Pub Date : 2011-07-12DOI: 10.1109/MULTI-TEMP.2011.6005062
Gustavo Bayma Siqueira Silva, M. P. Mello, Y. Shimabukuro, B. Rudorff, Daniel de Castro Victoria
Spectral-Temporal Analysis by Response Surface (STARS), which utilizes surface response to represent time series spectral-temporal behavior of pixels in satellite images, was used to map and discriminate savanna vegetation classes in portion of Cerrado biome of Mato Grosso State, Brazil, using MODIS data. STARS utilized 16 daily MODIS, cloud-free, images that were collected from September 1st 2008 to August 31st 2009. The Multi-Coefficient Image (MCI) resulted from the STARS was used as input attributes for the three tested classifiers: (i) ML — maximum likelihood; (ii) SVM — support vector machine; and (iii) NN — neural network. The results showed that the NN classifier presented higher kappa coefficient (0.58) and overall accuracy of 68.6%.
响应面光谱-时间分析(STARS)利用地表响应来表示卫星图像中像素的时间序列光谱-时间行为，利用MODIS数据对巴西马托格罗索州塞拉多生物群部分地区的稀树草原植被分类进行了制图和区分。STARS利用了从2008年9月1日到2009年8月31日收集的16张每日MODIS无云图像。由STARS产生的多系数图像(MCI)被用作三个测试分类器的输入属性:(i) ML -最大似然;支持向量机-支持向量机;(iii) NN -神经网络。结果表明，该分类器具有较高的kappa系数(0.58)和68.6%的总体准确率。
{"title":"Multitemporal classification of natural vegetation cover in Brazilian Cerrado","authors":"Gustavo Bayma Siqueira Silva, M. P. Mello, Y. Shimabukuro, B. Rudorff, Daniel de Castro Victoria","doi":"10.1109/MULTI-TEMP.2011.6005062","DOIUrl":"https://doi.org/10.1109/MULTI-TEMP.2011.6005062","url":null,"abstract":"Spectral-Temporal Analysis by Response Surface (STARS), which utilizes surface response to represent time series spectral-temporal behavior of pixels in satellite images, was used to map and discriminate savanna vegetation classes in portion of Cerrado biome of Mato Grosso State, Brazil, using MODIS data. STARS utilized 16 daily MODIS, cloud-free, images that were collected from September 1st 2008 to August 31st 2009. The Multi-Coefficient Image (MCI) resulted from the STARS was used as input attributes for the three tested classifiers: (i) ML — maximum likelihood; (ii) SVM — support vector machine; and (iii) NN — neural network. The results showed that the NN classifier presented higher kappa coefficient (0.58) and overall accuracy of 68.6%.","PeriodicalId":254778,"journal":{"name":"2011 6th International Workshop on the Analysis of Multi-temporal Remote Sensing Images (Multi-Temp)","volume":"171 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":"125192057","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.2011.6005076
Dea Doklestić, Ronald B. Smith
We test the hypothesis that strength of North American monsoon is influenced by surface processes such as evapotranspiration and sensible heat flux. In order to estimate evapotranspiration, three different satellite remote sensing-based methods are used: We use the Penman-Monteith approach developed by Cleugh et al. (2007) [2] and the revised Penman-Monteith approach developed by Mu et al. (2007) [5]. Furthermore, we use a simple latent heat residual method. All three methods use MODIS data as input datasets. The results obtained by the three methods are compared against flux tower measurements. Sensible heat flux is estimated using satellite measurements of land surface temperature and balloon sounding measurements of air temperature. Evapotranspiration shows a sharp peak during the monsoon season and this feature is captured by all three methods. This lends credence to the hypothesis that increased latent heat flux results in more monsoonal precipitation.
{"title":"Does evapotranspiration influence the strength of the North American monsoon? — Multitemporal satellite analysis of evapotranspiration and its effects","authors":"Dea Doklestić, Ronald B. Smith","doi":"10.1109/MULTI-TEMP.2011.6005076","DOIUrl":"https://doi.org/10.1109/MULTI-TEMP.2011.6005076","url":null,"abstract":"We test the hypothesis that strength of North American monsoon is influenced by surface processes such as evapotranspiration and sensible heat flux. In order to estimate evapotranspiration, three different satellite remote sensing-based methods are used: We use the Penman-Monteith approach developed by Cleugh et al. (2007) [2] and the revised Penman-Monteith approach developed by Mu et al. (2007) [5]. Furthermore, we use a simple latent heat residual method. All three methods use MODIS data as input datasets. The results obtained by the three methods are compared against flux tower measurements. Sensible heat flux is estimated using satellite measurements of land surface temperature and balloon sounding measurements of air temperature. Evapotranspiration shows a sharp peak during the monsoon season and this feature is captured by all three methods. This lends credence to the hypothesis that increased latent heat flux results in more monsoonal precipitation.","PeriodicalId":254778,"journal":{"name":"2011 6th International Workshop on the Analysis of Multi-temporal Remote Sensing Images (Multi-Temp)","volume":"1 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":"133179913","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.2011.6005070
B. Gokaraju, S. Durbha, R. King, N. Younan
In the present study we investigate the evolutionary feature subset selection using wrapper based genetic algorithms on Multi-temporal datasets. Feature subset selection helps in reducing the original feature dimension and also yields high performance. The evolutionary strategy attains a global optimum by reducing the computations iteratively and by traversing intelligently in the entire feature space. This method gave a very high performance improvement up to 0.97 kappa accuracy with a best reduced feature dimension for harmful algal bloom detection.
{"title":"Investigation of evolutionary feature subset selection in multi-temporal datasets for harmful algal bloom detection","authors":"B. Gokaraju, S. Durbha, R. King, N. Younan","doi":"10.1109/MULTI-TEMP.2011.6005070","DOIUrl":"https://doi.org/10.1109/MULTI-TEMP.2011.6005070","url":null,"abstract":"In the present study we investigate the evolutionary feature subset selection using wrapper based genetic algorithms on Multi-temporal datasets. Feature subset selection helps in reducing the original feature dimension and also yields high performance. The evolutionary strategy attains a global optimum by reducing the computations iteratively and by traversing intelligently in the entire feature space. This method gave a very high performance improvement up to 0.97 kappa accuracy with a best reduced feature dimension for harmful algal bloom detection.","PeriodicalId":254778,"journal":{"name":"2011 6th International Workshop on the Analysis of Multi-temporal Remote Sensing Images (Multi-Temp)","volume":"220 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":"121441274","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.2011.6005035
Gülsen Taskin Kaya, Hüseyin Kaya, O. Ersoy
Very high resolution (VHR) imagery exhibits high level of detailed information, but this may lead to the complicated urban structures in the spectral domain. In the context of change detection implementation, there are some issues when dealing with multitemporal change detection analysis in VHR imagery. One of the most important issues is to make a very accurate registration of two images taken at two different times. Due to some problems caused by scaling, shifting and rotation of the images, it is mostly impossible to register two images pixel-to-pixel exactly. Noise reduction, radiometric and geometric corrections are also the other factors affecting the quality of change detection analysis. All these issues may cause a great number of false alarms in addition to artifacts in change detection analysis with VHR images.
{"title":"Change detection in very high resolution imagery based on dynamic time warping: An implementation for Haiti earthquake damage assessment","authors":"Gülsen Taskin Kaya, Hüseyin Kaya, O. Ersoy","doi":"10.1109/MULTI-TEMP.2011.6005035","DOIUrl":"https://doi.org/10.1109/MULTI-TEMP.2011.6005035","url":null,"abstract":"Very high resolution (VHR) imagery exhibits high level of detailed information, but this may lead to the complicated urban structures in the spectral domain. In the context of change detection implementation, there are some issues when dealing with multitemporal change detection analysis in VHR imagery. One of the most important issues is to make a very accurate registration of two images taken at two different times. Due to some problems caused by scaling, shifting and rotation of the images, it is mostly impossible to register two images pixel-to-pixel exactly. Noise reduction, radiometric and geometric corrections are also the other factors affecting the quality of change detection analysis. All these issues may cause a great number of false alarms in addition to artifacts in change detection analysis with VHR images.","PeriodicalId":254778,"journal":{"name":"2011 6th International Workshop on the Analysis of Multi-temporal Remote Sensing Images (Multi-Temp)","volume":"33 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":"122829236","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.2011.6005087
S. Natali, A. Beccati, S. d'Elia, M. G. Veratelli, P. Campalani, M. Folegani, S. Mantovani
The development of new technologies and tools for as-much-as-possible automatic multi-temporal data analysis has been a goal for most of the institutions that aim at promoting the use of satellite data in different application domains. In the framework of the Support by Pre-classification to specific Applications Project, started in 2008, the European Space Agency has requested the development of a specific platform, named Multi-sensor Evolution Analysis (MEA), with the scope of demonstrating that long term satellite datasets coming from different sensors can be accessed and exploited in almost real time (few seconds) from a web application as user interface. The MEA system has been implemented based on 15 years of global (A)ATSR data (1 km resolution), together with 5 years of regional AVNIR-2 data (10 m resolution), with the final aim of permitting on-the-fly Land Use / Land Cover Change analysis. Moreover, a modified version of MEA has been set-up to permit the multi-temporal analysis of pollution maps coming from satellite observations and ground measurements, demonstrating the generality of the pursued approach. The present work aims at introducing the basis of the MEA system, describing the two implementations for land cover and pollution multi-temporal analysis, including external validation activities being performed for the first application by third parties.
{"title":"Multitemporal data management and exploitation infrastructure","authors":"S. Natali, A. Beccati, S. d'Elia, M. G. Veratelli, P. Campalani, M. Folegani, S. Mantovani","doi":"10.1109/MULTI-TEMP.2011.6005087","DOIUrl":"https://doi.org/10.1109/MULTI-TEMP.2011.6005087","url":null,"abstract":"The development of new technologies and tools for as-much-as-possible automatic multi-temporal data analysis has been a goal for most of the institutions that aim at promoting the use of satellite data in different application domains. In the framework of the Support by Pre-classification to specific Applications Project, started in 2008, the European Space Agency has requested the development of a specific platform, named Multi-sensor Evolution Analysis (MEA), with the scope of demonstrating that long term satellite datasets coming from different sensors can be accessed and exploited in almost real time (few seconds) from a web application as user interface. The MEA system has been implemented based on 15 years of global (A)ATSR data (1 km resolution), together with 5 years of regional AVNIR-2 data (10 m resolution), with the final aim of permitting on-the-fly Land Use / Land Cover Change analysis. Moreover, a modified version of MEA has been set-up to permit the multi-temporal analysis of pollution maps coming from satellite observations and ground measurements, demonstrating the generality of the pursued approach. The present work aims at introducing the basis of the MEA system, describing the two implementations for land cover and pollution multi-temporal analysis, including external validation activities being performed for the first application by third parties.","PeriodicalId":254778,"journal":{"name":"2011 6th International Workshop on the Analysis of Multi-temporal Remote Sensing Images (Multi-Temp)","volume":"62 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":"122150511","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.2011.6005073
Bontemps Sophie, Defourny Pierre, Van Bogaert Eric, Herold Martin, Kooistra Lammert, K. Vasileios, A. Olivier
Supported by the European Space Agency, the Climate Change Initiative land cover project focuses on the land cover in order to contribute to the corresponding Essential Climate Variable. Consultation mechanisms were established with the climate modelling community in order to identify its specific needs in terms of satellite-based global land cover products. Key findings were the needs for stable land cover data and a dynamic component in form of time-series and for consistency among the different datasets used as input to climate models. As response, an innovative global land cover mapping approach, based on multi-year earth observation datasets is proposed.
{"title":"Producing global land cover maps consistent over time to respond the needs of the climate modelling community","authors":"Bontemps Sophie, Defourny Pierre, Van Bogaert Eric, Herold Martin, Kooistra Lammert, K. Vasileios, A. Olivier","doi":"10.1109/MULTI-TEMP.2011.6005073","DOIUrl":"https://doi.org/10.1109/MULTI-TEMP.2011.6005073","url":null,"abstract":"Supported by the European Space Agency, the Climate Change Initiative land cover project focuses on the land cover in order to contribute to the corresponding Essential Climate Variable. Consultation mechanisms were established with the climate modelling community in order to identify its specific needs in terms of satellite-based global land cover products. Key findings were the needs for stable land cover data and a dynamic component in form of time-series and for consistency among the different datasets used as input to climate models. As response, an innovative global land cover mapping approach, based on multi-year earth observation datasets is proposed.","PeriodicalId":254778,"journal":{"name":"2011 6th International Workshop on the Analysis of Multi-temporal Remote Sensing Images (Multi-Temp)","volume":"120 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":"120959929","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.2011.6005037
G. Duveiller, F. Baret, P. Defourny
Optical remote sensing time series can be used to retrieve biophysical variables indicating crop status, such as leaf area index (LAI) or, more appropriately, green are index (GAI). If these variables are sensible to inter-annual seasonal variations, they can be of great value for crop growth monitoring, especially if they can be coupled with ecophysiological models using data assimilation. This study presents a multi-annual comparison between currently available global LAI products and crop specific GAI retrieved from MODIS 250 m imagery obtained by controlling pixel-target adequacy. This comparison is done over a region in Belgium with fragmented agricultural landscapes. Results indicate that, by assuring a crop specific information and smoothing information using thermal time, the GAI product has a higher sensitivity to the variability of growing conditions that may be encountered across the region, and thus out-performs the other LAI products.
{"title":"Monitoring crop growth inter-annual variability from MODIS time series: Performance comparison between crop specific green area index and current global leaf area index products","authors":"G. Duveiller, F. Baret, P. Defourny","doi":"10.1109/MULTI-TEMP.2011.6005037","DOIUrl":"https://doi.org/10.1109/MULTI-TEMP.2011.6005037","url":null,"abstract":"Optical remote sensing time series can be used to retrieve biophysical variables indicating crop status, such as leaf area index (LAI) or, more appropriately, green are index (GAI). If these variables are sensible to inter-annual seasonal variations, they can be of great value for crop growth monitoring, especially if they can be coupled with ecophysiological models using data assimilation. This study presents a multi-annual comparison between currently available global LAI products and crop specific GAI retrieved from MODIS 250 m imagery obtained by controlling pixel-target adequacy. This comparison is done over a region in Belgium with fragmented agricultural landscapes. Results indicate that, by assuring a crop specific information and smoothing information using thermal time, the GAI product has a higher sensitivity to the variability of growing conditions that may be encountered across the region, and thus out-performs the other LAI products.","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":"128292503","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.2011.6005060
L. Pasolli, C. Notarnicola, L. Bruzzone, M. Zebisch
This paper presents an improved algorithm for the retrieval of leaf area index (LAI) from satellite MODIS imagery specifically calibrated for Alpine meadows and pastures. The main features of the proposed algorithm, which is based on the inversion of a radiative transfer model, are: i) the improved spatial resolution (250 meters) with respect to the MODIS standard LAI product, and ii) the tuning of the retrieval system on the spectral characteristics of Alpine meadows and pastures. The analysis of a 10 year time series of LAI maps obtained with the proposed algorithm in comparison with both the MODIS standard LAI product and field measurements confirms the effectiveness of the technique presented for spatially and temporally mapping LAI in Alpine areas at regional scale.
{"title":"Spatial and temporal mapping of leaf area index in Alpine pastures and meadows with satellite MODIS imagery","authors":"L. Pasolli, C. Notarnicola, L. Bruzzone, M. Zebisch","doi":"10.1109/MULTI-TEMP.2011.6005060","DOIUrl":"https://doi.org/10.1109/MULTI-TEMP.2011.6005060","url":null,"abstract":"This paper presents an improved algorithm for the retrieval of leaf area index (LAI) from satellite MODIS imagery specifically calibrated for Alpine meadows and pastures. The main features of the proposed algorithm, which is based on the inversion of a radiative transfer model, are: i) the improved spatial resolution (250 meters) with respect to the MODIS standard LAI product, and ii) the tuning of the retrieval system on the spectral characteristics of Alpine meadows and pastures. The analysis of a 10 year time series of LAI maps obtained with the proposed algorithm in comparison with both the MODIS standard LAI product and field measurements confirms the effectiveness of the technique presented for spatially and temporally mapping LAI in Alpine areas at regional scale.","PeriodicalId":254778,"journal":{"name":"2011 6th International Workshop on the Analysis of Multi-temporal Remote Sensing Images (Multi-Temp)","volume":"51 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":"128890416","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.2011.6005045
E. Swinnen, S. Verbeiren, P. Henry, B. Deronde
This paper presents an on-going study on the impact of the orbital drift of VGT1 using concurrent images from VGT2, which is still orbiting within the mission specifications. The paper elaborates on the methodology and presents a few preliminary results.
{"title":"Assessing the impact of the orbital drift of SPOT-VGT1 by comparing with SPOT-VGT2 data","authors":"E. Swinnen, S. Verbeiren, P. Henry, B. Deronde","doi":"10.1109/MULTI-TEMP.2011.6005045","DOIUrl":"https://doi.org/10.1109/MULTI-TEMP.2011.6005045","url":null,"abstract":"This paper presents an on-going study on the impact of the orbital drift of VGT1 using concurrent images from VGT2, which is still orbiting within the mission specifications. The paper elaborates on the methodology and presents a few preliminary results.","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":"131077368","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.2011.6005032
D. Fernández-Prieto, M. Marconcini
In several applications the objective of change detection is actually limited to identify one (or few) specific “targeted” land-cover transition(s) affecting a certain area in a given time period. In such cases, ground-truth information is generally available for the only land-cover classes of interest at the two dates, which limits (or hinders) the possibility of successfully employing standard supervised approaches. Moreover, even unsupervised approaches cannot be effectively used, as they allow detecting all the areas experiencing any type of change, but not discriminating where specific transitions of interest occur. In this paper, we present a novel technique capable of addressing this challenging issue by using the only ground truth available for the targeted land-cover classes at the two dates. In particular, it jointly exploits the expectation-maximization algorithm and an iterative labeling strategy based on Markov random fields accounting for spatio-temporal correlation. Experimental results confirmed the effectiveness and the reliability of the proposed method.
{"title":"A novel approach to targeted change detection","authors":"D. Fernández-Prieto, M. Marconcini","doi":"10.1109/MULTI-TEMP.2011.6005032","DOIUrl":"https://doi.org/10.1109/MULTI-TEMP.2011.6005032","url":null,"abstract":"In several applications the objective of change detection is actually limited to identify one (or few) specific “targeted” land-cover transition(s) affecting a certain area in a given time period. In such cases, ground-truth information is generally available for the only land-cover classes of interest at the two dates, which limits (or hinders) the possibility of successfully employing standard supervised approaches. Moreover, even unsupervised approaches cannot be effectively used, as they allow detecting all the areas experiencing any type of change, but not discriminating where specific transitions of interest occur. In this paper, we present a novel technique capable of addressing this challenging issue by using the only ground truth available for the targeted land-cover classes at the two dates. In particular, it jointly exploits the expectation-maximization algorithm and an iterative labeling strategy based on Markov random fields accounting for spatio-temporal correlation. Experimental results confirmed the effectiveness and the reliability of the proposed method.","PeriodicalId":254778,"journal":{"name":"2011 6th International Workshop on the Analysis of Multi-temporal Remote Sensing Images (Multi-Temp)","volume":"359 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":"132800053","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：