Pub Date : 2017-07-25DOI: 10.1109/IGARSS.2017.8127958
T. Jagdhuber, M. Baur, M. Link, M. Piles, D. Entekhabi, C. Montzka, Jaakko Seppänen, O. Antropov, J. Praks, A. Loew
Vegetation optical depth and scattering albedo are crucial parameters within the widely used τ-ω model for passive microwave remote sensing of vegetation and soil. A multi-sensor data integration approach using ICESat lidar vegetation heights and SMAP radar as well as radiometer data enables a direct retrieval of the two parameters on a physics-derived basis. The crucial step within the retrieval methodology is the calculus of the vegetation scattering coefficient KS, where one exact and three approximated solutions are provided. It is shown that, when using the assumption of a randomly oriented volume, the backscatter measurements of the radar provide a sufficient first order estimate and subsequently lead to effective estimates of vegetation optical depth and scattering albedo acquired with the novel multi-sensor approach.
{"title":"PHYSICS-based retrieval of scattering albedo and vegetation optical depth using multi-sensor data integration","authors":"T. Jagdhuber, M. Baur, M. Link, M. Piles, D. Entekhabi, C. Montzka, Jaakko Seppänen, O. Antropov, J. Praks, A. Loew","doi":"10.1109/IGARSS.2017.8127958","DOIUrl":"https://doi.org/10.1109/IGARSS.2017.8127958","url":null,"abstract":"Vegetation optical depth and scattering albedo are crucial parameters within the widely used τ-ω model for passive microwave remote sensing of vegetation and soil. A multi-sensor data integration approach using ICESat lidar vegetation heights and SMAP radar as well as radiometer data enables a direct retrieval of the two parameters on a physics-derived basis. The crucial step within the retrieval methodology is the calculus of the vegetation scattering coefficient KS, where one exact and three approximated solutions are provided. It is shown that, when using the assumption of a randomly oriented volume, the backscatter measurements of the radar provide a sufficient first order estimate and subsequently lead to effective estimates of vegetation optical depth and scattering albedo acquired with the novel multi-sensor approach.","PeriodicalId":6466,"journal":{"name":"2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)","volume":"24 1","pages":"4322-4325"},"PeriodicalIF":0.0,"publicationDate":"2017-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81099179","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 : 2017-07-25DOI: 10.1109/IGARSS.2017.8127281
S. Jacobsen, A. Pleskachevsky, S. Singha, A. Frost, D. Velotto
The number of offshore wind facilities is increasing with a proportionate decline in fossil and nuclear power production. The study of turbulent wakes inside a turbine cluster is a very important topic in order to optimize cluster layout for power production. With an increasing density of wind farms in the exclusive economic zone (EEZ) of a country, shadowing effects of wind farms on adjacent clusters are becoming an important issue for wind farm performance and need to be investigated to improve power harvest predictions. We present a comparative study of wind fields of different resolutions and coverages derived from TerraSAR-X and Sentinel-1 images. We elucidate the benefits of certain data for particular applications.
{"title":"SAR-based wind fields over offshore wind farms — A valuable tool for planning, monitoring and optimization","authors":"S. Jacobsen, A. Pleskachevsky, S. Singha, A. Frost, D. Velotto","doi":"10.1109/IGARSS.2017.8127281","DOIUrl":"https://doi.org/10.1109/IGARSS.2017.8127281","url":null,"abstract":"The number of offshore wind facilities is increasing with a proportionate decline in fossil and nuclear power production. The study of turbulent wakes inside a turbine cluster is a very important topic in order to optimize cluster layout for power production. With an increasing density of wind farms in the exclusive economic zone (EEZ) of a country, shadowing effects of wind farms on adjacent clusters are becoming an important issue for wind farm performance and need to be investigated to improve power harvest predictions. We present a comparative study of wind fields of different resolutions and coverages derived from TerraSAR-X and Sentinel-1 images. We elucidate the benefits of certain data for particular applications.","PeriodicalId":6466,"journal":{"name":"2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)","volume":"2 1","pages":"1611-1613"},"PeriodicalIF":0.0,"publicationDate":"2017-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91296508","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}
Remote sensing images often suffer from cloud cover. Cloud removal is required in many applications of remote sensing images. Multitemporal-based methods are popular and effective to cope with thick clouds. This paper contributes to a summarization and experimental comparation of the existing multitemporal-based methods. Furthermore, we propose a spatiotemporal-fusion with poisson-adjustment method to fuse multi-sensor and multitemporal images for cloud removal. The experimental results show that the proposed method is able to obtain more accurate results than the current multitemporal-based methods, especially when the multi-temporal images suffer from significant changes.
{"title":"Cloud removal by fusing multi-source and multi-temporal images","authors":"Chengyue Zhang, Zhiwei Li, Qing Cheng, Xinghua Li, Huanfeng Shen","doi":"10.1109/IGARSS.2017.8127522","DOIUrl":"https://doi.org/10.1109/IGARSS.2017.8127522","url":null,"abstract":"Remote sensing images often suffer from cloud cover. Cloud removal is required in many applications of remote sensing images. Multitemporal-based methods are popular and effective to cope with thick clouds. This paper contributes to a summarization and experimental comparation of the existing multitemporal-based methods. Furthermore, we propose a spatiotemporal-fusion with poisson-adjustment method to fuse multi-sensor and multitemporal images for cloud removal. The experimental results show that the proposed method is able to obtain more accurate results than the current multitemporal-based methods, especially when the multi-temporal images suffer from significant changes.","PeriodicalId":6466,"journal":{"name":"2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)","volume":"52 1","pages":"2577-2580"},"PeriodicalIF":0.0,"publicationDate":"2017-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85803026","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 : 2017-07-25DOI: 10.1109/IGARSS.2017.8127330
Zilong Zhong, Jonathan Li, Lingfei Ma, Han Jiang, He Zhao
Deep neural networks can learn deep feature representation for hyperspectral image (HSI) interpretation and achieve high classification accuracy in different datasets. However, counterintuitively, the classification performance of deep learning models degrades as their depth increases. Therefore, we add identity mappings to convolutional neural networks for every two convolutional layers to build deep residual networks (ResNets). To study the influence of deep learning model size on HSI classification accuracy, this paper applied ResNets and CNNs with different depth and width using two challenging datasets. Moreover, we tested the effectiveness of batch normalization as a regularization method with different model settings. The experimental results demonstrate that ResNets mitigate the declining-accuracy effect and achieved promising classification performance with 10% and 5% training sample percentages for the University of Pavia and Indian Pines datasets, respectively. In addition, t-Distributed Stochastic Neighbor Embedding (t-SNE) provides a direct view of the extracted features through dimensionality reduction.
{"title":"Deep residual networks for hyperspectral image classification","authors":"Zilong Zhong, Jonathan Li, Lingfei Ma, Han Jiang, He Zhao","doi":"10.1109/IGARSS.2017.8127330","DOIUrl":"https://doi.org/10.1109/IGARSS.2017.8127330","url":null,"abstract":"Deep neural networks can learn deep feature representation for hyperspectral image (HSI) interpretation and achieve high classification accuracy in different datasets. However, counterintuitively, the classification performance of deep learning models degrades as their depth increases. Therefore, we add identity mappings to convolutional neural networks for every two convolutional layers to build deep residual networks (ResNets). To study the influence of deep learning model size on HSI classification accuracy, this paper applied ResNets and CNNs with different depth and width using two challenging datasets. Moreover, we tested the effectiveness of batch normalization as a regularization method with different model settings. The experimental results demonstrate that ResNets mitigate the declining-accuracy effect and achieved promising classification performance with 10% and 5% training sample percentages for the University of Pavia and Indian Pines datasets, respectively. In addition, t-Distributed Stochastic Neighbor Embedding (t-SNE) provides a direct view of the extracted features through dimensionality reduction.","PeriodicalId":6466,"journal":{"name":"2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)","volume":"3 4 1","pages":"1824-1827"},"PeriodicalIF":0.0,"publicationDate":"2017-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90584732","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 : 2017-07-24DOI: 10.1109/igarss.2017.8127602
M. Baur, T. Jagdhuber, M. Link, M. Piles, D. Entekhabi, A. Fink
In this study the framework of the τ — ω model is used to derive vegetation loss coefficients and canopy penetration depths from SMAP multi-temporal retrievals of vegetation optical depth, single scattering albedo and ICESat lidar vegetation heights. The vegetation loss coefficients serve as a global indicator of how strong absorption and scattering processes attenuate L-band microwave radiation. By inverting the vegetation loss coefficients, penetration depths into the canopy can be obtained, which are displayed for the global forest reservoirs. A simple penetration index is formed combining vegetation heights and penetration depth estimates. The distribution and level of this index reveal that for densely forested areas in the tropics the soil signal is attenuated considerably, and this attenuation must be carefully accounted for in soil moisture retrieval algorithms.
{"title":"Estimation of vegetation loss coefficients and canopy penetration depths from smap radiometer and ICESat lidar data","authors":"M. Baur, T. Jagdhuber, M. Link, M. Piles, D. Entekhabi, A. Fink","doi":"10.1109/igarss.2017.8127602","DOIUrl":"https://doi.org/10.1109/igarss.2017.8127602","url":null,"abstract":"In this study the framework of the τ — ω model is used to derive vegetation loss coefficients and canopy penetration depths from SMAP multi-temporal retrievals of vegetation optical depth, single scattering albedo and ICESat lidar vegetation heights. The vegetation loss coefficients serve as a global indicator of how strong absorption and scattering processes attenuate L-band microwave radiation. By inverting the vegetation loss coefficients, penetration depths into the canopy can be obtained, which are displayed for the global forest reservoirs. A simple penetration index is formed combining vegetation heights and penetration depth estimates. The distribution and level of this index reveal that for densely forested areas in the tropics the soil signal is attenuated considerably, and this attenuation must be carefully accounted for in soil moisture retrieval algorithms.","PeriodicalId":6466,"journal":{"name":"2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)","volume":"68 1","pages":"2891-2894"},"PeriodicalIF":0.0,"publicationDate":"2017-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89195482","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 : 2017-07-24DOI: 10.1109/IGARSS.2017.8127315
Clement Rambour, L. Denis, F. Tupin, J. Nicolas, H. Oriot, L. Ferro-Famil, C. Deledalle
Starting from a stack of co-registered SAR images in interferometric configuration, SAR tomography performs a reconstruction of the reflectivity of scatterers in 3-D. Several scatterers observed within the same resolution cell of each SAR image can be separated by jointly unmixing the SAR complex amplitude observed throughout the stack. To achieve a reliable tomographic reconstruction, it is necessary to estimate locally the SAR covariance matrix by performing some spatial averaging. This necessary averaging step introduces some resolution loss and can bias the tomographic reconstruction by mistakenly including the response of scatterers located within the averaging area but outside the resolution cell of interest. This paper addresses the problem of identifying pixels corresponding to similar tomographic content, i.e., pixels that can be safely averaged prior to tomographic reconstruction. We derive a similarity criterion adapted to SAR tomography and compare its performance with existing criteria on a stack of Spotlight TerraSAR-X images.
{"title":"Similarity criterion for SAR tomography over dense urban area","authors":"Clement Rambour, L. Denis, F. Tupin, J. Nicolas, H. Oriot, L. Ferro-Famil, C. Deledalle","doi":"10.1109/IGARSS.2017.8127315","DOIUrl":"https://doi.org/10.1109/IGARSS.2017.8127315","url":null,"abstract":"Starting from a stack of co-registered SAR images in interferometric configuration, SAR tomography performs a reconstruction of the reflectivity of scatterers in 3-D. Several scatterers observed within the same resolution cell of each SAR image can be separated by jointly unmixing the SAR complex amplitude observed throughout the stack. To achieve a reliable tomographic reconstruction, it is necessary to estimate locally the SAR covariance matrix by performing some spatial averaging. This necessary averaging step introduces some resolution loss and can bias the tomographic reconstruction by mistakenly including the response of scatterers located within the averaging area but outside the resolution cell of interest. This paper addresses the problem of identifying pixels corresponding to similar tomographic content, i.e., pixels that can be safely averaged prior to tomographic reconstruction. We derive a similarity criterion adapted to SAR tomography and compare its performance with existing criteria on a stack of Spotlight TerraSAR-X images.","PeriodicalId":6466,"journal":{"name":"2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)","volume":"70 1","pages":"1760-1763"},"PeriodicalIF":0.0,"publicationDate":"2017-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89416816","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 : 2017-07-24DOI: 10.1109/IGARSS.2017.8127500
N. Das, D. Entekhabi, Seungbum Kim, T. Jagdhuber, R. Dunbar, S. Yueh, A. Colliander
SMAP project is working on a new and enhanced high-resolution (3km and 1km) soil moisture product. This product will combine SMAP radiometer data and Sentinel-1A and -1B data, and it will use the heritage SMAP active-passive approach. However, modifications in the SMAP active-passive algorithm are done to accommodate the Sentinel-1A and -1B C-band SAR data. Tests of the SMAP and Sentinel active-passive algorithm has been conducted and results show great promise for the high-resolution soil moisture data. The beta version of this product will be released to public in end of the March, 2017. This high-resolution (1 km and 3 km) soil moisture product will be useful for agriculture, flooding, watershed and rangeland management, and ecological and hydrological applications. Specific examples of interest will be shown from the proposed product for the above mention geophysical applications.
{"title":"High-resolution enhanced product based on SMAP active-passive approach using Sentinel 1 data and its applications","authors":"N. Das, D. Entekhabi, Seungbum Kim, T. Jagdhuber, R. Dunbar, S. Yueh, A. Colliander","doi":"10.1109/IGARSS.2017.8127500","DOIUrl":"https://doi.org/10.1109/IGARSS.2017.8127500","url":null,"abstract":"SMAP project is working on a new and enhanced high-resolution (3km and 1km) soil moisture product. This product will combine SMAP radiometer data and Sentinel-1A and -1B data, and it will use the heritage SMAP active-passive approach. However, modifications in the SMAP active-passive algorithm are done to accommodate the Sentinel-1A and -1B C-band SAR data. Tests of the SMAP and Sentinel active-passive algorithm has been conducted and results show great promise for the high-resolution soil moisture data. The beta version of this product will be released to public in end of the March, 2017. This high-resolution (1 km and 3 km) soil moisture product will be useful for agriculture, flooding, watershed and rangeland management, and ecological and hydrological applications. Specific examples of interest will be shown from the proposed product for the above mention geophysical applications.","PeriodicalId":6466,"journal":{"name":"2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)","volume":"247 3‐9","pages":"2493-2494"},"PeriodicalIF":0.0,"publicationDate":"2017-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91422082","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 : 2017-07-24DOI: 10.1109/IGARSS.2017.8127913
M. Link, D. Entekhabi, T. Jagdhuber, P. Ferrazzoli, L. Guerriero, M. Baur, R. Ludwig
The NASA Soil Moisture Active Passive (SMAP) mission aims to disaggregate L-band microwave brightness temperatures (∼40 km2) with finer resolution radar backscatter (1–3 km2) to obtain an intermediate resolution soil moisture product. The disaggregation is based on a linear functional relationship between backscatter and emissivity microwave observations that is captured by a covariation parameter β. Since SMAP's L-Band radar has stopped operations in July 2015, the substitution of Sentinel 1's C-Band radar for an operational soil moisture product is in preparation. However, while multiple studies have provided understanding of active-passive covariation for the L/L-Band case, little is known about the C/L-Band case. We utilize the Tor Vergata discrete backscatter and emission model to simulate growing wheat and corn stands and calculate the covariation parameter β for the L/L-Band and C/L-Band case. The study aims to provide insights into the strength, temporal dynamics and underlying scattering mechanisms of active-passive covariation for different vegetation types and frequency combinations. Our results indicate that for the C/L-Band case, vegetation cover limitations are generally more severe, and different β-dynamics and underlying scattering mechanisms are observed with respect to the L/L-Band case.
{"title":"Simulating L/L-band and C/L-band active-passive microwave covariation of crops with the Tor Vergata scattering and emission model for a SMAP-Sentinel 1 combination","authors":"M. Link, D. Entekhabi, T. Jagdhuber, P. Ferrazzoli, L. Guerriero, M. Baur, R. Ludwig","doi":"10.1109/IGARSS.2017.8127913","DOIUrl":"https://doi.org/10.1109/IGARSS.2017.8127913","url":null,"abstract":"The NASA Soil Moisture Active Passive (SMAP) mission aims to disaggregate L-band microwave brightness temperatures (∼40 km2) with finer resolution radar backscatter (1–3 km2) to obtain an intermediate resolution soil moisture product. The disaggregation is based on a linear functional relationship between backscatter and emissivity microwave observations that is captured by a covariation parameter β. Since SMAP's L-Band radar has stopped operations in July 2015, the substitution of Sentinel 1's C-Band radar for an operational soil moisture product is in preparation. However, while multiple studies have provided understanding of active-passive covariation for the L/L-Band case, little is known about the C/L-Band case. We utilize the Tor Vergata discrete backscatter and emission model to simulate growing wheat and corn stands and calculate the covariation parameter β for the L/L-Band and C/L-Band case. The study aims to provide insights into the strength, temporal dynamics and underlying scattering mechanisms of active-passive covariation for different vegetation types and frequency combinations. Our results indicate that for the C/L-Band case, vegetation cover limitations are generally more severe, and different β-dynamics and underlying scattering mechanisms are observed with respect to the L/L-Band case.","PeriodicalId":6466,"journal":{"name":"2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)","volume":"43 1","pages":"4143-4146"},"PeriodicalIF":0.0,"publicationDate":"2017-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76918631","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 : 2017-07-24DOI: 10.1109/IGARSS.2017.8126966
A. Frost, S. Jacobsen, S. Singha
High resolution sea ice drift fields, the location and extend of converging and diverging zones as well as ice ridges are most important parameters for ship navigation in ice infested waters. In this paper, we present the prototype of a new processor which is aimed to derive the surface ice parameters on the basis of pairs of space-borne Synthetic Aperture Radar (SAR) data of the same and of different sensors, i.e. from data of different bands, resolutions, and orbits. The study is carried out on image data collected during a joint campaign with the Office of Naval Research (ONR) in the western Arctic in 2015. The algorithm proposed is foreseen to be integrated into near-real time (NRT) processing chain at DLR ground stations in order to provide time-critical information as soon as possible to users and stakeholders.
{"title":"High resolution sea ice drift estimation using combined TerraSAR-X and RADARSAT-2 data: First tests","authors":"A. Frost, S. Jacobsen, S. Singha","doi":"10.1109/IGARSS.2017.8126966","DOIUrl":"https://doi.org/10.1109/IGARSS.2017.8126966","url":null,"abstract":"High resolution sea ice drift fields, the location and extend of converging and diverging zones as well as ice ridges are most important parameters for ship navigation in ice infested waters. In this paper, we present the prototype of a new processor which is aimed to derive the surface ice parameters on the basis of pairs of space-borne Synthetic Aperture Radar (SAR) data of the same and of different sensors, i.e. from data of different bands, resolutions, and orbits. The study is carried out on image data collected during a joint campaign with the Office of Naval Research (ONR) in the western Arctic in 2015. The algorithm proposed is foreseen to be integrated into near-real time (NRT) processing chain at DLR ground stations in order to provide time-critical information as soon as possible to users and stakeholders.","PeriodicalId":6466,"journal":{"name":"2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)","volume":"4 1","pages":"342-345"},"PeriodicalIF":0.0,"publicationDate":"2017-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74778044","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 : 2017-07-23DOI: 10.1109/IGARSS.2017.8127659
Pooja Shah, T. Zaveri, Raj Kumar, S. Sharma, Darshan Patel
Oil spill is a growing threat to marine eco-system, and it continues to grow with the growing marine traffic. Intentional or accidental oil discharges in the ocean are not limited to endangering marine eco-system but also coastal zones where the accumulated oil spill reaches as remains in form of tar. Automation of oil spill detection is challenging from SAR data. It is also surveyed that free and open source software (FOSS) solution for oceanographic applications is rare but essential for the scientists who are working in this area. Proposed FOSS framework also provides flexibility to apply standard data processing algorithms for the SAR data processing. In this paper, proposed FOSS framework to process C band RISAT-1 SAR data is described. This paper also provides the comparative study on shortcomings of the widely accepted tools for oil spill detection. The experimental results of super-pixel based segmentation technique for dark spot detection are described using proposed FOSS framework.
{"title":"Research oriented foss solution for automatic oil spill detection using risat-1 sar data","authors":"Pooja Shah, T. Zaveri, Raj Kumar, S. Sharma, Darshan Patel","doi":"10.1109/IGARSS.2017.8127659","DOIUrl":"https://doi.org/10.1109/IGARSS.2017.8127659","url":null,"abstract":"Oil spill is a growing threat to marine eco-system, and it continues to grow with the growing marine traffic. Intentional or accidental oil discharges in the ocean are not limited to endangering marine eco-system but also coastal zones where the accumulated oil spill reaches as remains in form of tar. Automation of oil spill detection is challenging from SAR data. It is also surveyed that free and open source software (FOSS) solution for oceanographic applications is rare but essential for the scientists who are working in this area. Proposed FOSS framework also provides flexibility to apply standard data processing algorithms for the SAR data processing. In this paper, proposed FOSS framework to process C band RISAT-1 SAR data is described. This paper also provides the comparative study on shortcomings of the widely accepted tools for oil spill detection. The experimental results of super-pixel based segmentation technique for dark spot detection are described using proposed FOSS framework.","PeriodicalId":6466,"journal":{"name":"2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)","volume":"63 1","pages":"3121-3124"},"PeriodicalIF":0.0,"publicationDate":"2017-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75191866","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：