment in the network. This poses a serious problem when the GIS layer is used as input to historic analyses investigating the growth of the human footprint in an area still being developed, since there is no way of finding out what features already existed at each time lag of the period under analysis. Here we assess the possibility of backdating (a.k.a. retro-fitting) a road network to a reference year (by removing features in the GIS layer whose ground counterparts were not yet built then), using (1) a single Landsat image from the reference year (single date approach); and (2) the latter plus another from a more recent year (multi-date approach). We provide succinct information on the study area, input RS and GIS data, methods, and results; and conclude that full automation of this task is feasible.
{"title":"Automated backdating of transportation networks with Landsat imagery","authors":"G. Castilla, G. McDermid","doi":"10.1109/MULTI-TEMP.2011.6005079","DOIUrl":"https://doi.org/10.1109/MULTI-TEMP.2011.6005079","url":null,"abstract":"Unfortunately, many GIS layers depicting transportation networks do not provide information on the construction year of each line segment in the network. This poses a serious problem when the GIS layer is used as input to historic analyses investigating the growth of the human footprint in an area still being developed, since there is no way of finding out what features already existed at each time lag of the period under analysis. Here we assess the possibility of backdating (a.k.a. retro-fitting) a road network to a reference year (by removing features in the GIS layer whose ground counterparts were not yet built then), using (1) a single Landsat image from the reference year (single date approach); and (2) the latter plus another from a more recent year (multi-date approach). We provide succinct information on the study area, input RS and GIS data, methods, and results; and conclude that full automation of this task is feasible.","PeriodicalId":254778,"journal":{"name":"2011 6th International Workshop on the Analysis of Multi-temporal Remote Sensing Images (Multi-Temp)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131275308","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}
Pub Date : 2011-07-12DOI: 10.1109/MULTI-TEMP.2011.6005051
B. Aiazzi, L. Alparone, S. Baronti, R. Carlà, A. Garzelli, L. Santurri, M. Selva
Goal of this work is to investigate the effects of temporal misalignments between multispectral (MS) and panchromatic (Pan) observations when they are fused together to yield a pansharpened product. Conversely from the case in which spatial misalignments are present between MS and PAN images, for which the performances of component substitution (CS) fusion methods are recognized better than multiresolution analysis (MRA) schemes [1], both quantitative and qualitative results show that multitemporal misalignments are better compensated by MRA rather than by CS methods.
{"title":"Effects of multitemporal scene changes on pansharpening fusion","authors":"B. Aiazzi, L. Alparone, S. Baronti, R. Carlà, A. Garzelli, L. Santurri, M. Selva","doi":"10.1109/MULTI-TEMP.2011.6005051","DOIUrl":"https://doi.org/10.1109/MULTI-TEMP.2011.6005051","url":null,"abstract":"Goal of this work is to investigate the effects of temporal misalignments between multispectral (MS) and panchromatic (Pan) observations when they are fused together to yield a pansharpened product. Conversely from the case in which spatial misalignments are present between MS and PAN images, for which the performances of component substitution (CS) fusion methods are recognized better than multiresolution analysis (MRA) schemes [1], both quantitative and qualitative results show that multitemporal misalignments are better compensated by MRA rather than by CS methods.","PeriodicalId":254778,"journal":{"name":"2011 6th International Workshop on the Analysis of Multi-temporal Remote Sensing Images (Multi-Temp)","volume":"264 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114411035","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}
Pub Date : 2011-07-12DOI: 10.1109/MULTI-TEMP.2011.6005077
D. Stroppiana, M. Boschetti, P. Brivio, F. Nutini, E. Bartholomé
The hydrology of tropical forests play a key role in watershed processes such as soil erosion, streamflow and ground water recharge. However, tropical forests of Africa are least investigated due to the poor network for data acquisition. Earth Observations can fill this gap by providing consistent time series of data. We analyzed trends of rainfall, vegetation index and river water levels derived from satellite data for the Uele sub-basin and we pointed out that rainfall and river water levels are positively correlated only during the dry season when vegetation activities is low. The unexpected low correlation during the season of highest precipitations is due to the role of vegetation, which is characterized by a significant seasonality also in evergreen tropical forests. These results underline the importance of modeling the role of canopy in the interception and evapotranspiration of the available precipitation in order to provide reliable information on stream flow dynamics.
{"title":"Analysis of earth observation time series to investigate the relation between rainfall, vegetation dynamic and streamflow in the Uele' basin (Central African Republic)","authors":"D. Stroppiana, M. Boschetti, P. Brivio, F. Nutini, E. Bartholomé","doi":"10.1109/MULTI-TEMP.2011.6005077","DOIUrl":"https://doi.org/10.1109/MULTI-TEMP.2011.6005077","url":null,"abstract":"The hydrology of tropical forests play a key role in watershed processes such as soil erosion, streamflow and ground water recharge. However, tropical forests of Africa are least investigated due to the poor network for data acquisition. Earth Observations can fill this gap by providing consistent time series of data. We analyzed trends of rainfall, vegetation index and river water levels derived from satellite data for the Uele sub-basin and we pointed out that rainfall and river water levels are positively correlated only during the dry season when vegetation activities is low. The unexpected low correlation during the season of highest precipitations is due to the role of vegetation, which is characterized by a significant seasonality also in evergreen tropical forests. These results underline the importance of modeling the role of canopy in the interception and evapotranspiration of the available precipitation in order to provide reliable information on stream flow dynamics.","PeriodicalId":254778,"journal":{"name":"2011 6th International Workshop on the Analysis of Multi-temporal Remote Sensing Images (Multi-Temp)","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117314038","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}
Pub Date : 2011-07-12DOI: 10.1109/MULTI-TEMP.2011.6005069
Pauline Dusseux, L. Hubert‐Moy, R. Lecerf, X. Gong, T. Corpetti
In many regions, a decrease of grasslands and change in their management can be observed with agriculture intensification. Hence, the evaluation of grassland status and management in farming systems is a key-issue for sustainable agriculture. However, inventory of grassland surfaces in agricultural areas is very incomplete and the spatiotemporal distribution of their management is still largely unknown. The objective of this study is to identify mown and grazed grasslands from a time series of high spatial resolution images acquired in 2006 on an experimental watershed located in Brittany, France. The coupling of two radiative transfer models (PROSPECT+SAIL) has been applied to the remote sensing images to derive biophysical variables, in order to identify grassland management. Then, based on training samples, the classification of the temporal profiles extracted from the images was performed using three different methods with increasing automation: a knowledge-based classification, a k-nearest neighborhood and a decision tree procedure.
{"title":"Identification of grazed and mown grasslands using a time series of high-spatial-resolution remote sensing images","authors":"Pauline Dusseux, L. Hubert‐Moy, R. Lecerf, X. Gong, T. Corpetti","doi":"10.1109/MULTI-TEMP.2011.6005069","DOIUrl":"https://doi.org/10.1109/MULTI-TEMP.2011.6005069","url":null,"abstract":"In many regions, a decrease of grasslands and change in their management can be observed with agriculture intensification. Hence, the evaluation of grassland status and management in farming systems is a key-issue for sustainable agriculture. However, inventory of grassland surfaces in agricultural areas is very incomplete and the spatiotemporal distribution of their management is still largely unknown. The objective of this study is to identify mown and grazed grasslands from a time series of high spatial resolution images acquired in 2006 on an experimental watershed located in Brittany, France. The coupling of two radiative transfer models (PROSPECT+SAIL) has been applied to the remote sensing images to derive biophysical variables, in order to identify grassland management. Then, based on training samples, the classification of the temporal profiles extracted from the images was performed using three different methods with increasing automation: a knowledge-based classification, a k-nearest neighborhood and a decision tree procedure.","PeriodicalId":254778,"journal":{"name":"2011 6th International Workshop on the Analysis of Multi-temporal Remote Sensing Images (Multi-Temp)","volume":"160 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116182264","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}
Pub Date : 2011-07-12DOI: 10.1109/MULTI-TEMP.2011.6005099
M. Forster, A. Frick, B. Kleinschmit
The presented study aims at developing methods of a seasonal correction with the help of phenological observations of the German Weather Service (Deutscher Wetterdienst) and spectral field measurements for classifying grassland habitats. Therefore, spectral measurements were taken between 2007 and 2010 in a study heathland area of 60 km². These measurements were phenological corrected by a long-term time series. Each measurement date was corrected to a phonological date. With this information, the measurements could be used independently to a specific year. Finally, the measurements were combined in a phonological curve per class. This curve was applied to a time-series of RapidEye images to classify grassland habitats. First results indicate that a wide-range phonological curve is required to achieve results with an increasing accuracy.
{"title":"Utilization of spectral measurements and phenological observations to detect grassland-habitats with a RapidEye intra-annual time-series","authors":"M. Forster, A. Frick, B. Kleinschmit","doi":"10.1109/MULTI-TEMP.2011.6005099","DOIUrl":"https://doi.org/10.1109/MULTI-TEMP.2011.6005099","url":null,"abstract":"The presented study aims at developing methods of a seasonal correction with the help of phenological observations of the German Weather Service (Deutscher Wetterdienst) and spectral field measurements for classifying grassland habitats. Therefore, spectral measurements were taken between 2007 and 2010 in a study heathland area of 60 km². These measurements were phenological corrected by a long-term time series. Each measurement date was corrected to a phonological date. With this information, the measurements could be used independently to a specific year. Finally, the measurements were combined in a phonological curve per class. This curve was applied to a time-series of RapidEye images to classify grassland habitats. First results indicate that a wide-range phonological curve is required to achieve results with an increasing accuracy.","PeriodicalId":254778,"journal":{"name":"2011 6th International Workshop on the Analysis of Multi-temporal Remote Sensing Images (Multi-Temp)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128575101","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}
Pub Date : 2011-07-12DOI: 10.1109/MULTI-TEMP.2011.6005086
A. Gromek, M. Jenerowicz
Change detection is the process of identifying differences that have occurred in the terrain situation at different times. The Earth Observation (EO) data contribute to obtain the rapid and reliable change detection information making them particular and important source of information for Land Border Monitoring. Objective of the analysis is to provide consistent change detection method based on image processing techniques applied to the Synthetic Aperture Radar (SAR) images acquired over the same geographical area, but at two different time instances. The approach adopted in our work requires incorporation of results with the additional information derived from analysis based on mathematical morphology (MM) techniques and visual interpretation of multitemporal VHR optical satellite images.
{"title":"SAR imagery change detection method for Land Border Monitoring","authors":"A. Gromek, M. Jenerowicz","doi":"10.1109/MULTI-TEMP.2011.6005086","DOIUrl":"https://doi.org/10.1109/MULTI-TEMP.2011.6005086","url":null,"abstract":"Change detection is the process of identifying differences that have occurred in the terrain situation at different times. The Earth Observation (EO) data contribute to obtain the rapid and reliable change detection information making them particular and important source of information for Land Border Monitoring. Objective of the analysis is to provide consistent change detection method based on image processing techniques applied to the Synthetic Aperture Radar (SAR) images acquired over the same geographical area, but at two different time instances. The approach adopted in our work requires incorporation of results with the additional information derived from analysis based on mathematical morphology (MM) techniques and visual interpretation of multitemporal VHR optical satellite images.","PeriodicalId":254778,"journal":{"name":"2011 6th International Workshop on the Analysis of Multi-temporal Remote Sensing Images (Multi-Temp)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131600554","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}
Pub Date : 2011-07-12DOI: 10.1109/MULTI-TEMP.2011.6005047
B. Demir, F. Bovolo, L. Bruzzone
This paper presents a novel active-learning (AL) technique in the context of the cascade classification of multitemporal remote-sensing images for updating land-cover maps. The proposed AL technique is based on the selection of unlabeled samples that have maximum uncertainty on their labels assigned by cascade classification, and explicitly exploits temporal correlation between multitemporal images. Uncertainty of samples is assessed by conditional entropy that is defined on the basis of class-conditional independence assumption in time domain. The proposed conditional entropy based AL method for cascade classification technique is compared with a marginal entropy based AL technique adopted in the context of single-date image classification. Experimental results obtained on two multispectral and multitemporal data sets show the effectiveness of the proposed technique.
{"title":"Active-learning based cascade classification of multitemporal images for updating land-cover maps","authors":"B. Demir, F. Bovolo, L. Bruzzone","doi":"10.1109/MULTI-TEMP.2011.6005047","DOIUrl":"https://doi.org/10.1109/MULTI-TEMP.2011.6005047","url":null,"abstract":"This paper presents a novel active-learning (AL) technique in the context of the cascade classification of multitemporal remote-sensing images for updating land-cover maps. The proposed AL technique is based on the selection of unlabeled samples that have maximum uncertainty on their labels assigned by cascade classification, and explicitly exploits temporal correlation between multitemporal images. Uncertainty of samples is assessed by conditional entropy that is defined on the basis of class-conditional independence assumption in time domain. The proposed conditional entropy based AL method for cascade classification technique is compared with a marginal entropy based AL technique adopted in the context of single-date image classification. Experimental results obtained on two multispectral and multitemporal data sets show the effectiveness of the proposed technique.","PeriodicalId":254778,"journal":{"name":"2011 6th International Workshop on the Analysis of Multi-temporal Remote Sensing Images (Multi-Temp)","volume":"184 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127864747","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}
Pub Date : 2011-07-12DOI: 10.1109/MULTI-TEMP.2011.6005050
F. Petitjean, J. Inglada, Pierre Gancarskv
Satellite Image Time Series are becoming increasingly available and will continue to do so in the coming years thanks to the launch of space missions which aim at providing a coverage of the Earth every few days with high spatial resolution. In the case of optical imagery, it will be possible to produce land use and cover change maps with detailed nomenclatures. However, due to meteorological phenomena, such as clouds, these time series will become irregular in terms of temporal sampling and one will need to compare irregularly sensed time series. In this paper, we present an approach to satellite image time series analysis which is able to both deal with irregularly sampled series and to capture distorted behaviors. We present the Dynamic Time Warping from a theoretical point of view and illustrate its abilities for satellite image time series clustering.
{"title":"Clustering of satellite image time series under Time Warping","authors":"F. Petitjean, J. Inglada, Pierre Gancarskv","doi":"10.1109/MULTI-TEMP.2011.6005050","DOIUrl":"https://doi.org/10.1109/MULTI-TEMP.2011.6005050","url":null,"abstract":"Satellite Image Time Series are becoming increasingly available and will continue to do so in the coming years thanks to the launch of space missions which aim at providing a coverage of the Earth every few days with high spatial resolution. In the case of optical imagery, it will be possible to produce land use and cover change maps with detailed nomenclatures. However, due to meteorological phenomena, such as clouds, these time series will become irregular in terms of temporal sampling and one will need to compare irregularly sensed time series. In this paper, we present an approach to satellite image time series analysis which is able to both deal with irregularly sampled series and to capture distorted behaviors. We present the Dynamic Time Warping from a theoretical point of view and illustrate its abilities for satellite image time series clustering.","PeriodicalId":254778,"journal":{"name":"2011 6th International Workshop on the Analysis of Multi-temporal Remote Sensing Images (Multi-Temp)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128276637","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：