Pub Date : 2011-07-12DOI: 10.1109/MULTI-TEMP.2011.6005085
A. Masse, D. Ducrot, P. Marthon
As acquisition technology progresses, remote sensing data contains an ever increasing amount of information. Future projects in remote sensing will give high repeatability of acquisition like Venμs (CNES1) which may provide data every 2 days with a resolution of 5.3 meters on 12 bands (420nm–900nm) and Sentinel−2 (ESA) 13 bands, 10–60m resolution and 5 days. With such data, process automation appears crucial. For that purpose, we develop several algorithms to automate image processing (classification, segmentation, interpretation, etc.). In this paper, we present an algorithm of automatic analysis which selects the best dataset of dates maximizing classification quality indices. We create two indices to evaluate jointly accuracy and precision. We present tests performed on Formosat-2 images which are similar to Venμs and Sentinel−2 for temporal repetitiveness. These tests allow validating the presented process for temporal discrimination improvement.
{"title":"Tools for multitemporal analysis and classification of multisource satellite imagery","authors":"A. Masse, D. Ducrot, P. Marthon","doi":"10.1109/MULTI-TEMP.2011.6005085","DOIUrl":"https://doi.org/10.1109/MULTI-TEMP.2011.6005085","url":null,"abstract":"As acquisition technology progresses, remote sensing data contains an ever increasing amount of information. Future projects in remote sensing will give high repeatability of acquisition like Venμs (CNES1) which may provide data every 2 days with a resolution of 5.3 meters on 12 bands (420nm–900nm) and Sentinel−2 (ESA) 13 bands, 10–60m resolution and 5 days. With such data, process automation appears crucial. For that purpose, we develop several algorithms to automate image processing (classification, segmentation, interpretation, etc.). In this paper, we present an algorithm of automatic analysis which selects the best dataset of dates maximizing classification quality indices. We create two indices to evaluate jointly accuracy and precision. We present tests performed on Formosat-2 images which are similar to Venμs and Sentinel−2 for temporal repetitiveness. These tests allow validating the presented process for temporal discrimination improvement.","PeriodicalId":254778,"journal":{"name":"2011 6th International Workshop on the Analysis of Multi-temporal Remote Sensing Images (Multi-Temp)","volume":"7 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":"130724587","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.2011.6005088
R. d’Andrimont, G. Duveiller, P. Defourny
This paper presents some exploratory results of the FP-7 MOCCCASIN project that aims to MOnitor Crops in Continental Climates through ASsimilation of Satellite Information. MOCCCASIN is a collaborative project which focuses on improving the monitoring of winter-wheat and forecasting of winter-wheat yield in Russia by combining modelling techniques with satellite data assimilation [1]. In continental climate, winter wheat is particularly affected by low temperatures during the winter which determine whether rapid regrowth is possible in spring. A pre-requisite to use satellite earth observation to characterize the effect of winter kill on wheat is to determine if the multi-annual seasonal variability over the entire growing season can be grasped by remote sensing indicators. The results over an exploratory study site in Tula region for 5 years (2005–2009) demonstrate that it was possible to retrieve crop status indicators using an approach combining radiative transfer modeling and neural networks which could inform on where winter kill has stricken.
{"title":"Exploring the capacity to grasp multi-annual seasonal variability of winter wheat in Continental Climates with MODIS","authors":"R. d’Andrimont, G. Duveiller, P. Defourny","doi":"10.1109/MULTI-TEMP.2011.6005088","DOIUrl":"https://doi.org/10.1109/MULTI-TEMP.2011.6005088","url":null,"abstract":"This paper presents some exploratory results of the FP-7 MOCCCASIN project that aims to MOnitor Crops in Continental Climates through ASsimilation of Satellite Information. MOCCCASIN is a collaborative project which focuses on improving the monitoring of winter-wheat and forecasting of winter-wheat yield in Russia by combining modelling techniques with satellite data assimilation [1]. In continental climate, winter wheat is particularly affected by low temperatures during the winter which determine whether rapid regrowth is possible in spring. A pre-requisite to use satellite earth observation to characterize the effect of winter kill on wheat is to determine if the multi-annual seasonal variability over the entire growing season can be grasped by remote sensing indicators. The results over an exploratory study site in Tula region for 5 years (2005–2009) demonstrate that it was possible to retrieve crop status indicators using an approach combining radiative transfer modeling and neural networks which could inform on where winter kill has stricken.","PeriodicalId":254778,"journal":{"name":"2011 6th International Workshop on the Analysis of Multi-temporal Remote Sensing Images (Multi-Temp)","volume":"28 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":"114715937","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.2011.6005033
Salvatore Resta, N. Acito, M. Diani, G. Corsini, T. Opsahl, T. Haavardsholm
In this work we investigate the problem of detecting small changes in images acquired by airborne sensors, using direct georeferencing from gyro data and GPS position. We intend to avoid the time consuming step of image registration, exploiting direct georeferencing cascaded with a robust change detection strategy that can properly manage the typical registration errors given by onboard instrumentation. We investigate the effectiveness of this approach in the urban scenarios, where we are interested in detecting changes induced by small objects. The experimental analysis conducted on real hyperspectral data with very high spatial resolution highlights the effectiveness of the proposed approach, resulting in a consistent improvement of both the capability of detecting changes and of suppressing the background.
{"title":"Detection of small changes in airborne hyperspectral imagery: Experimental results over urban areas","authors":"Salvatore Resta, N. Acito, M. Diani, G. Corsini, T. Opsahl, T. Haavardsholm","doi":"10.1109/MULTI-TEMP.2011.6005033","DOIUrl":"https://doi.org/10.1109/MULTI-TEMP.2011.6005033","url":null,"abstract":"In this work we investigate the problem of detecting small changes in images acquired by airborne sensors, using direct georeferencing from gyro data and GPS position. We intend to avoid the time consuming step of image registration, exploiting direct georeferencing cascaded with a robust change detection strategy that can properly manage the typical registration errors given by onboard instrumentation. We investigate the effectiveness of this approach in the urban scenarios, where we are interested in detecting changes induced by small objects. The experimental analysis conducted on real hyperspectral data with very high spatial resolution highlights the effectiveness of the proposed approach, resulting in a consistent improvement of both the capability of detecting changes and of suppressing the background.","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":"129565383","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.2011.6005092
M. Tuohy
The Rakaia River and its tributaries have their source high in the Southern Alps but soon flow through broad valleys and then onto the Canterbury Plains. In these wide valleys the river channel is constantly changing as more rock is weathered and eroded from the mountains to maintain the supply of gravels to the system. Beginning with a Landsat TM image from 1989 a succession of satellite images (ASTER, SPOT and Worldview 2) has been analyzed to provide quantitative data that can be interpreted in terms of river dynamics. Within the permanent, well-defined high banks, the river channel, gravels and more persistent islands have been identified for different reaches in the Upper Rakaia. Changes in the distribution of the gravels within these various reaches have been related to the geomorphologic characteristics of the associated sub-catchments.
{"title":"Braided river dynamics determined using satellite imagery — Upper Rakaia River, Canterbury, New Zealand","authors":"M. Tuohy","doi":"10.1109/MULTI-TEMP.2011.6005092","DOIUrl":"https://doi.org/10.1109/MULTI-TEMP.2011.6005092","url":null,"abstract":"The Rakaia River and its tributaries have their source high in the Southern Alps but soon flow through broad valleys and then onto the Canterbury Plains. In these wide valleys the river channel is constantly changing as more rock is weathered and eroded from the mountains to maintain the supply of gravels to the system. Beginning with a Landsat TM image from 1989 a succession of satellite images (ASTER, SPOT and Worldview 2) has been analyzed to provide quantitative data that can be interpreted in terms of river dynamics. Within the permanent, well-defined high banks, the river channel, gravels and more persistent islands have been identified for different reaches in the Upper Rakaia. Changes in the distribution of the gravels within these various reaches have been related to the geomorphologic characteristics of the associated sub-catchments.","PeriodicalId":254778,"journal":{"name":"2011 6th International Workshop on the Analysis of Multi-temporal Remote Sensing Images (Multi-Temp)","volume":"19 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":"123757308","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.2011.6005096
J. Sobrino, Y. Julien, C. Mattar, R. Oltra-Carrió, J. Jiménez-Muñoz, G. Sòria, B. Franch, V. Hidalgo
Numerous datasets have been made available for the observation of our planet from space. The aim of this work is the observation of changes in vegetation, through the use of a recent remote sensing dataset, NASA's Long Term Data Record (LTDR). Several authors have pointed out that vegetation monitoring benefits of the simultaneous use of Normalized Difference Vegetation Index (NDVI) and land surface temperature (LST). Therefore, this work presents the procedure developed to monitor vegetation with the LTDR dataset, using both NDVI and LST parameters. This procedure includes data preprocessing (estimation of NDVI and LST, orbital drift correction, atmospherically contaminated data reconstruction), and analysis (Mann-Kendall statistical framework).
{"title":"Using NASA'S Long Term Data Record version 3 for the monitoring of land surface vegetation","authors":"J. Sobrino, Y. Julien, C. Mattar, R. Oltra-Carrió, J. Jiménez-Muñoz, G. Sòria, B. Franch, V. Hidalgo","doi":"10.1109/MULTI-TEMP.2011.6005096","DOIUrl":"https://doi.org/10.1109/MULTI-TEMP.2011.6005096","url":null,"abstract":"Numerous datasets have been made available for the observation of our planet from space. The aim of this work is the observation of changes in vegetation, through the use of a recent remote sensing dataset, NASA's Long Term Data Record (LTDR). Several authors have pointed out that vegetation monitoring benefits of the simultaneous use of Normalized Difference Vegetation Index (NDVI) and land surface temperature (LST). Therefore, this work presents the procedure developed to monitor vegetation with the LTDR dataset, using both NDVI and LST parameters. This procedure includes data preprocessing (estimation of NDVI and LST, orbital drift correction, atmospherically contaminated data reconstruction), and analysis (Mann-Kendall statistical framework).","PeriodicalId":254778,"journal":{"name":"2011 6th International Workshop on the Analysis of Multi-temporal Remote Sensing Images (Multi-Temp)","volume":"54 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":"125112459","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.2011.6005083
S. Ding, C. M. Rulinda, A. Stein, W. Bijker
The objective of this study is to explore the potential of using Markov chains to model the changes of vegetative drought classes. NOAA-AVHRR dekadal NDVI images and fuzzy functions are used to characterize the drought classes while capturing the gradual transition between them. The transition probabilities are estimated using the maximum class membership values at a location. The Markov transition probability matrix is then used to model the changes of vegetative drought classes at selected locations. Future vegetative drought classes are predicted using the estimated transition matrix, then compared with actual data. Twenty pixel locations clustered in four regions of the two main agricultural type in Kenya are selected to implement this approach. Half of the pixels are predicted correctly. 5 of them are predicted either one class higher or lower and 2 of them, two classes higher. We can conclude that Markov chains applied to fuzzy numbers have the potential to model the changes of of vegetative drought classes at a pixel, hence provide a benefit for early warning systems.
{"title":"NDVI time series and Markov chains to model the change of fuzzy vegetative drought classes","authors":"S. Ding, C. M. Rulinda, A. Stein, W. Bijker","doi":"10.1109/MULTI-TEMP.2011.6005083","DOIUrl":"https://doi.org/10.1109/MULTI-TEMP.2011.6005083","url":null,"abstract":"The objective of this study is to explore the potential of using Markov chains to model the changes of vegetative drought classes. NOAA-AVHRR dekadal NDVI images and fuzzy functions are used to characterize the drought classes while capturing the gradual transition between them. The transition probabilities are estimated using the maximum class membership values at a location. The Markov transition probability matrix is then used to model the changes of vegetative drought classes at selected locations. Future vegetative drought classes are predicted using the estimated transition matrix, then compared with actual data. Twenty pixel locations clustered in four regions of the two main agricultural type in Kenya are selected to implement this approach. Half of the pixels are predicted correctly. 5 of them are predicted either one class higher or lower and 2 of them, two classes higher. We can conclude that Markov chains applied to fuzzy numbers have the potential to model the changes of of vegetative drought classes at a pixel, hence provide a benefit for early warning systems.","PeriodicalId":254778,"journal":{"name":"2011 6th International Workshop on the Analysis of Multi-temporal Remote Sensing Images (Multi-Temp)","volume":"17 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":"121766868","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.2011.6005058
M. Villarreal, L. Norman, R. Webb, Diane E. Boyer, R. Turner
A significant amount of research conducted in the Sonoran Desert of North America has documented, both anecdotally and empirically, major vegetation changes over the past century due to human land use activities. However, many studies lack coincidental landscape-scale data characterizing the spatial and temporal manifestation of these changes. Vegetation changes in a binational (USA and Mexico) watershed were documented using a series of four land cover maps (1979–2009) derived from multispectral satellite imagery. Cover changes are compared to georeferenced, repeat oblique photographs dating from the late 19th century to present. Results indicate the expansion of grassland over the past 20 years following nearly a century of decline. Historical repeat photography documents early-mid 20th century mesquite invasions, but recent land cover data and rephotography demonstrate declines in xeroriparian/riparian mesquite communities in recent decades. These vegetation changes are variable over the landscape and influenced by topography and land management.
{"title":"Unravelling long-term vegetation change patterns in a binational watershed using multitemporal land cover data and historical photography","authors":"M. Villarreal, L. Norman, R. Webb, Diane E. Boyer, R. Turner","doi":"10.1109/MULTI-TEMP.2011.6005058","DOIUrl":"https://doi.org/10.1109/MULTI-TEMP.2011.6005058","url":null,"abstract":"A significant amount of research conducted in the Sonoran Desert of North America has documented, both anecdotally and empirically, major vegetation changes over the past century due to human land use activities. However, many studies lack coincidental landscape-scale data characterizing the spatial and temporal manifestation of these changes. Vegetation changes in a binational (USA and Mexico) watershed were documented using a series of four land cover maps (1979–2009) derived from multispectral satellite imagery. Cover changes are compared to georeferenced, repeat oblique photographs dating from the late 19th century to present. Results indicate the expansion of grassland over the past 20 years following nearly a century of decline. Historical repeat photography documents early-mid 20th century mesquite invasions, but recent land cover data and rephotography demonstrate declines in xeroriparian/riparian mesquite communities in recent decades. These vegetation changes are variable over the landscape and influenced by topography and land management.","PeriodicalId":254778,"journal":{"name":"2011 6th International Workshop on the Analysis of Multi-temporal Remote Sensing Images (Multi-Temp)","volume":"47 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":"132783909","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.2011.6005048
D. Frey, M. Butenuth
In this paper, a Dynamic Bayesian Network (DBN) is presented which assesses infrastructural objects concerning their functionality after natural disasters. The presented model combines multi-temporal observations from remote sensed images with simulations based on Digital Elevation Models (DEM). The inference in the DBN is established using the sum-product algorithm. The improved performance of DBN is shown compared to simpler pixel-based and topology-based graphical models. The paper shows results of the model assessing roads concerning their trafficability after flooding. In addition, an evaluation of the results with a reference is conducted.
{"title":"Multi-temporal damage assessment of linear infrastructural objects using Dynamic Bayesian Networks","authors":"D. Frey, M. Butenuth","doi":"10.1109/MULTI-TEMP.2011.6005048","DOIUrl":"https://doi.org/10.1109/MULTI-TEMP.2011.6005048","url":null,"abstract":"In this paper, a Dynamic Bayesian Network (DBN) is presented which assesses infrastructural objects concerning their functionality after natural disasters. The presented model combines multi-temporal observations from remote sensed images with simulations based on Digital Elevation Models (DEM). The inference in the DBN is established using the sum-product algorithm. The improved performance of DBN is shown compared to simpler pixel-based and topology-based graphical models. The paper shows results of the model assessing roads concerning their trafficability after flooding. In addition, an evaluation of the results with a reference is conducted.","PeriodicalId":254778,"journal":{"name":"2011 6th International Workshop on the Analysis of Multi-temporal Remote Sensing Images (Multi-Temp)","volume":"4 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":"134034336","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.2011.6005098
G. Roerink, M. Danes, O. G. Prieto, A. de Wit, A. V. van Vliet
Plant phenology is the study of the timing of periodic vegetation cycles and their connection to climate. Examples are the date of emergence of leaves and flowers or the date of leaf colouring and fall in deciduous trees. It is an independent measure on how ecosystems are responding to climate change and therefore experiencing renewed interest from the scientific research community. This paper describes a method to derive plant phenology indicators from time series of satellite images. The satellite images are Normalized Difference Vegetation Index (NDVI) images from the MODIS sensor, which encompass the European continent from 2000 onwards. The Harmonic Analysis of NDVI Time Series (HANTS) algorithm is used to process and analyse the time series of satellite images for each individual year. The resulting amplitude and phase values are translated into commonly understandable phenology indicators like start of growing season, which can be linked again to the biological definitions of plant phenology. The indicators are validated with field observations, recorded by a volunteer's network in the Netherlands and Germany. Conclusions are that the method produces consistant maps, which correlate well with the crop type. However, on average the remote sensing derived start of season is 14 days earlier than the observed values.
{"title":"Deriving plant phenology from remote sensing","authors":"G. Roerink, M. Danes, O. G. Prieto, A. de Wit, A. V. van Vliet","doi":"10.1109/MULTI-TEMP.2011.6005098","DOIUrl":"https://doi.org/10.1109/MULTI-TEMP.2011.6005098","url":null,"abstract":"Plant phenology is the study of the timing of periodic vegetation cycles and their connection to climate. Examples are the date of emergence of leaves and flowers or the date of leaf colouring and fall in deciduous trees. It is an independent measure on how ecosystems are responding to climate change and therefore experiencing renewed interest from the scientific research community. This paper describes a method to derive plant phenology indicators from time series of satellite images. The satellite images are Normalized Difference Vegetation Index (NDVI) images from the MODIS sensor, which encompass the European continent from 2000 onwards. The Harmonic Analysis of NDVI Time Series (HANTS) algorithm is used to process and analyse the time series of satellite images for each individual year. The resulting amplitude and phase values are translated into commonly understandable phenology indicators like start of growing season, which can be linked again to the biological definitions of plant phenology. The indicators are validated with field observations, recorded by a volunteer's network in the Netherlands and Germany. Conclusions are that the method produces consistant maps, which correlate well with the crop type. However, on average the remote sensing derived start of season is 14 days earlier than the observed values.","PeriodicalId":254778,"journal":{"name":"2011 6th International Workshop on the Analysis of Multi-temporal Remote Sensing Images (Multi-Temp)","volume":"25 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":"134315980","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.2011.6005038
C. Vancutsem, Jean-François Pekel, F. Kayitakire
Mapping cropland areas in a dynamic way is of great interest to successfully monitor agricultural areas and food security. Existing cropland masks are either too coarse or inaccurate or are limited in spatial coverage. This study aims at developing a method for dynamic mapping of cropland areas in Sub-Saharan Africa and at producing a multi-annual map of cropland extent at 250m using MODIS time series. The originality of the approach consists of including a dynamic and automatic stratification that allows tuning the classification parameters according to the inter-annual variability, and exploiting the local differences of spectral signatures between natural vegetation and crops during the green-up season. The accuracy of the product is assessed using a large sample of points interpreted on high resolution images and is compared to the accuracy of two existing cropland maps.
{"title":"Dynamic mapping of cropland areas in Sub-Saharan Africa using MODIS time series","authors":"C. Vancutsem, Jean-François Pekel, F. Kayitakire","doi":"10.1109/MULTI-TEMP.2011.6005038","DOIUrl":"https://doi.org/10.1109/MULTI-TEMP.2011.6005038","url":null,"abstract":"Mapping cropland areas in a dynamic way is of great interest to successfully monitor agricultural areas and food security. Existing cropland masks are either too coarse or inaccurate or are limited in spatial coverage. This study aims at developing a method for dynamic mapping of cropland areas in Sub-Saharan Africa and at producing a multi-annual map of cropland extent at 250m using MODIS time series. The originality of the approach consists of including a dynamic and automatic stratification that allows tuning the classification parameters according to the inter-annual variability, and exploiting the local differences of spectral signatures between natural vegetation and crops during the green-up season. The accuracy of the product is assessed using a large sample of points interpreted on high resolution images and is compared to the accuracy of two existing cropland maps.","PeriodicalId":254778,"journal":{"name":"2011 6th International Workshop on the Analysis of Multi-temporal Remote Sensing Images (Multi-Temp)","volume":"3 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":"133383206","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：