Pub Date : 2020-03-01DOI: 10.1109/LAGIRS48042.2020.9165561
J. Clemente, G. Fontanelli, G. Ovando, Y. Roa, A. Lapini, E. Santi
Remote sensing has become an important mean to assess crop areas, specially for the identification of crop types. Google Earth Engine (GEE) is a free platform that provides a large number of satellite images from different constellations. Moreover, GEE provides pixel-based classifiers, which are used for mapping agricultural areas. The objective of this work is to evaluate the performance of different classification algorithms such as Minimum Distance (MD), Random Forest (RF), Support Vector Machine (SVM), Classification and Regression Trees (CART) and Naïve Bayes (NB) on an agricultural area in Tuscany (Italy). Four different scenarios were implemented in GEE combining different information such as optical and Synthetic Aperture Radar (SAR) data, indices and time series. Among the five classifiers used the best performers were RF and SVM. Integrating Sentinel-1 (S1) and Sentinel-2 (S2) slightly improves the classification in comparison to the only S2 image classifications. The use of time series substantially improves supervised classifications. The analysis carried out so far lays the foundation for the integration of time series of SAR and optical data.
{"title":"Google Earth Engine: Application Of Algorithms For Remote Sensing Of Crops In Tuscany (Italy)","authors":"J. Clemente, G. Fontanelli, G. Ovando, Y. Roa, A. Lapini, E. Santi","doi":"10.1109/LAGIRS48042.2020.9165561","DOIUrl":"https://doi.org/10.1109/LAGIRS48042.2020.9165561","url":null,"abstract":"Remote sensing has become an important mean to assess crop areas, specially for the identification of crop types. Google Earth Engine (GEE) is a free platform that provides a large number of satellite images from different constellations. Moreover, GEE provides pixel-based classifiers, which are used for mapping agricultural areas. The objective of this work is to evaluate the performance of different classification algorithms such as Minimum Distance (MD), Random Forest (RF), Support Vector Machine (SVM), Classification and Regression Trees (CART) and Naïve Bayes (NB) on an agricultural area in Tuscany (Italy). Four different scenarios were implemented in GEE combining different information such as optical and Synthetic Aperture Radar (SAR) data, indices and time series. Among the five classifiers used the best performers were RF and SVM. Integrating Sentinel-1 (S1) and Sentinel-2 (S2) slightly improves the classification in comparison to the only S2 image classifications. The use of time series substantially improves supervised classifications. The analysis carried out so far lays the foundation for the integration of time series of SAR and optical data.","PeriodicalId":111863,"journal":{"name":"2020 IEEE Latin American GRSS & ISPRS Remote Sensing Conference (LAGIRS)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127746779","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 : 2020-03-01DOI: 10.1109/LAGIRS48042.2020.9165584
C. Bello, N. Santillán, A. Cochachin, S. Arias, W. Suarez
Ground Penetrating Radar (GPR) survey was carried out to estimate the ice thickness and mapping the bedrock topography at Znosko glacier on King George Island, Antarctic Peninsula during 25th Peruvian Antarctic Expedition (2018). GPR surveying did at 5.2 MHz frequency with a 16 m antenna gap (transmitter and receiver). The mean ice thickness profiles vary from 7 to 123 m across the 350 m profile length. This high-resolution survey also identified a different type of ices and glaciological features which will help in modelling the nature of the glaciers in the future.
{"title":"ICE Thickness Using Ground Penetrating Radar at Znosko Glacier on King George Island","authors":"C. Bello, N. Santillán, A. Cochachin, S. Arias, W. Suarez","doi":"10.1109/LAGIRS48042.2020.9165584","DOIUrl":"https://doi.org/10.1109/LAGIRS48042.2020.9165584","url":null,"abstract":"Ground Penetrating Radar (GPR) survey was carried out to estimate the ice thickness and mapping the bedrock topography at Znosko glacier on King George Island, Antarctic Peninsula during 25th Peruvian Antarctic Expedition (2018). GPR surveying did at 5.2 MHz frequency with a 16 m antenna gap (transmitter and receiver). The mean ice thickness profiles vary from 7 to 123 m across the 350 m profile length. This high-resolution survey also identified a different type of ices and glaciological features which will help in modelling the nature of the glaciers in the future.","PeriodicalId":111863,"journal":{"name":"2020 IEEE Latin American GRSS & ISPRS Remote Sensing Conference (LAGIRS)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128222310","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 : 2020-03-01DOI: 10.1109/lagirs48042.2020.9165579
S. Banchero, D. Abelleyra, S. Verón, M. J. Mosciaro, F. Arévalos, J. Volante
Land transformation is one of the most significant human changes on the Earth’s surface processes. Therefore, land use land cover time series are a key input for environmental monitoring, natural resources management, territorial planning enforcement at national scale. We here capitalize from the MapBiomas initiative to characterize land use land cover (LULC) change in the Gran Chaco between 2010 and 2017. Specifically we sought to a) quantify annual changes in the main LULC classes; b) identify the main LULC transitions and c) relate these transitions to current land use policies. Within the MapBiomas project, Landsat based annual maps depicting natural woody vegetation, natural herbaceous vegetation, dispersed natural vegetation, cropland, pastures, bare areas and water. We used Random Forest machine learning algorithms trained by samples produced by visual interpretation of high resolution images. Annual overall accuracy ranged from 0,73 to 0,74. Our results showed that, between 2010 and 2017, agriculture and pasture lands increased ca. 3.7 Mha while natural forestry decreased by 2.3 Mha. Transitions from forests to agriculture accounted for 1.14% of the overall deforestation while 86% was associated to pastures and natural herbaceous vegetation. In Argentina, forest loss occurred primarily (39%) on areas non considered by the territorial planning Law, followed by medium (33%), high (19%) and low (9%) conservation priority classes. These results illustrate the potential contribution of remote sensing to characterize complex human environmental interactions occurring over extended areas and time frames.
{"title":"Recent Land Use and Land Cover Change Dynamics in the Gran Chaco Americano","authors":"S. Banchero, D. Abelleyra, S. Verón, M. J. Mosciaro, F. Arévalos, J. Volante","doi":"10.1109/lagirs48042.2020.9165579","DOIUrl":"https://doi.org/10.1109/lagirs48042.2020.9165579","url":null,"abstract":"Land transformation is one of the most significant human changes on the Earth’s surface processes. Therefore, land use land cover time series are a key input for environmental monitoring, natural resources management, territorial planning enforcement at national scale. We here capitalize from the MapBiomas initiative to characterize land use land cover (LULC) change in the Gran Chaco between 2010 and 2017. Specifically we sought to a) quantify annual changes in the main LULC classes; b) identify the main LULC transitions and c) relate these transitions to current land use policies. Within the MapBiomas project, Landsat based annual maps depicting natural woody vegetation, natural herbaceous vegetation, dispersed natural vegetation, cropland, pastures, bare areas and water. We used Random Forest machine learning algorithms trained by samples produced by visual interpretation of high resolution images. Annual overall accuracy ranged from 0,73 to 0,74. Our results showed that, between 2010 and 2017, agriculture and pasture lands increased ca. 3.7 Mha while natural forestry decreased by 2.3 Mha. Transitions from forests to agriculture accounted for 1.14% of the overall deforestation while 86% was associated to pastures and natural herbaceous vegetation. In Argentina, forest loss occurred primarily (39%) on areas non considered by the territorial planning Law, followed by medium (33%), high (19%) and low (9%) conservation priority classes. These results illustrate the potential contribution of remote sensing to characterize complex human environmental interactions occurring over extended areas and time frames.","PeriodicalId":111863,"journal":{"name":"2020 IEEE Latin American GRSS & ISPRS Remote Sensing Conference (LAGIRS)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127573061","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 : 2020-03-01DOI: 10.1109/LAGIRS48042.2020.9165621
M. G. Lacerda, E. H. Shiguemori, A. Damiao, C. S. Anjos, M. Habermann
Given the wide variety of image classifiers available nowadays, some questions remain about the accuracy and processing time of Very High Resolution (VHR) images. Another question concerns the use of a Single or Ensemble Classifiers. Of course, the main factor to consider is the quality of the classified image, but computational cost is also important, especially in applications that require real-time processing. Given this scenario, this paper aims to relate the accuracy of seven single classifiers and the ensemble of the same classifiers with the processing time. In this paper the ensemble of classifiers had the best results in terms of accuracy, however, it comes to processing time, the decision tree had the best performance.
{"title":"Analysis of VHR Image Classification by Single and Ensemble of Classifiers","authors":"M. G. Lacerda, E. H. Shiguemori, A. Damiao, C. S. Anjos, M. Habermann","doi":"10.1109/LAGIRS48042.2020.9165621","DOIUrl":"https://doi.org/10.1109/LAGIRS48042.2020.9165621","url":null,"abstract":"Given the wide variety of image classifiers available nowadays, some questions remain about the accuracy and processing time of Very High Resolution (VHR) images. Another question concerns the use of a Single or Ensemble Classifiers. Of course, the main factor to consider is the quality of the classified image, but computational cost is also important, especially in applications that require real-time processing. Given this scenario, this paper aims to relate the accuracy of seven single classifiers and the ensemble of the same classifiers with the processing time. In this paper the ensemble of classifiers had the best results in terms of accuracy, however, it comes to processing time, the decision tree had the best performance.","PeriodicalId":111863,"journal":{"name":"2020 IEEE Latin American GRSS & ISPRS Remote Sensing Conference (LAGIRS)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127940415","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 : 2020-03-01DOI: 10.1109/LAGIRS48042.2020.9165604
Roberto O. Chávez, J. A. Lastra, D. Valencia, I. Díaz-Hormazábal
The Chilean SNASPE is a complex network of 104 protected areas covering 18.5 million hectares of continental and insular Chile in South America. The geographical complexity and high biodiversity of the SNASPE make difficult to develop a unified monitoring system for conservation and management. In this contribution, we introduce a novel and remote-sensing web-platform for monitoring SNASPE units based completely in open acces data and software. The platform was designed in close cooperation with the Chilean forest service CONAF in order to make it applicable to the whole SNASPE. Following the framework of the Group on Earth Observation - Biodiversity Observation Network (GEO-BON), we used the Essential Biodiversity Variable (EBV) Phenology and MODIS Enhanced Vegetation Index (EVI) data to detect in near-real-time anomalies from the normal annual phenological cycle of vegetation. The platform is based on a flexible non-parametric probabilistic algorithm (the “npphen” R package) capable to reconstruct any type of leaf phenology and to quantify its inter-annual variation by means of confidence intervals around the most probable annual curve. Phenological anomalies are then calculated as a deviation from the expected annual cycle and judged based on their location within the confidence intervals. Anomalies located above 95% confidence interval trigger a “red alert” which is displayed on the web application as soon as the MODIS data become available. This user-friendly platform was implemented in the La Campana National Park giving early alerts of a severe drought in 2019, warning Conaf to implement actions to protect the park from potential wild fires.
{"title":"A User-Friendly Remote-Sensing Web-Platform for Biodiversity Conservation and Management in Protected Areas","authors":"Roberto O. Chávez, J. A. Lastra, D. Valencia, I. Díaz-Hormazábal","doi":"10.1109/LAGIRS48042.2020.9165604","DOIUrl":"https://doi.org/10.1109/LAGIRS48042.2020.9165604","url":null,"abstract":"The Chilean SNASPE is a complex network of 104 protected areas covering 18.5 million hectares of continental and insular Chile in South America. The geographical complexity and high biodiversity of the SNASPE make difficult to develop a unified monitoring system for conservation and management. In this contribution, we introduce a novel and remote-sensing web-platform for monitoring SNASPE units based completely in open acces data and software. The platform was designed in close cooperation with the Chilean forest service CONAF in order to make it applicable to the whole SNASPE. Following the framework of the Group on Earth Observation - Biodiversity Observation Network (GEO-BON), we used the Essential Biodiversity Variable (EBV) Phenology and MODIS Enhanced Vegetation Index (EVI) data to detect in near-real-time anomalies from the normal annual phenological cycle of vegetation. The platform is based on a flexible non-parametric probabilistic algorithm (the “npphen” R package) capable to reconstruct any type of leaf phenology and to quantify its inter-annual variation by means of confidence intervals around the most probable annual curve. Phenological anomalies are then calculated as a deviation from the expected annual cycle and judged based on their location within the confidence intervals. Anomalies located above 95% confidence interval trigger a “red alert” which is displayed on the web application as soon as the MODIS data become available. This user-friendly platform was implemented in the La Campana National Park giving early alerts of a severe drought in 2019, warning Conaf to implement actions to protect the park from potential wild fires.","PeriodicalId":111863,"journal":{"name":"2020 IEEE Latin American GRSS & ISPRS Remote Sensing Conference (LAGIRS)","volume":"188 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122999492","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 : 2020-03-01DOI: 10.1109/LAGIRS48042.2020.9165620
E. Ferreira, M. Brito, R. Balaniuk, M. Alvim, J. A. D. Santos
In this work we present BrazilDAM, a novel public dataset based on Sentinel-2 and Landsat-8 satellite images covering all tailings dams cataloged by the Brazilian National Mining Agency (ANM). The dataset was built using georeferenced images from 769 dams, recorded between 2016 and 2019. The time series were processed in order to produce cloud free images. The dams contain mining waste from different ore categories and have highly varying shapes, areas and volumes, making BrazilDAM particularly interesting and challenging to be used in machine learning benchmarks. The original catalog contains, besides the dam coordinates, information about: the main ore, constructive method, risk category, and associated potential damage. To evaluate BrazilDAM’s predictive potential we performed classification essays using state-of-the-art deep Convolutional Neural Network (CNNs). In the experiments, we achieved an average classification accuracy of 94.11% in tailing dam binary classification task. In addition, others four setups of experiments were made using the complementary information from the original catalog, exhaustively exploiting the capacity of the proposed dataset.
{"title":"Brazildam: A Benchmark Dataset For Tailings Dam Detection","authors":"E. Ferreira, M. Brito, R. Balaniuk, M. Alvim, J. A. D. Santos","doi":"10.1109/LAGIRS48042.2020.9165620","DOIUrl":"https://doi.org/10.1109/LAGIRS48042.2020.9165620","url":null,"abstract":"In this work we present BrazilDAM, a novel public dataset based on Sentinel-2 and Landsat-8 satellite images covering all tailings dams cataloged by the Brazilian National Mining Agency (ANM). The dataset was built using georeferenced images from 769 dams, recorded between 2016 and 2019. The time series were processed in order to produce cloud free images. The dams contain mining waste from different ore categories and have highly varying shapes, areas and volumes, making BrazilDAM particularly interesting and challenging to be used in machine learning benchmarks. The original catalog contains, besides the dam coordinates, information about: the main ore, constructive method, risk category, and associated potential damage. To evaluate BrazilDAM’s predictive potential we performed classification essays using state-of-the-art deep Convolutional Neural Network (CNNs). In the experiments, we achieved an average classification accuracy of 94.11% in tailing dam binary classification task. In addition, others four setups of experiments were made using the complementary information from the original catalog, exhaustively exploiting the capacity of the proposed dataset.","PeriodicalId":111863,"journal":{"name":"2020 IEEE Latin American GRSS & ISPRS Remote Sensing Conference (LAGIRS)","volume":"4 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116765590","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 : 2020-03-01DOI: 10.1109/LAGIRS48042.2020.9165661
F. A. Rodrigues, J. Nobre, R. Vig´elis, V. Liesenberg, R. Marques, F. Medeiros
Synthetic aperture radar (SAR) image processing and analysis rely on statistical modeling and parameter estimation of the probability density functions that characterize data. The method of log-cumulants (MoLC) is a reliable alternative for parameter estimation of SAR data models and image processing. However, numerical methods are usually applied to estimate parameters using MoLC, and it may lead to a high computational cost. Thus, MoLC may be unsuitable for real-time SAR imagery applications such as change detection and marine search and rescue, for example. Our paper introduces a fast approach to overcome this limitation of MoLC, focusing on parameter estimation of single-channel SAR data modeled by the $G_{I}^{0}$ distribution. Experiments with simulated and real SAR data demonstrate that our approach performs faster than MoLC, while the precision of the estimation is comparable with that of the original MoLC. We tested the fast approach with multitemporal data and applied the arithmetic-geometric distance to real SAR images for change detection on the ocean. The experiments showed that the fast MoLC outperformed the original estimation method with regard to the computational time.
{"title":"A Fast Approach for the Log-Cumulants Method Applied to Intensity Sar Image Processing","authors":"F. A. Rodrigues, J. Nobre, R. Vig´elis, V. Liesenberg, R. Marques, F. Medeiros","doi":"10.1109/LAGIRS48042.2020.9165661","DOIUrl":"https://doi.org/10.1109/LAGIRS48042.2020.9165661","url":null,"abstract":"Synthetic aperture radar (SAR) image processing and analysis rely on statistical modeling and parameter estimation of the probability density functions that characterize data. The method of log-cumulants (MoLC) is a reliable alternative for parameter estimation of SAR data models and image processing. However, numerical methods are usually applied to estimate parameters using MoLC, and it may lead to a high computational cost. Thus, MoLC may be unsuitable for real-time SAR imagery applications such as change detection and marine search and rescue, for example. Our paper introduces a fast approach to overcome this limitation of MoLC, focusing on parameter estimation of single-channel SAR data modeled by the $G_{I}^{0}$ distribution. Experiments with simulated and real SAR data demonstrate that our approach performs faster than MoLC, while the precision of the estimation is comparable with that of the original MoLC. We tested the fast approach with multitemporal data and applied the arithmetic-geometric distance to real SAR images for change detection on the ocean. The experiments showed that the fast MoLC outperformed the original estimation method with regard to the computational time.","PeriodicalId":111863,"journal":{"name":"2020 IEEE Latin American GRSS & ISPRS Remote Sensing Conference (LAGIRS)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115172176","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 : 2020-03-01DOI: 10.1109/LAGIRS48042.2020.9165650
J. Sartori, J. B. Sbruzzi, E. L. Fonseca
This work aims to define the basic parameters for the automatic mapping of the channel between the Lagoa do Peixe and the Atlantic Ocean, which is located in the municipalities of Tavares and Mostardas, Rio Grande do Sul state, Brazil. The automatic mapping is based on an unsupervised classification of Landsat 8 satellite images at the Google Earth Engine cloud computing platform. The images used were selected to present both channel situations (opened and closed). Three images were selected with acquisition dates that presented the open channel and three that presented the closed channel. Each image was classified using the K-means clustering method, using separately band 6, band 7 (both located at shortwave infrared - SWIR) and the Normalized Difference Water Index (NDWI). Once the number of clusters must be defined a priori by the analyst, as well as the training sample area, these parameters were tested over the dataset and clustering results were compared. All of the generated clusters maps were analyzed over 10 random points, identifying the clustering hits and errors. Due to the absence of reference maps, all the final clustering maps for each date were compared with the composite true color image from the same acquisition date. The NDWI cluster maps showed the best results in separating water and non-water pixels.
这项工作旨在为位于巴西南里奥格兰德州塔瓦雷斯和莫斯塔达斯市的Lagoa do Peixe和大西洋之间的通道自动测绘定义基本参数。自动绘图是基于谷歌地球引擎云计算平台上对Landsat 8卫星图像的无监督分类。所使用的图像被选择来呈现两种通道情况(打开和关闭)。选取三幅图像，采集日期分别为开放通道和封闭通道。每张图像使用K-means聚类方法，分别使用波段6、波段7(均位于短波红外- SWIR)和归一化差水指数(NDWI)进行分类。一旦分析人员必须先验地定义聚类的数量，以及训练样本区域，这些参数将在数据集上进行测试，并比较聚类结果。所有生成的聚类图在10个随机点上进行分析，识别聚类命中和错误。由于缺乏参考地图，每个日期的所有最终聚类地图都与同一采集日期的合成真彩色图像进行比较。NDWI聚类图在分离水像元和非水像元方面效果最好。
{"title":"Preliminary Analysis For Automatic Tidal Inlets Mapping Using Google Earth Engine","authors":"J. Sartori, J. B. Sbruzzi, E. L. Fonseca","doi":"10.1109/LAGIRS48042.2020.9165650","DOIUrl":"https://doi.org/10.1109/LAGIRS48042.2020.9165650","url":null,"abstract":"This work aims to define the basic parameters for the automatic mapping of the channel between the Lagoa do Peixe and the Atlantic Ocean, which is located in the municipalities of Tavares and Mostardas, Rio Grande do Sul state, Brazil. The automatic mapping is based on an unsupervised classification of Landsat 8 satellite images at the Google Earth Engine cloud computing platform. The images used were selected to present both channel situations (opened and closed). Three images were selected with acquisition dates that presented the open channel and three that presented the closed channel. Each image was classified using the K-means clustering method, using separately band 6, band 7 (both located at shortwave infrared - SWIR) and the Normalized Difference Water Index (NDWI). Once the number of clusters must be defined a priori by the analyst, as well as the training sample area, these parameters were tested over the dataset and clustering results were compared. All of the generated clusters maps were analyzed over 10 random points, identifying the clustering hits and errors. Due to the absence of reference maps, all the final clustering maps for each date were compared with the composite true color image from the same acquisition date. The NDWI cluster maps showed the best results in separating water and non-water pixels.","PeriodicalId":111863,"journal":{"name":"2020 IEEE Latin American GRSS & ISPRS Remote Sensing Conference (LAGIRS)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114982621","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 : 2020-03-01DOI: 10.1109/LAGIRS48042.2020.9165682
A. Filho, P. Borba, V. Silva, A. Cerdeira, A. Poz
Quality control (QC) of geospatial data is relevant to urban territorial management to ensure accurate data for government to make strategic decisions when planning cities. The acquisition and control of geospatial data in the Brazilian government must follow INDE – National Data Spatial Infrastructure – through the Technical Specifications. The cadastral cartography from urban areas in Brasilia was updated and divided into 10 areas. Acquired data includes classes, features, attributes and metadata on 1: 1,000 scale. High resolution images and LIDAR data were used to assist the QC process. The first step of the QC was to check positional accuracy. Samples were applied for each class in the mapping block with 4% rate on the feature random selection and all features class had the same level of confidence. Then, three stages were automatically verified: logical consistency, commision and attribute thematic accuracy evaluations. The process also includes the visual interpretation for omission and classification, which involves a certain subjectivity. Everything was executed with QGIS, FME, Erdas Imagine, Postgresql, PostGIS and a plugin specifically developed for that, the DSGTools. The results show that in general, the quantity of errors were low. However, many errors were detected in the elements completeness and thematic accuracy, specially in áreas 1, 2, 3, 6 and 9. In the opposite, the logical consistency and positional accuracy presented the lowest quantity of errors, which does not diminish the relevance of these errors, since it compromises the usability of the data.
{"title":"Quality Control Relevance on Acquisition of Large Scale Geospatial Data to Urban Territorial Management","authors":"A. Filho, P. Borba, V. Silva, A. Cerdeira, A. Poz","doi":"10.1109/LAGIRS48042.2020.9165682","DOIUrl":"https://doi.org/10.1109/LAGIRS48042.2020.9165682","url":null,"abstract":"Quality control (QC) of geospatial data is relevant to urban territorial management to ensure accurate data for government to make strategic decisions when planning cities. The acquisition and control of geospatial data in the Brazilian government must follow INDE – National Data Spatial Infrastructure – through the Technical Specifications. The cadastral cartography from urban areas in Brasilia was updated and divided into 10 areas. Acquired data includes classes, features, attributes and metadata on 1: 1,000 scale. High resolution images and LIDAR data were used to assist the QC process. The first step of the QC was to check positional accuracy. Samples were applied for each class in the mapping block with 4% rate on the feature random selection and all features class had the same level of confidence. Then, three stages were automatically verified: logical consistency, commision and attribute thematic accuracy evaluations. The process also includes the visual interpretation for omission and classification, which involves a certain subjectivity. Everything was executed with QGIS, FME, Erdas Imagine, Postgresql, PostGIS and a plugin specifically developed for that, the DSGTools. The results show that in general, the quantity of errors were low. However, many errors were detected in the elements completeness and thematic accuracy, specially in áreas 1, 2, 3, 6 and 9. In the opposite, the logical consistency and positional accuracy presented the lowest quantity of errors, which does not diminish the relevance of these errors, since it compromises the usability of the data.","PeriodicalId":111863,"journal":{"name":"2020 IEEE Latin American GRSS & ISPRS Remote Sensing Conference (LAGIRS)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126752867","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 : 2020-03-01DOI: 10.1109/LAGIRS48042.2020.9165649
K. Ferreira, G. R. Queiroz, G. Câmara, R. C. Souza, L. Vinhas, R. F. B. Marujo, R. Simões, C. Noronha, R. W. Costa, J. S. Arcanjo, V. Gomes, M. C. Zaglia
The Brazilian National Institute for Space Research (INPE) produces official information about deforestation as well as land use and cover in the country, based on remote sensing images. The current open data policy adopted by many space agencies and governments worldwide provided access to petabytes of remote sensing images. To properly deal with this vast amount of images, novel technologies have been proposed and developed based on cloud computing and big data systems. This paper describes the INPE’s initiatives in using remote sensing images and cloud services of the Amazon Web Services (AWS) infrastructure to improve land use and cover monitoring.
{"title":"Using Remote Sensing Images and Cloud Services on Aws to Improve Land Use and Cover Monitoring","authors":"K. Ferreira, G. R. Queiroz, G. Câmara, R. C. Souza, L. Vinhas, R. F. B. Marujo, R. Simões, C. Noronha, R. W. Costa, J. S. Arcanjo, V. Gomes, M. C. Zaglia","doi":"10.1109/LAGIRS48042.2020.9165649","DOIUrl":"https://doi.org/10.1109/LAGIRS48042.2020.9165649","url":null,"abstract":"The Brazilian National Institute for Space Research (INPE) produces official information about deforestation as well as land use and cover in the country, based on remote sensing images. The current open data policy adopted by many space agencies and governments worldwide provided access to petabytes of remote sensing images. To properly deal with this vast amount of images, novel technologies have been proposed and developed based on cloud computing and big data systems. This paper describes the INPE’s initiatives in using remote sensing images and cloud services of the Amazon Web Services (AWS) infrastructure to improve land use and cover monitoring.","PeriodicalId":111863,"journal":{"name":"2020 IEEE Latin American GRSS & ISPRS Remote Sensing Conference (LAGIRS)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121758679","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：