Pub Date : 2020-03-01DOI: 10.1109/LAGIRS48042.2020.9165564
O. Monserrat, C. Cárdenas, P. Olea, V. Krishnakumar, B. Crippa
This work shows two examples on the use of Sentinel-1 data for monitoring different natural processes, like active geohazards or glacier dynamics in the Patagonia region. Sentinel-1 is a two-satellite constellation, launched by the European Space Agency (ESA), that provides SAR imagery with interferometric capabilities. It is in operation since 2014 and has supposed a significant improvement in the exploitation of these type of data for applications like natural hazards mapping and monitoring. The acquisition policy, that guarantees an acquisition each few days (12 days in Patagonia region) for both ascending and descending trajectories, and the data distribution policy, that allows free access to the images without legal constrains, are the main reasons for this improvement. These two aspects allowed not only to assure the data in the past but also to perform monitoring plans at medium-long term. In this work we show the potentialities of the use of these data in the Patagonia region through the application of two different techniques in two different application test sites: urban areas and glaciers.
{"title":"Potentialities of Sentinel-1 for mapping and monitoring geological and cryospheric processes in the Patagonia region (Chile)","authors":"O. Monserrat, C. Cárdenas, P. Olea, V. Krishnakumar, B. Crippa","doi":"10.1109/LAGIRS48042.2020.9165564","DOIUrl":"https://doi.org/10.1109/LAGIRS48042.2020.9165564","url":null,"abstract":"This work shows two examples on the use of Sentinel-1 data for monitoring different natural processes, like active geohazards or glacier dynamics in the Patagonia region. Sentinel-1 is a two-satellite constellation, launched by the European Space Agency (ESA), that provides SAR imagery with interferometric capabilities. It is in operation since 2014 and has supposed a significant improvement in the exploitation of these type of data for applications like natural hazards mapping and monitoring. The acquisition policy, that guarantees an acquisition each few days (12 days in Patagonia region) for both ascending and descending trajectories, and the data distribution policy, that allows free access to the images without legal constrains, are the main reasons for this improvement. These two aspects allowed not only to assure the data in the past but also to perform monitoring plans at medium-long term. In this work we show the potentialities of the use of these data in the Patagonia region through the application of two different techniques in two different application test sites: urban areas and glaciers.","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":"115535008","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/LAGIRS48042.2020.9165643
J. González, K. Sankaran, V. Ayma, C. Beltrán
Remote sensing is widely used to monitor earth surfaces with the main objective of extracting information from it. Such is the case of water surface, which is one of the most affected extensions when flood events occur, and its monitoring helps in the analysis of detecting such affected areas, considering that adequately defining water surfaces is one of the biggest problems that Peruvian authorities are concerned with. In this regard, semiautomatic mapping methods improve this monitoring, but this process remains a time-consuming task and into the subjectivity of the experts.In this work, we present a new approach for segmenting water surfaces from satellite images based on the application of convolutional neural networks. First, we explore the application of a U-Net model and then a transfer knowledge-based model. Our results show that both approaches are comparable when trained using an 680-labelled satellite image dataset; however, as the number of training samples is reduced, the performance of the transfer knowledge-based model, which combines high and very high image resolution characteristics, is improved.
{"title":"Application of Semantic Segmentation with Few Labels in the Detection of Water Bodies from Perusat-1 Satellite’s Images","authors":"J. González, K. Sankaran, V. Ayma, C. Beltrán","doi":"10.1109/LAGIRS48042.2020.9165643","DOIUrl":"https://doi.org/10.1109/LAGIRS48042.2020.9165643","url":null,"abstract":"Remote sensing is widely used to monitor earth surfaces with the main objective of extracting information from it. Such is the case of water surface, which is one of the most affected extensions when flood events occur, and its monitoring helps in the analysis of detecting such affected areas, considering that adequately defining water surfaces is one of the biggest problems that Peruvian authorities are concerned with. In this regard, semiautomatic mapping methods improve this monitoring, but this process remains a time-consuming task and into the subjectivity of the experts.In this work, we present a new approach for segmenting water surfaces from satellite images based on the application of convolutional neural networks. First, we explore the application of a U-Net model and then a transfer knowledge-based model. Our results show that both approaches are comparable when trained using an 680-labelled satellite image dataset; however, as the number of training samples is reduced, the performance of the transfer knowledge-based model, which combines high and very high image resolution characteristics, is improved.","PeriodicalId":111863,"journal":{"name":"2020 IEEE Latin American GRSS & ISPRS Remote Sensing Conference (LAGIRS)","volume":"22 4 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":"123728203","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/LAGIRS48042.2020.9165657
C. Amisse, M. E. Jijón-Palma, Jorge Antonio Silva Centeno
In this paper it is described a study case of a rapid assessment of change detections for post-cyclone Idai vegetated damage and flood extension estimation by fusion of multi-temporal Landsat and sentinel-1 SAR images. For automated change detection, after disasters, many algorithms have been proposed. To visualize the changes induced by cyclone we tested and compared two automated change detection techniques namely: Principal Components Analysis (PCA), Normalized Difference Vegetation Index (NDVI) and image segmentation. With the image segmentation of multispectral and SAR images, it was possible to visualize the extension of the wet area. For this specific application, PCA was identified as the optimal change detection indicator than NDVI. This study suggested that image segmentation, principal components analysis, and normalized difference vegetation index can be used for change detection of surface water due to flood and disasters especially in prone countries like Mozambique.
{"title":"Mapping Extension and Magnitude of Changes Induced by Cyclone Idai with Multi-Temporal Landsat and Sar Images","authors":"C. Amisse, M. E. Jijón-Palma, Jorge Antonio Silva Centeno","doi":"10.1109/LAGIRS48042.2020.9165657","DOIUrl":"https://doi.org/10.1109/LAGIRS48042.2020.9165657","url":null,"abstract":"In this paper it is described a study case of a rapid assessment of change detections for post-cyclone Idai vegetated damage and flood extension estimation by fusion of multi-temporal Landsat and sentinel-1 SAR images. For automated change detection, after disasters, many algorithms have been proposed. To visualize the changes induced by cyclone we tested and compared two automated change detection techniques namely: Principal Components Analysis (PCA), Normalized Difference Vegetation Index (NDVI) and image segmentation. With the image segmentation of multispectral and SAR images, it was possible to visualize the extension of the wet area. For this specific application, PCA was identified as the optimal change detection indicator than NDVI. This study suggested that image segmentation, principal components analysis, and normalized difference vegetation index can be used for change detection of surface water due to flood and disasters especially in prone countries like Mozambique.","PeriodicalId":111863,"journal":{"name":"2020 IEEE Latin American GRSS & ISPRS Remote Sensing Conference (LAGIRS)","volume":"8 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":"122435132","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/LAGIRS48042.2020.9165590
E. Pinheiro, N. A. Camini, M. Soares, S. Sumida
The factors that contribute to land use change in the municipality of Gaúcha do Norte - MT, are entirely linked to the economic process and agricultural production. This process has left brazil in a state of alert due to the process of deforestation and loss of tropical forests. From 2000 to 2010, the forest areas converted into agriculture accounted for 13.3%, the main factor that directly potentiated with deforestation was the cultivation of soybeans, which in turn was occupying places previously occupied by livestock and pushing the livestock forest inside. The phenomena of land use change and land cover start from multidimensional issues in the environmental and economic context. The use of environmental modeling through cellular automata to analyze land use change phenomena and reproduce the trajectory through future land use simulations and evolution establishes an integration associated by mathematical models and flow integration systems. That predict the trajectory of land use change, thus generating a dynamic model capable of predicting future land use changes by replicating possible patterns of landscape evolution and enabling assessments of future ecological implications for the environment.
导致Gaúcha do Norte - MT市土地利用变化的因素与经济进程和农业生产完全相关。由于森林砍伐和热带森林的丧失，这一过程使巴西处于警戒状态。2000 - 2010年，森林转农面积占13.3%，直接加剧毁林的主要因素是种植大豆，大豆反过来又占据了原来畜牧业占据的地方，将畜牧林推向内部。土地利用变化和土地覆盖现象是从环境和经济背景下的多维问题出发的。通过元胞自动机使用环境建模来分析土地利用变化现象，并通过未来土地利用模拟和演变再现轨迹，建立了与数学模型和流量集成系统相关的集成。预测土地利用变化的轨迹，从而产生一个动态模型，能够通过复制景观演变的可能模式来预测未来的土地利用变化，并能够评估未来对环境的生态影响。
{"title":"Cellular Automata Model - Landscape Dynamics Simulation Tool in the Process of Change in Land Use and Cover in the City of GaÚCha Do Norte – Mt","authors":"E. Pinheiro, N. A. Camini, M. Soares, S. Sumida","doi":"10.1109/LAGIRS48042.2020.9165590","DOIUrl":"https://doi.org/10.1109/LAGIRS48042.2020.9165590","url":null,"abstract":"The factors that contribute to land use change in the municipality of Gaúcha do Norte - MT, are entirely linked to the economic process and agricultural production. This process has left brazil in a state of alert due to the process of deforestation and loss of tropical forests. From 2000 to 2010, the forest areas converted into agriculture accounted for 13.3%, the main factor that directly potentiated with deforestation was the cultivation of soybeans, which in turn was occupying places previously occupied by livestock and pushing the livestock forest inside. The phenomena of land use change and land cover start from multidimensional issues in the environmental and economic context. The use of environmental modeling through cellular automata to analyze land use change phenomena and reproduce the trajectory through future land use simulations and evolution establishes an integration associated by mathematical models and flow integration systems. That predict the trajectory of land use change, thus generating a dynamic model capable of predicting future land use changes by replicating possible patterns of landscape evolution and enabling assessments of future ecological implications for the environment.","PeriodicalId":111863,"journal":{"name":"2020 IEEE Latin American GRSS & ISPRS Remote Sensing Conference (LAGIRS)","volume":"1 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":"130153693","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/LAGIRS48042.2020.9165630
Soumyashree Kar, Ryokei Tanaka, H. Iwata, J. Kholová, S. Durbha, J. Adinarayana, V. Vadez
This work is undertaken considering the significance of functional phenotyping (primarily measured from continuous profiles of plant-water relations) for crop selection purposes. High-Throughput Plant Phenotyping (HTPP) platforms which largely employ state-of-the-art sensor technologies for acquisition of vast amount of field data, often fail to efficiently translate sensor information into knowledge due to the major challenges of data handling and processing. Hence, it is imperative to concurrently find a way for dissociating noise from useful data. Additionally, another important aspect is understanding how frequent should be the data collection, so that information is maximized. This paper presents a novel approach for identifying the optimal frequency for phenotyping evapotranspiration (ET) by assimilating results from both time series forecast as well as classification models. Thus, at the optimal frequency, plant-water relations can not only be desirably predicted but genotypes can also be classified based on the characteristics of their ET profiles. Consequently, this will aid better crop selection, besides minimizing noise, redundancy, cost and effort in HTPP data collection. High frequency (15 min) ET time series data of 48 chickpea varieties (with considerable genotypic diversity) collected at the LeasyScan HTPP platform, ICRISAT is used for this study. Time series forecast and classification is performed by varying frequency up to 180 min. Multiple performance measures of time series forecast and classification are combined, followed by implementation of entropy theory for sampling frequency optimization. The results demonstrate that ET time series with a frequency of 60 min per day potentially yield the optimum information.
{"title":"Multi-Scale Time Series Analysis Of Evapotranspiration For High-Throughput Phenotyping Frequency Optimization","authors":"Soumyashree Kar, Ryokei Tanaka, H. Iwata, J. Kholová, S. Durbha, J. Adinarayana, V. Vadez","doi":"10.1109/LAGIRS48042.2020.9165630","DOIUrl":"https://doi.org/10.1109/LAGIRS48042.2020.9165630","url":null,"abstract":"This work is undertaken considering the significance of functional phenotyping (primarily measured from continuous profiles of plant-water relations) for crop selection purposes. High-Throughput Plant Phenotyping (HTPP) platforms which largely employ state-of-the-art sensor technologies for acquisition of vast amount of field data, often fail to efficiently translate sensor information into knowledge due to the major challenges of data handling and processing. Hence, it is imperative to concurrently find a way for dissociating noise from useful data. Additionally, another important aspect is understanding how frequent should be the data collection, so that information is maximized. This paper presents a novel approach for identifying the optimal frequency for phenotyping evapotranspiration (ET) by assimilating results from both time series forecast as well as classification models. Thus, at the optimal frequency, plant-water relations can not only be desirably predicted but genotypes can also be classified based on the characteristics of their ET profiles. Consequently, this will aid better crop selection, besides minimizing noise, redundancy, cost and effort in HTPP data collection. High frequency (15 min) ET time series data of 48 chickpea varieties (with considerable genotypic diversity) collected at the LeasyScan HTPP platform, ICRISAT is used for this study. Time series forecast and classification is performed by varying frequency up to 180 min. Multiple performance measures of time series forecast and classification are combined, followed by implementation of entropy theory for sampling frequency optimization. The results demonstrate that ET time series with a frequency of 60 min per day potentially yield the optimum information.","PeriodicalId":111863,"journal":{"name":"2020 IEEE Latin American GRSS & ISPRS Remote Sensing Conference (LAGIRS)","volume":"35 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":"128532645","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/LAGIRS48042.2020.9165686
C. Cárdenas, G. Casassa, X. Aguilar, D. Mojica, E. Johnson, F. Brondi
To determine the biological and physical mechanisms between Lange glacier and its pro-glacier marine system located in Almirantazgo bay, King George Island, Antarctica, specific variables were determined through remote sensing approaches shown in this work. These preliminary results will allow relating the dynamics of both systems, the glacier, and the marine ecosystem. The information for the estimation of surface flux velocity of the glacier was derived through Radar satellite images (Sentinel-1) by means of offset tracking, the bathymetry was derived from a Multi-beam Echo Sounder, and the Digital Elevation Modell was obtained by means of a Remotely Piloted Aircraft; Finally, the biological parameters were derived from MODIS and OLCI images for the analysis of satellite data to have a first insight to the characteristics of the marine system. This information will help to build the first frame needed to study through remote sensing approaches, the mechanisms that govern the interface among “Lang Glacier” and the “Almirantazgo Bay” at King George Island, Antarctica.
{"title":"From Space to Earth: physical and biological impacts of glacier dynamics in the marine system by means of Remote Sensing at Almirantazgo Bay, Antarctica","authors":"C. Cárdenas, G. Casassa, X. Aguilar, D. Mojica, E. Johnson, F. Brondi","doi":"10.1109/LAGIRS48042.2020.9165686","DOIUrl":"https://doi.org/10.1109/LAGIRS48042.2020.9165686","url":null,"abstract":"To determine the biological and physical mechanisms between Lange glacier and its pro-glacier marine system located in Almirantazgo bay, King George Island, Antarctica, specific variables were determined through remote sensing approaches shown in this work. These preliminary results will allow relating the dynamics of both systems, the glacier, and the marine ecosystem. The information for the estimation of surface flux velocity of the glacier was derived through Radar satellite images (Sentinel-1) by means of offset tracking, the bathymetry was derived from a Multi-beam Echo Sounder, and the Digital Elevation Modell was obtained by means of a Remotely Piloted Aircraft; Finally, the biological parameters were derived from MODIS and OLCI images for the analysis of satellite data to have a first insight to the characteristics of the marine system. This information will help to build the first frame needed to study through remote sensing approaches, the mechanisms that govern the interface among “Lang Glacier” and the “Almirantazgo Bay” at King George Island, Antarctica.","PeriodicalId":111863,"journal":{"name":"2020 IEEE Latin American GRSS & ISPRS Remote Sensing Conference (LAGIRS)","volume":"1 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":"130441899","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/lagirs48042.2020.9165631
Yan Gao, D. Jimenez, M. Skutsch, M. Salinas, J. Solórzano
This paper presents the results of a statistical study of forest inventory data for tropical dry forest in Ayuquila River Basin, Jalisco state, Mexico. The field inventory was carried out between May-June of 2019 which is at the end of dry season and the beginning of raining season. The field inventory data were collected in 43 plots of 500 $mathrm{m}^{2}$ each which were designed in a way to include tropical dry forests in two conditions: degraded and conserved. In each plot, the collected data include DBH, tree height, number of trees per plot, and the density of tree stems. A study was carried out to find out if there are statistically significant differences variables relating to forest structure between degraded and conserved status. The Mann-Whitney test shows that there is significant differences in canopy cover, biomass, tree height, and basal area. This information is important since it helps to understand whether and how forest degradation can be detected using remote sensing data.
{"title":"Which Variables in Forest Survey Data Can Better Distinguish Conserved and Degraded Tropical Dry Forest?","authors":"Yan Gao, D. Jimenez, M. Skutsch, M. Salinas, J. Solórzano","doi":"10.1109/lagirs48042.2020.9165631","DOIUrl":"https://doi.org/10.1109/lagirs48042.2020.9165631","url":null,"abstract":"This paper presents the results of a statistical study of forest inventory data for tropical dry forest in Ayuquila River Basin, Jalisco state, Mexico. The field inventory was carried out between May-June of 2019 which is at the end of dry season and the beginning of raining season. The field inventory data were collected in 43 plots of 500 $mathrm{m}^{2}$ each which were designed in a way to include tropical dry forests in two conditions: degraded and conserved. In each plot, the collected data include DBH, tree height, number of trees per plot, and the density of tree stems. A study was carried out to find out if there are statistically significant differences variables relating to forest structure between degraded and conserved status. The Mann-Whitney test shows that there is significant differences in canopy cover, biomass, tree height, and basal area. This information is important since it helps to understand whether and how forest degradation can be detected using remote sensing data.","PeriodicalId":111863,"journal":{"name":"2020 IEEE Latin American GRSS & ISPRS Remote Sensing Conference (LAGIRS)","volume":"1 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":"131270064","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/LAGIRS48042.2020.9165593
J. Salinas, M. K. P. Eggerth, M. E. Miller, R. R. B. Meza, J. Chacaltana, J. Acuña, G. Barroso
A classification method with multi-temporal images of synthetic aperture radar (SAR) combined with Geographic information system, geoinformation data, and field validation, was applied for wetland mapping accuracy and typology. Wetland mapping is vital for management and conservation, particularly under environmental pressures such as wetland drainage and land reclamation. The aim of this study is to develop an accurate mapping of wetlands and open water systems of the Lower Doce River Valley - LDRV (Southeastern Brazil) with Synthetic Aperture Radar (SAR) imagery, using multitemporal classification techniques and ground truth validation. Sentinel-1B SAR imagery from 2016 and 2019 was processed with Google Earth Engine (GEE). Monthly median imagery condition for the rainy season was obtained and K-means unsupervised classification was applied. The study yields 4,157 wetlands, 262.27 km2 with predominant small patches. Fieldwork revealed three main wetlands categories: coastal wetlands, inland wetlands and artificial wetlands. The results have shown an overall accuracy of 81.9% and a Kappa coefficient of 0.71. Wetlands, non-wetlands, and open waters classes present accuracy of 50, 80 and 95%, respectively.
{"title":"Wetland Mapping With Multitemporal Sentinel Radar Remote Sensing In The Southeast Region Of Brazil","authors":"J. Salinas, M. K. P. Eggerth, M. E. Miller, R. R. B. Meza, J. Chacaltana, J. Acuña, G. Barroso","doi":"10.1109/LAGIRS48042.2020.9165593","DOIUrl":"https://doi.org/10.1109/LAGIRS48042.2020.9165593","url":null,"abstract":"A classification method with multi-temporal images of synthetic aperture radar (SAR) combined with Geographic information system, geoinformation data, and field validation, was applied for wetland mapping accuracy and typology. Wetland mapping is vital for management and conservation, particularly under environmental pressures such as wetland drainage and land reclamation. The aim of this study is to develop an accurate mapping of wetlands and open water systems of the Lower Doce River Valley - LDRV (Southeastern Brazil) with Synthetic Aperture Radar (SAR) imagery, using multitemporal classification techniques and ground truth validation. Sentinel-1B SAR imagery from 2016 and 2019 was processed with Google Earth Engine (GEE). Monthly median imagery condition for the rainy season was obtained and K-means unsupervised classification was applied. The study yields 4,157 wetlands, 262.27 km2 with predominant small patches. Fieldwork revealed three main wetlands categories: coastal wetlands, inland wetlands and artificial wetlands. The results have shown an overall accuracy of 81.9% and a Kappa coefficient of 0.71. Wetlands, non-wetlands, and open waters classes present accuracy of 50, 80 and 95%, respectively.","PeriodicalId":111863,"journal":{"name":"2020 IEEE Latin American GRSS & ISPRS Remote Sensing Conference (LAGIRS)","volume":"13 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":"134543546","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/LAGIRS48042.2020.9165668
F. Pirotti, E. Kutchartt, E. Csaplovics
Initial results of biomass estimation in the La Fusta area from existing equations found in literature are presented. As expected, accuracy of general equations suffer from the equation coefficients being obtained from fitting training data from different sites. It is also clear from the results that there is a high variance between different methods, in particular when complex data mixture is applied. Biomass is difficult to assess for dense forests, as pixels are saturated. This must be considered when planning field-data collection, with more samples in dense forest to provide more robust estimators from the training phase. The SAR-only (PALSAR) method from eq. 4 provided the most bias in results, overestimating with respect to the other methods.
{"title":"Assessment of Volume and Above-Ground Biomass in Araucaria Forest Through Satellite Images, Comparing Different Methods in the South of Chile","authors":"F. Pirotti, E. Kutchartt, E. Csaplovics","doi":"10.1109/LAGIRS48042.2020.9165668","DOIUrl":"https://doi.org/10.1109/LAGIRS48042.2020.9165668","url":null,"abstract":"Initial results of biomass estimation in the La Fusta area from existing equations found in literature are presented. As expected, accuracy of general equations suffer from the equation coefficients being obtained from fitting training data from different sites. It is also clear from the results that there is a high variance between different methods, in particular when complex data mixture is applied. Biomass is difficult to assess for dense forests, as pixels are saturated. This must be considered when planning field-data collection, with more samples in dense forest to provide more robust estimators from the training phase. The SAR-only (PALSAR) method from eq. 4 provided the most bias in results, overestimating with respect to the other methods.","PeriodicalId":111863,"journal":{"name":"2020 IEEE Latin American GRSS & ISPRS Remote Sensing Conference (LAGIRS)","volume":"6 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":"134146045","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/LAGIRS48042.2020.9165628
R. C. dos Santos, M. Galo, A. C. Carrilho, G. G. Pessoa, R. A. R. de Oliveira
The automatic detection of building changes is an essential process for urban area monitoring, urban planning, and database update. In this context, 3D information derived from multi-temporal airborne LiDAR scanning is one effective alternative. Despite several works in the literature, the separation of change areas in building and non-building remains a challenge. In this sense, it is proposed a new method for building change detection, having as the main contribution the use of height entropy concept to identify the building change areas. The experiments were performed considering multi-temporal airborne LiDAR data from 2012 and 2014, both with average density around 5 points/m2. Qualitative and quantitative analyses indicate that the proposed method is robust in building change detection, having the potential to identify small changes (larger than 20 m2). In general, the change detection method presented average completeness and correctness around 97% and 71%, respectively.
{"title":"Automatic Building Change Detection Using Multi-Temporal Airborne Lidar Data","authors":"R. C. dos Santos, M. Galo, A. C. Carrilho, G. G. Pessoa, R. A. R. de Oliveira","doi":"10.1109/LAGIRS48042.2020.9165628","DOIUrl":"https://doi.org/10.1109/LAGIRS48042.2020.9165628","url":null,"abstract":"The automatic detection of building changes is an essential process for urban area monitoring, urban planning, and database update. In this context, 3D information derived from multi-temporal airborne LiDAR scanning is one effective alternative. Despite several works in the literature, the separation of change areas in building and non-building remains a challenge. In this sense, it is proposed a new method for building change detection, having as the main contribution the use of height entropy concept to identify the building change areas. The experiments were performed considering multi-temporal airborne LiDAR data from 2012 and 2014, both with average density around 5 points/m2. Qualitative and quantitative analyses indicate that the proposed method is robust in building change detection, having the potential to identify small changes (larger than 20 m2). In general, the change detection method presented average completeness and correctness around 97% and 71%, respectively.","PeriodicalId":111863,"journal":{"name":"2020 IEEE Latin American GRSS & ISPRS Remote Sensing Conference (LAGIRS)","volume":"89 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":"131825573","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：