Pub Date : 2005-05-16DOI: 10.1109/AMTRSI.2005.1469845
M. C. García-Aguirre, R. Álvarez, R. Dirzo, A. Bernal
Changes in forest cover during a 16-year period were evaluated by means of a post-classification digital change detection process in a site to the southwest of the basin of Mexico City. Post-classification was preferred over other change detection methods since it offers the advantage of indicating the nature of changes, such as forest to shrubland, to cropland, or to other land uses. Overall classification accuracy ranges from 59.8 percent to 70.2 percent, and the multivariate measure of classification accuracy from 0.55 to 0.66 (kappa coefficient). The forest coverage maps obtained for 1973, 1985, and 1989 show an 18 percent deforestation in that period in that area. The derived annual deforestation rates, expressed as the percentage of remaining forest that is cleared per year, were 0.5 percent for the interval 1973-1985 and 3.4 percent for 1985-1989. A digital elevation model (DEM) and derived slope gradient, and slope aspect maps, were useful in the digital classification adjustment. The digital change detection performed herein only reported quantities of lost forest, but fieldwork observations indicate some regions of the remaining forest are already severely affected. Hence, further research on the type of changes, and general vigor of the forest or its degradation level, are required to evaluate the full impact of forest destruction in other areas, such as aquifer recharge.
{"title":"Post-classification digital change detection analysis of a temperate forest in the southwest basin of Mexico City, in a 16-year span","authors":"M. C. García-Aguirre, R. Álvarez, R. Dirzo, A. Bernal","doi":"10.1109/AMTRSI.2005.1469845","DOIUrl":"https://doi.org/10.1109/AMTRSI.2005.1469845","url":null,"abstract":"Changes in forest cover during a 16-year period were evaluated by means of a post-classification digital change detection process in a site to the southwest of the basin of Mexico City. Post-classification was preferred over other change detection methods since it offers the advantage of indicating the nature of changes, such as forest to shrubland, to cropland, or to other land uses. Overall classification accuracy ranges from 59.8 percent to 70.2 percent, and the multivariate measure of classification accuracy from 0.55 to 0.66 (kappa coefficient). The forest coverage maps obtained for 1973, 1985, and 1989 show an 18 percent deforestation in that period in that area. The derived annual deforestation rates, expressed as the percentage of remaining forest that is cleared per year, were 0.5 percent for the interval 1973-1985 and 3.4 percent for 1985-1989. A digital elevation model (DEM) and derived slope gradient, and slope aspect maps, were useful in the digital classification adjustment. The digital change detection performed herein only reported quantities of lost forest, but fieldwork observations indicate some regions of the remaining forest are already severely affected. Hence, further research on the type of changes, and general vigor of the forest or its degradation level, are required to evaluate the full impact of forest destruction in other areas, such as aquifer recharge.","PeriodicalId":302923,"journal":{"name":"International Workshop on the Analysis of Multi-Temporal Remote Sensing Images, 2005.","volume":"466 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115323583","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 : 2005-05-16DOI: 10.1109/AMTRSI.2005.1469880
R. Fraser
A procedure was developed to map large-scale forest disturbances at annual, continental scales using 1-km resolution data from a combination of satellite sensors and ancillary spatial data. The method, dubbed Change Screening Analysis Technique (Change-SAT), creates a probability of change map using multiple logistic regression and multi-temporal change metrics. The probability map is converted to binary change map and a decision tree model applied to attribute the most likely cause of change among burning, harvesting, flooding, or defoliation. This paper presents the results of applying Change-SAT over Canada for the period 1998-2004. A variety of interesting change examples is demonstrated, including insect defoliation, flooding related to a hydroelectric project, and widespread damage and die-off resulting from drought and a snow/wind storm. Although the method is generally not well suited to providing quantitative estimates of change, it identifies large disturbances that can be investigated in greater detail based on field visits or higher resolution imagery.
{"title":"An analysis of large-scale forest cover disturbance in Canada (1998-2004) based on multi-temporal coarse resolution data","authors":"R. Fraser","doi":"10.1109/AMTRSI.2005.1469880","DOIUrl":"https://doi.org/10.1109/AMTRSI.2005.1469880","url":null,"abstract":"A procedure was developed to map large-scale forest disturbances at annual, continental scales using 1-km resolution data from a combination of satellite sensors and ancillary spatial data. The method, dubbed Change Screening Analysis Technique (Change-SAT), creates a probability of change map using multiple logistic regression and multi-temporal change metrics. The probability map is converted to binary change map and a decision tree model applied to attribute the most likely cause of change among burning, harvesting, flooding, or defoliation. This paper presents the results of applying Change-SAT over Canada for the period 1998-2004. A variety of interesting change examples is demonstrated, including insect defoliation, flooding related to a hydroelectric project, and widespread damage and die-off resulting from drought and a snow/wind storm. Although the method is generally not well suited to providing quantitative estimates of change, it identifies large disturbances that can be investigated in greater detail based on field visits or higher resolution imagery.","PeriodicalId":302923,"journal":{"name":"International Workshop on the Analysis of Multi-Temporal Remote Sensing Images, 2005.","volume":"104 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121817211","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 : 2005-05-16DOI: 10.1109/AMTRSI.2005.1469878
D. Liu, M. Kelly, P. Gong
In this paper, we propose a spatial-temporally explicit algorithm to simultaneously classify multi-temporal images for land cover information. This algorithm has three steps: first, a machine learning algorithm Support Vector Machines (SVM), is trained with spectral observations to initialize the classification and estimate pixel-by-pixel class conditional probabilities for each individual image; second, Markov Random Fields (MRF) are used to model the spatial-temporal contextual prior probabilities of images; and finally, an iterative algorithm is used to update the classification based on the combination of the spectral class conditional probability and the spatial-temporal contextual prior probability. Increased accuracies from the contributions of spatial-temporal contextual evidence confirmed the importance of spatial-temporal modeling in multi-temporal remote sensing. In this paper, we propose a spatial-temporally explicit algorithm based on Markov Random Fields (MRF) and Support Vector Machines (SVM) to simultaneously classify multi-temporal images for land cover information. We first review SVM and MRF and present our proposed algorithm based on both of them. We then evaluate the algorithm using a real data set and compare the result with conventional non- contextual and partial-contextual (spatial only and temporal only) approaches.
{"title":"Classifying multi-temporal TM imagery using Markov random fields and support vector machines","authors":"D. Liu, M. Kelly, P. Gong","doi":"10.1109/AMTRSI.2005.1469878","DOIUrl":"https://doi.org/10.1109/AMTRSI.2005.1469878","url":null,"abstract":"In this paper, we propose a spatial-temporally explicit algorithm to simultaneously classify multi-temporal images for land cover information. This algorithm has three steps: first, a machine learning algorithm Support Vector Machines (SVM), is trained with spectral observations to initialize the classification and estimate pixel-by-pixel class conditional probabilities for each individual image; second, Markov Random Fields (MRF) are used to model the spatial-temporal contextual prior probabilities of images; and finally, an iterative algorithm is used to update the classification based on the combination of the spectral class conditional probability and the spatial-temporal contextual prior probability. Increased accuracies from the contributions of spatial-temporal contextual evidence confirmed the importance of spatial-temporal modeling in multi-temporal remote sensing. In this paper, we propose a spatial-temporally explicit algorithm based on Markov Random Fields (MRF) and Support Vector Machines (SVM) to simultaneously classify multi-temporal images for land cover information. We first review SVM and MRF and present our proposed algorithm based on both of them. We then evaluate the algorithm using a real data set and compare the result with conventional non- contextual and partial-contextual (spatial only and temporal only) approaches.","PeriodicalId":302923,"journal":{"name":"International Workshop on the Analysis of Multi-Temporal Remote Sensing Images, 2005.","volume":"135 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122852533","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 : 2005-05-16DOI: 10.1109/AMTRSI.2005.1469865
M. Beauchemin, K. Fung
An adaptive filter for the reduction of artifacts caused by misregistration in difference images is presented. The technique relies on an adaptive center weighted median filter. The central pixel weight of the filter varies spatially and is controlled through an estimate of local heterogeneity in the original images. The performance of the method is illustrated using a subset of multitemporal Landsat TM images.
{"title":"An adaptive filter for the reduction of artifacts caused by image misregistration","authors":"M. Beauchemin, K. Fung","doi":"10.1109/AMTRSI.2005.1469865","DOIUrl":"https://doi.org/10.1109/AMTRSI.2005.1469865","url":null,"abstract":"An adaptive filter for the reduction of artifacts caused by misregistration in difference images is presented. The technique relies on an adaptive center weighted median filter. The central pixel weight of the filter varies spatially and is controlled through an estimate of local heterogeneity in the original images. The performance of the method is illustrated using a subset of multitemporal Landsat TM images.","PeriodicalId":302923,"journal":{"name":"International Workshop on the Analysis of Multi-Temporal Remote Sensing Images, 2005.","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125958546","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 : 2005-05-16DOI: 10.1109/AMTRSI.2005.1469877
L. Aurdal, R. B. Huseby, L. Eikvil, R. Solberg, D. Vikhamar, A. Solberg
Ground cover classification based on a single satel- lite image can be challenging. The work reported here concerns the use of multitemporal satellite image data in order to alleviate this problem. We consider the problem of vegetation mapping and model the phenological evolution of the vegetation using a Hidden Markov Model (HMM). The different vegetation classes can be in one of a predefined set of states related to their phenological development. The characteristics of a given class are specified by the state transition probabilities as well as the probability of given satellite observations for that class and state. Classification of a specific pixel is thus reduced to selecting the class that has the highest probability of producing a given series of observations for that pixel. Compared to standard classification techniques such as maximum likelihood (ML) classification, the proposed scheme is flexible in that it derives its properties not only from image specific training data, but also from a model of the temporal behavior of the ground cover. It is shown to produce results that compare favorably to those obtained using ML classification on single satellite images, it also generalizes better than this approach. Obtaining good ground cover classifications based on a single satellite image can be challenging. The work reported here concerns the use of multitemporal satellite image data in order to alleviate this problem. We will consider an application of these methods to mapping of high mountain vegetation in Norway. The traditional mapping method based on manual field work is prohibitively expensive and alternatives are therefore sought. Vegetation classification based on satellite images is an interesting alternative, but the complexity of the vegetation ground cover is high and the use of multitemporal satellite image acquisitions is shown to improve the classifi- cation quality. This document is organized as follows: In the next section, we briefly recapitulate previous work related to multitemporal satellite image classification and phenological models. In section IV we discuss the HMM and how it can be used for classification. In section V we show results of the application of our algorithm, conclusions are given in section VI.
{"title":"Use of hidden Markov models and phenology for multitemporal satellite image classification: applications to mountain vegetation classification","authors":"L. Aurdal, R. B. Huseby, L. Eikvil, R. Solberg, D. Vikhamar, A. Solberg","doi":"10.1109/AMTRSI.2005.1469877","DOIUrl":"https://doi.org/10.1109/AMTRSI.2005.1469877","url":null,"abstract":"Ground cover classification based on a single satel- lite image can be challenging. The work reported here concerns the use of multitemporal satellite image data in order to alleviate this problem. We consider the problem of vegetation mapping and model the phenological evolution of the vegetation using a Hidden Markov Model (HMM). The different vegetation classes can be in one of a predefined set of states related to their phenological development. The characteristics of a given class are specified by the state transition probabilities as well as the probability of given satellite observations for that class and state. Classification of a specific pixel is thus reduced to selecting the class that has the highest probability of producing a given series of observations for that pixel. Compared to standard classification techniques such as maximum likelihood (ML) classification, the proposed scheme is flexible in that it derives its properties not only from image specific training data, but also from a model of the temporal behavior of the ground cover. It is shown to produce results that compare favorably to those obtained using ML classification on single satellite images, it also generalizes better than this approach. Obtaining good ground cover classifications based on a single satellite image can be challenging. The work reported here concerns the use of multitemporal satellite image data in order to alleviate this problem. We will consider an application of these methods to mapping of high mountain vegetation in Norway. The traditional mapping method based on manual field work is prohibitively expensive and alternatives are therefore sought. Vegetation classification based on satellite images is an interesting alternative, but the complexity of the vegetation ground cover is high and the use of multitemporal satellite image acquisitions is shown to improve the classifi- cation quality. This document is organized as follows: In the next section, we briefly recapitulate previous work related to multitemporal satellite image classification and phenological models. In section IV we discuss the HMM and how it can be used for classification. In section V we show results of the application of our algorithm, conclusions are given in section VI.","PeriodicalId":302923,"journal":{"name":"International Workshop on the Analysis of Multi-Temporal Remote Sensing Images, 2005.","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130778188","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 : 2005-05-16DOI: 10.1109/AMTRSI.2005.1469874
S. Burkhalter, N. Herold, C. Robinson
National Oceanic and Atmospheric Administration’s Coastal-Change Analysis Program (C-CAP) develops land cover data for the coastal zone of the U.S. An immediate objective for C-CAP is to expeditiously complete a national standard of land cover and land cover change data, to which additional eras of imagery will be used to track coastal changes through time. This paper highlights techniques for mapping and interpreting multiple eras of land cover within a study area. Recent era Landsat Enhanced Thematic Mapper and retrospective Landsat Multi Spectral Scanner imagery were analyzed in conjunction with the existing C-CAP land cover and corresponding Landsat Thematic Mapper imagery. Spectral differencing change analysis techniques identified areas that have changed from era to era. Spectral clustering for each era of Landsat imagery derived land cover labels for the areas of change. The change areas were then applied to the C-CAP land cover maps to produce a full land cover product for each era in the study. Trends highlighted in this study were related to increased development within existing urban boundaries, the spread of residential development in the suburbs, and loss of forest cover in rural areas. The data sources, interpretation techniques, and change analysis methodology described in this paper could be employed to produce land cover, and trend data products in most regions that have existing land cover data, and is envisioned as a component of a continued CCAP land cover change and trend mapping strategy.
美国国家海洋和大气管理局的海岸变化分析计划(C-CAP)开发了美国沿海地区的土地覆盖数据。C-CAP的直接目标是迅速完成土地覆盖和土地覆盖变化数据的国家标准，并使用额外的时代图像来跟踪沿海地区的变化。本文重点介绍了在研究区域内绘制和解释多个时期土地覆盖的技术。结合现有的C-CAP土地覆盖和相应的Landsat Thematic Mapper图像，分析了近年Landsat Enhanced Thematic Mapper图像和Landsat Multi Spectral Scanner回顾性图像。光谱差异变化分析技术确定了各个时代变化的区域。对每个时代的陆地卫星图像进行光谱聚类，得出变化区域的土地覆盖标签。然后将变化区域应用于C-CAP土地覆盖图，以生成研究中每个时代的完整土地覆盖产品。这项研究强调的趋势与现有城市边界内的发展增加、郊区住宅发展的蔓延以及农村地区森林覆盖的丧失有关。本文所描述的数据源、解释技术和变化分析方法可用于在大多数拥有现有土地覆盖数据的地区生产土地覆盖和趋势数据产品，并被设想为持续的CCAP土地覆盖变化和趋势制图策略的组成部分。
{"title":"The coastal change analysis program: mapping change and monitoring change trends in the coastal zone","authors":"S. Burkhalter, N. Herold, C. Robinson","doi":"10.1109/AMTRSI.2005.1469874","DOIUrl":"https://doi.org/10.1109/AMTRSI.2005.1469874","url":null,"abstract":"National Oceanic and Atmospheric Administration’s Coastal-Change Analysis Program (C-CAP) develops land cover data for the coastal zone of the U.S. An immediate objective for C-CAP is to expeditiously complete a national standard of land cover and land cover change data, to which additional eras of imagery will be used to track coastal changes through time. This paper highlights techniques for mapping and interpreting multiple eras of land cover within a study area. Recent era Landsat Enhanced Thematic Mapper and retrospective Landsat Multi Spectral Scanner imagery were analyzed in conjunction with the existing C-CAP land cover and corresponding Landsat Thematic Mapper imagery. Spectral differencing change analysis techniques identified areas that have changed from era to era. Spectral clustering for each era of Landsat imagery derived land cover labels for the areas of change. The change areas were then applied to the C-CAP land cover maps to produce a full land cover product for each era in the study. Trends highlighted in this study were related to increased development within existing urban boundaries, the spread of residential development in the suburbs, and loss of forest cover in rural areas. The data sources, interpretation techniques, and change analysis methodology described in this paper could be employed to produce land cover, and trend data products in most regions that have existing land cover data, and is envisioned as a component of a continued CCAP land cover change and trend mapping strategy.","PeriodicalId":302923,"journal":{"name":"International Workshop on the Analysis of Multi-Temporal Remote Sensing Images, 2005.","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130980612","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 : 2005-05-16DOI: 10.1109/AMTRSI.2005.1469858
A. Milne, I. Tapley
AIRSAR data were collected over the Tonle Sap Great Lake (TSGL) and Angkor regions of Cambodia during the NASA-Australia sponsored PACRIM2 Mission flown in September 2000 and analysed to produce a wetlands vegetation map and to determine flood extent in the TSGL. Archival JERS-1, L-band radar data for the period 1992-98 was available to assess changing environmental conditions brought about by the seasonal variation in water levels associated with flooding and that caused by human occupation and migration. Assessment of the changing environmental conditions was undertaken using three JERS-1 L-band images acquired in 1997. One image was obtained during the dry season in January when water levels associated with the TSGL were changing; one at the end of the dry season in April near to the period of low water in the lake, and the third image in August at the beginning of the next wet season.
{"title":"Change detection analysis in wetlands using JERS-1 radar data:tonle Sap Great Lake, Cambodia","authors":"A. Milne, I. Tapley","doi":"10.1109/AMTRSI.2005.1469858","DOIUrl":"https://doi.org/10.1109/AMTRSI.2005.1469858","url":null,"abstract":"AIRSAR data were collected over the Tonle Sap Great Lake (TSGL) and Angkor regions of Cambodia during the NASA-Australia sponsored PACRIM2 Mission flown in September 2000 and analysed to produce a wetlands vegetation map and to determine flood extent in the TSGL. Archival JERS-1, L-band radar data for the period 1992-98 was available to assess changing environmental conditions brought about by the seasonal variation in water levels associated with flooding and that caused by human occupation and migration. Assessment of the changing environmental conditions was undertaken using three JERS-1 L-band images acquired in 1997. One image was obtained during the dry season in January when water levels associated with the TSGL were changing; one at the end of the dry season in April near to the period of low water in the lake, and the third image in August at the beginning of the next wet season.","PeriodicalId":302923,"journal":{"name":"International Workshop on the Analysis of Multi-Temporal Remote Sensing Images, 2005.","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131328327","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 : 2005-05-16DOI: 10.1109/AMTRSI.2005.1469855
V. Vijayaraj, C. O'Hara, G. Olson, Sung-Jun Kim
Utilizing boundaries of segmented objects from a later temporal image to constrain the segmentation of an earlier co- registered image enables information about the spectral, textural, and other characteristic attributes of image segmented objects within the two images to be mined for differences that would be indicative of specific types of land use and land cover change. Significant changes in homogeneity, hue, and vegetation indices among others provide strong cues about changes that may have occurred within segmented objects. Depending on the nature of the initial segmentation and the degree to which it was designed to extract class features of a desired size, shape, color, and texture, the method described enables highly targeted change detection to be conducted to explore desired types of land use and land cover change. For a collection of precision orthorectified QuickBird bi-temporal images, segmentation results for later images are utilized to constrain the segmentation of earlier images. Object attributes of the segmented images that provide a feature space for defining class memberships functions are employed to determine areas that were changed
{"title":"Object and feature-space fusion and information mining for change detection","authors":"V. Vijayaraj, C. O'Hara, G. Olson, Sung-Jun Kim","doi":"10.1109/AMTRSI.2005.1469855","DOIUrl":"https://doi.org/10.1109/AMTRSI.2005.1469855","url":null,"abstract":"Utilizing boundaries of segmented objects from a later temporal image to constrain the segmentation of an earlier co- registered image enables information about the spectral, textural, and other characteristic attributes of image segmented objects within the two images to be mined for differences that would be indicative of specific types of land use and land cover change. Significant changes in homogeneity, hue, and vegetation indices among others provide strong cues about changes that may have occurred within segmented objects. Depending on the nature of the initial segmentation and the degree to which it was designed to extract class features of a desired size, shape, color, and texture, the method described enables highly targeted change detection to be conducted to explore desired types of land use and land cover change. For a collection of precision orthorectified QuickBird bi-temporal images, segmentation results for later images are utilized to constrain the segmentation of earlier images. Object attributes of the segmented images that provide a feature space for defining class memberships functions are employed to determine areas that were changed","PeriodicalId":302923,"journal":{"name":"International Workshop on the Analysis of Multi-Temporal Remote Sensing Images, 2005.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131202619","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 : 2005-05-16DOI: 10.1109/AMTRSI.2005.1469851
J. Tilton, W. Lawrence
NASA's Goddard Space Flight Center has developed a fast and effective method for generating image segmentation hierarchies. These segmentation hierarchies organize image data in a manner that makes their information content more accessible for analysis. Image segmentation enables analysis through the examination of image regions rather than individual image pixels. In addition, the segmentation hierarchy provides additional analysis clues through the tracing of the behavior of image region characteristics at several levels of segmentation detail. The potential for extracting the information content from imagery data based on segmentation hierarchies has not been fully explored for the benefit of the Earth and space science communities. This paper explores the potential of exploiting these segmentation hierarchies for the analysis of multi-date data sets, and for the particular application of change monitoring. A segmentation hierarchy is a set of several segmentations of the same image at different levels of detail in which the segmentations at coarser levels of detail can be produced from simple merges of regions at finer levels of detail. This is useful for applications that require different levels of image segmentation detail depending on the particular image objects segmented. A unique feature of a segmentation hierarchy that distinguishes it from most other multilevel representations is that the segment or region boundaries are maintained at the full image spatial resolution for all levels of the segmentation hierarchy.
{"title":"Monitoring change through hierarchical segmentation of remotely sensed image data","authors":"J. Tilton, W. Lawrence","doi":"10.1109/AMTRSI.2005.1469851","DOIUrl":"https://doi.org/10.1109/AMTRSI.2005.1469851","url":null,"abstract":"NASA's Goddard Space Flight Center has developed a fast and effective method for generating image segmentation hierarchies. These segmentation hierarchies organize image data in a manner that makes their information content more accessible for analysis. Image segmentation enables analysis through the examination of image regions rather than individual image pixels. In addition, the segmentation hierarchy provides additional analysis clues through the tracing of the behavior of image region characteristics at several levels of segmentation detail. The potential for extracting the information content from imagery data based on segmentation hierarchies has not been fully explored for the benefit of the Earth and space science communities. This paper explores the potential of exploiting these segmentation hierarchies for the analysis of multi-date data sets, and for the particular application of change monitoring. A segmentation hierarchy is a set of several segmentations of the same image at different levels of detail in which the segmentations at coarser levels of detail can be produced from simple merges of regions at finer levels of detail. This is useful for applications that require different levels of image segmentation detail depending on the particular image objects segmented. A unique feature of a segmentation hierarchy that distinguishes it from most other multilevel representations is that the segment or region boundaries are maintained at the full image spatial resolution for all levels of the segmentation hierarchy.","PeriodicalId":302923,"journal":{"name":"International Workshop on the Analysis of Multi-Temporal Remote Sensing Images, 2005.","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128083452","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 : 2005-05-16DOI: 10.1109/AMTRSI.2005.1469849
Antonio Plaza, J. L. Moigne, N. Netanyahu
With the recent explosion in the amount of remotely sensed imagery and the corresponding interest in temporal change detection and modeling, image registration has become increasingly important as a necessary first step in the integration of multi-temporal and multi-sensor data for applications such as the analysis of seasonal and annual global climate changes, as well as land use/cover changes. The task of image registration can be divided into two major components: (1) the extraction of control points or features from images; and (2) the search among the extracted features for the matching pairs that represent the same feature in the images to be matched. Manual control feature extraction can be subjective and extremely time consuming, and often results in few usable points. Automated feature extraction is a solution to this problem, where desired target features are invariant, and represent evenly distributed landmarks such as edges, corners and line intersections. In this paper, we develop a novel automated registration approach based on the following steps. First, a mathematical morphology (MM)-based method is used to obtain a scale-orientation morphological profile at each image pixel. Next, a spectral dissimilarity metric such as the spectral information divergence is applied for automated extraction of landmark chips, followed by an initial approximate matching. This initial condition is then refined using a hierarchical robust feature matching (RFM) procedure. Experimental results reveal that the proposed registration technique offers a robust solution in the presence of seasonal changes and other interfering factors.
{"title":"Automated image registration using morphological region of interest feature extraction","authors":"Antonio Plaza, J. L. Moigne, N. Netanyahu","doi":"10.1109/AMTRSI.2005.1469849","DOIUrl":"https://doi.org/10.1109/AMTRSI.2005.1469849","url":null,"abstract":"With the recent explosion in the amount of remotely sensed imagery and the corresponding interest in temporal change detection and modeling, image registration has become increasingly important as a necessary first step in the integration of multi-temporal and multi-sensor data for applications such as the analysis of seasonal and annual global climate changes, as well as land use/cover changes. The task of image registration can be divided into two major components: (1) the extraction of control points or features from images; and (2) the search among the extracted features for the matching pairs that represent the same feature in the images to be matched. Manual control feature extraction can be subjective and extremely time consuming, and often results in few usable points. Automated feature extraction is a solution to this problem, where desired target features are invariant, and represent evenly distributed landmarks such as edges, corners and line intersections. In this paper, we develop a novel automated registration approach based on the following steps. First, a mathematical morphology (MM)-based method is used to obtain a scale-orientation morphological profile at each image pixel. Next, a spectral dissimilarity metric such as the spectral information divergence is applied for automated extraction of landmark chips, followed by an initial approximate matching. This initial condition is then refined using a hierarchical robust feature matching (RFM) procedure. Experimental results reveal that the proposed registration technique offers a robust solution in the presence of seasonal changes and other interfering factors.","PeriodicalId":302923,"journal":{"name":"International Workshop on the Analysis of Multi-Temporal Remote Sensing Images, 2005.","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132925113","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：