Pub Date : 2015-11-12DOI: 10.1109/IGARSS.2015.7326494
A. Budillon, Gilda Schirinzi
In this paper we investigate SAR image compression based on sparse representation. Two approaches are considered: the first one is based on the use of an Overcomplete ICA transform coding method, the second one is based on Compressive Sensing (CS). In both cases an Overcomplete ICA representation is used as sparse representation, but while in the first case the significant overcomplete ICA coefficients are coded using an optimal entropy constrained threshold quantizer, in the latter case a reduced number of measurements obtained combining the SAR image pixels through a random measurement matrix are directly coded. Numerical results on TerraSAR-X images are presented.
{"title":"SAR image compression based on sparsity","authors":"A. Budillon, Gilda Schirinzi","doi":"10.1109/IGARSS.2015.7326494","DOIUrl":"https://doi.org/10.1109/IGARSS.2015.7326494","url":null,"abstract":"In this paper we investigate SAR image compression based on sparse representation. Two approaches are considered: the first one is based on the use of an Overcomplete ICA transform coding method, the second one is based on Compressive Sensing (CS). In both cases an Overcomplete ICA representation is used as sparse representation, but while in the first case the significant overcomplete ICA coefficients are coded using an optimal entropy constrained threshold quantizer, in the latter case a reduced number of measurements obtained combining the SAR image pixels through a random measurement matrix are directly coded. Numerical results on TerraSAR-X images are presented.","PeriodicalId":125717,"journal":{"name":"2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122952099","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 : 2015-11-12DOI: 10.1109/IGARSS.2015.7326292
A. Saranathan, M. Parente
Classical unmixing algorithms focus primarily on scenarios with a single mixture. These techniques are easily extensible in the case of images with multiple discrete mixtures (i.e. no shared endmembers). Unmixing in scenarios with multiple mixtures with shared or common endmembers is significantly harder. Manifold clustering and embedding seem tailor-made for such a scenario, but generally these algorithms focus on intersecting manifolds (i.e. manifolds that pass through each other) rather than adjoining manifolds (i.e. manifolds that share a boundary) as is the case with mixtures. In this paper we propose a NNMF based technique for simultaneous manifold clustering and embedding of adjoining manifolds. The algorithm is based on including a clustering term in the objective for finding an appropriate reconstruction matrix. The performance of the new algorithm is tested on a toy dataset made of a couple of simulated manifolds which share a boundary and a simulated dataset made up of two ternary Hapke mixtures with two shared endmembers. The algorithm shows improvements on the state-of-the-art manifold clustering algorithms in terms of both clustering and embedding.
{"title":"Simultaneous clustering and embedding for multiple intimate mixtures","authors":"A. Saranathan, M. Parente","doi":"10.1109/IGARSS.2015.7326292","DOIUrl":"https://doi.org/10.1109/IGARSS.2015.7326292","url":null,"abstract":"Classical unmixing algorithms focus primarily on scenarios with a single mixture. These techniques are easily extensible in the case of images with multiple discrete mixtures (i.e. no shared endmembers). Unmixing in scenarios with multiple mixtures with shared or common endmembers is significantly harder. Manifold clustering and embedding seem tailor-made for such a scenario, but generally these algorithms focus on intersecting manifolds (i.e. manifolds that pass through each other) rather than adjoining manifolds (i.e. manifolds that share a boundary) as is the case with mixtures. In this paper we propose a NNMF based technique for simultaneous manifold clustering and embedding of adjoining manifolds. The algorithm is based on including a clustering term in the objective for finding an appropriate reconstruction matrix. The performance of the new algorithm is tested on a toy dataset made of a couple of simulated manifolds which share a boundary and a simulated dataset made up of two ternary Hapke mixtures with two shared endmembers. The algorithm shows improvements on the state-of-the-art manifold clustering algorithms in terms of both clustering and embedding.","PeriodicalId":125717,"journal":{"name":"2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124048499","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 : 2015-11-12DOI: 10.1109/IGARSS.2015.7326451
Lan Li, E. Chen, Zeng-yuan Li, Q. Feng, Lei Zhao, Wen Yang
The objective of this paper is to derive DEM and DHM in tropical forests based on the technology of multi-baseline InSAR tomography, focusing on the requirement of the minimum number of flight tracks. The experiments were carried out on P-band HH polarization airborne multi-baseline InSAR data over the site of Paracou, French Guiana, during the European Space Agency campaign TropiSAR 2009. Tomographic processing was carried out by Capon spectral estimation technique with three-track observations, subsequently two elevation values with respect to the relative maximum peaks were retrieved representing DEM and DSM respectively. As expected, the retrieved DEM and DHM are found agreements with LiDAR measurements.
{"title":"DEM and DHM reconstruction in tropical forests: Tomographic results at P-band with three flight tracks","authors":"Lan Li, E. Chen, Zeng-yuan Li, Q. Feng, Lei Zhao, Wen Yang","doi":"10.1109/IGARSS.2015.7326451","DOIUrl":"https://doi.org/10.1109/IGARSS.2015.7326451","url":null,"abstract":"The objective of this paper is to derive DEM and DHM in tropical forests based on the technology of multi-baseline InSAR tomography, focusing on the requirement of the minimum number of flight tracks. The experiments were carried out on P-band HH polarization airborne multi-baseline InSAR data over the site of Paracou, French Guiana, during the European Space Agency campaign TropiSAR 2009. Tomographic processing was carried out by Capon spectral estimation technique with three-track observations, subsequently two elevation values with respect to the relative maximum peaks were retrieved representing DEM and DSM respectively. As expected, the retrieved DEM and DHM are found agreements with LiDAR measurements.","PeriodicalId":125717,"journal":{"name":"2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121362299","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 : 2015-11-12DOI: 10.1109/IGARSS.2015.7326553
M. Meroni, F. Rembold, M. Migliavacca, J. Ardö
Monitoring vegetation gross primary production (GPP) is required for both carbon balance studies and early warning systems aiming to detect unfavorable crop and pasture conditions. This manuscript describes the assimilation of MODIS observations by a simple process model, fed by meteorological data (temperature, incident radiation and rainfall) and linked with a canopy reflectance model, to estimate GPP. GPP simulations are benchmarked against eddy covariance data collected in a semi-arid environment of a sparse Savanna in the Sudan.
{"title":"Assimilation of satellite observations for the estimation of Savanna gross primary production","authors":"M. Meroni, F. Rembold, M. Migliavacca, J. Ardö","doi":"10.1109/IGARSS.2015.7326553","DOIUrl":"https://doi.org/10.1109/IGARSS.2015.7326553","url":null,"abstract":"Monitoring vegetation gross primary production (GPP) is required for both carbon balance studies and early warning systems aiming to detect unfavorable crop and pasture conditions. This manuscript describes the assimilation of MODIS observations by a simple process model, fed by meteorological data (temperature, incident radiation and rainfall) and linked with a canopy reflectance model, to estimate GPP. GPP simulations are benchmarked against eddy covariance data collected in a semi-arid environment of a sparse Savanna in the Sudan.","PeriodicalId":125717,"journal":{"name":"2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128766093","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 : 2015-11-12DOI: 10.1109/IGARSS.2015.7326783
W. Biamino, M. Borasi, M. Cavagnero, A. Croce, L. D. Matteo, F. Fontebasso, F. Tataranni, P. Trivero
A novel approach to land masking in synthetic aperture radar (SAR) images is designed and implemented. The developed algorithm takes as input an archived shoreline from a public domain database and modifies it to draw the actual shoreline on SAR images by analysing backscatter values. Starting with data from the GSHHS (the global self-consistent hierarchical high-resolution shoreline database), coastline positioning is improved by evaluating the radiometric intensity gradient in coastal areas of the SAR image. A further enhancement is obtained by applying the Canny edge detection algorithm. The methodology is tested on Envisat and ERS images, as well as on ALOS and COSMO SkyMed images.
{"title":"A “dynamic” land masking algorithm for synthetic aperture radar images","authors":"W. Biamino, M. Borasi, M. Cavagnero, A. Croce, L. D. Matteo, F. Fontebasso, F. Tataranni, P. Trivero","doi":"10.1109/IGARSS.2015.7326783","DOIUrl":"https://doi.org/10.1109/IGARSS.2015.7326783","url":null,"abstract":"A novel approach to land masking in synthetic aperture radar (SAR) images is designed and implemented. The developed algorithm takes as input an archived shoreline from a public domain database and modifies it to draw the actual shoreline on SAR images by analysing backscatter values. Starting with data from the GSHHS (the global self-consistent hierarchical high-resolution shoreline database), coastline positioning is improved by evaluating the radiometric intensity gradient in coastal areas of the SAR image. A further enhancement is obtained by applying the Canny edge detection algorithm. The methodology is tested on Envisat and ERS images, as well as on ALOS and COSMO SkyMed images.","PeriodicalId":125717,"journal":{"name":"2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130805508","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 : 2015-11-12DOI: 10.1109/IGARSS.2015.7326057
M. Costantini, F. Minati, M. G. Ciminelli, A. Ferretti, S. Costabile
The availability of long time series of interferometric data acquired all over the world from several synthetic aperture radar (SAR) satellite missions makes possible to perform a worldwide assessment of the terrain and infrastructure stability by persistent scatterer (PS) SAR interferometry techniques. This technology is computationally demanding, in particular because it requires a 3D processing. When applied to large areas, several problems have to be faced to handle huge amounts of data. In this work, we present a significant example of PS big data processing performed at national scale (the whole Italian territory) with ERS, Envisat and COSMO-SkyMed data. The main challenges and results related to this project are discussed, and the possible worldwide extension with Sentinel data is suggested.
{"title":"Nationwide ground deformation monitoring by persistent scatterer interferometry","authors":"M. Costantini, F. Minati, M. G. Ciminelli, A. Ferretti, S. Costabile","doi":"10.1109/IGARSS.2015.7326057","DOIUrl":"https://doi.org/10.1109/IGARSS.2015.7326057","url":null,"abstract":"The availability of long time series of interferometric data acquired all over the world from several synthetic aperture radar (SAR) satellite missions makes possible to perform a worldwide assessment of the terrain and infrastructure stability by persistent scatterer (PS) SAR interferometry techniques. This technology is computationally demanding, in particular because it requires a 3D processing. When applied to large areas, several problems have to be faced to handle huge amounts of data. In this work, we present a significant example of PS big data processing performed at national scale (the whole Italian territory) with ERS, Envisat and COSMO-SkyMed data. The main challenges and results related to this project are discussed, and the possible worldwide extension with Sentinel data is suggested.","PeriodicalId":125717,"journal":{"name":"2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121567466","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 : 2015-11-12DOI: 10.1109/IGARSS.2015.7326762
C. Munyati, N. I. Sinthumule
The coexistence of woody vegetation and grass characterises savannas. High spatial resolution digital satellite images and appropriate image processing algorithms can facilitate monitoring of the woody cover. Historical aerial photographs enable an extension of high spatial resolution analysis of the woody cover to periods before satellite imagery. This study tested a methodology that used historical (1998, 2012) SPOT-4 HRVIR gray scale (“red”) band (0.6-0.68um, 10m resolution) and SPOT-5 HRG panchromatic band (0.48-0.71 urn, 5m resolution) images in combination with panchromatic (0.4-0.7um) aerial photographs (1940, 1968, 1977; 0.44-1.35m resolution) in monitoring woody cover at sites in the Kruger National Park, South Africa. Mean Euclidean Distance texture analysis in 3×3 moving windows enhanced woody cover. The woody cover on the respective multitemporal texture images was extracted through K-means clustering, with high (>85%) indicative classification accuracy. Boolean GIS overlay analysis of the resulting woody cover thematic layers enabled woody cover change detection.
{"title":"Assessing woody vegetation cover dynamics in the Kruger National Park, South Africa: Linking historical aerial photographs and spot imagery","authors":"C. Munyati, N. I. Sinthumule","doi":"10.1109/IGARSS.2015.7326762","DOIUrl":"https://doi.org/10.1109/IGARSS.2015.7326762","url":null,"abstract":"The coexistence of woody vegetation and grass characterises savannas. High spatial resolution digital satellite images and appropriate image processing algorithms can facilitate monitoring of the woody cover. Historical aerial photographs enable an extension of high spatial resolution analysis of the woody cover to periods before satellite imagery. This study tested a methodology that used historical (1998, 2012) SPOT-4 HRVIR gray scale (“red”) band (0.6-0.68um, 10m resolution) and SPOT-5 HRG panchromatic band (0.48-0.71 urn, 5m resolution) images in combination with panchromatic (0.4-0.7um) aerial photographs (1940, 1968, 1977; 0.44-1.35m resolution) in monitoring woody cover at sites in the Kruger National Park, South Africa. Mean Euclidean Distance texture analysis in 3×3 moving windows enhanced woody cover. The woody cover on the respective multitemporal texture images was extracted through K-means clustering, with high (>85%) indicative classification accuracy. Boolean GIS overlay analysis of the resulting woody cover thematic layers enabled woody cover change detection.","PeriodicalId":125717,"journal":{"name":"2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124406135","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 : 2015-11-12DOI: 10.1109/IGARSS.2015.7327015
V. Nandan, John J. Jacket, J. P. Gill, T. Geldsetzer, M. Fuller
This study explores the potential of a multi-frequency (Ku-, X- and C-band) scatterometry approach, to understand microwave interactions between teo statistically different snow thickness covers (14cm and 8cm) on first-year Arctic sea ice during the late winter to early-melt season transition. The results show substantial differences in backscatter response from all three frequencies, for both snow covers. Highly-saline snow covers with fluctuating snow geophysical and thermodynamic properties cause these backscatter fluctuations, with contributions from surface and volume scattering from different snow layers and interfaces. C-band exhibited drastic variations in backscatter, especially for the 14cm snow cover, when compared to Ku- and X-band. In the case of 8cm snow cover, all the three frequencies show minimal sensitivity to snow electro-thermo-physical properties. Our results show distinctly different snow thermodynamic processes operating within the different snow layers, essential for snow thickness estimation on first-year sea ice using active microwave remote sensing approaches.
{"title":"Multi-frequency polarimetric microwave observations of snow cover on first-year Arctic sea ice","authors":"V. Nandan, John J. Jacket, J. P. Gill, T. Geldsetzer, M. Fuller","doi":"10.1109/IGARSS.2015.7327015","DOIUrl":"https://doi.org/10.1109/IGARSS.2015.7327015","url":null,"abstract":"This study explores the potential of a multi-frequency (Ku-, X- and C-band) scatterometry approach, to understand microwave interactions between teo statistically different snow thickness covers (14cm and 8cm) on first-year Arctic sea ice during the late winter to early-melt season transition. The results show substantial differences in backscatter response from all three frequencies, for both snow covers. Highly-saline snow covers with fluctuating snow geophysical and thermodynamic properties cause these backscatter fluctuations, with contributions from surface and volume scattering from different snow layers and interfaces. C-band exhibited drastic variations in backscatter, especially for the 14cm snow cover, when compared to Ku- and X-band. In the case of 8cm snow cover, all the three frequencies show minimal sensitivity to snow electro-thermo-physical properties. Our results show distinctly different snow thermodynamic processes operating within the different snow layers, essential for snow thickness estimation on first-year sea ice using active microwave remote sensing approaches.","PeriodicalId":125717,"journal":{"name":"2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126026109","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 : 2015-11-12DOI: 10.1109/IGARSS.2015.7326709
S. Leinss, J. Lemmetyinen, A. Wiesmann, I. Hajnsek
Dry snow can be considered as a transparent but refractive medium which causes a phase delay in the reflected signal of active radar remote sensing systems. Here, we analyze the phase delay to estimate Snow Water Equivalent (SWE), the depth of fresh snow and the anisotropic orientation of ice grains in the snow volume. SWE is determined from the integrated phase shift measured by differential interferometry. The temporal evolution of the snow anisotropy could be observed because different microwave polarizations show different propagation speeds in anisotropic snow. The depth of fresh snow as well as snow metamorphosis is discussed with respect to characteristic phase-shifts in the co-polar phase difference. Ground based radar observations from the Snow-scat instrument installed at a test site near Sodankylä, Finland, form the data basis for this paper.
{"title":"Interferometric and polarimetric methods to determine SWE, fresh snow depth and the anisotropy of dry snow","authors":"S. Leinss, J. Lemmetyinen, A. Wiesmann, I. Hajnsek","doi":"10.1109/IGARSS.2015.7326709","DOIUrl":"https://doi.org/10.1109/IGARSS.2015.7326709","url":null,"abstract":"Dry snow can be considered as a transparent but refractive medium which causes a phase delay in the reflected signal of active radar remote sensing systems. Here, we analyze the phase delay to estimate Snow Water Equivalent (SWE), the depth of fresh snow and the anisotropic orientation of ice grains in the snow volume. SWE is determined from the integrated phase shift measured by differential interferometry. The temporal evolution of the snow anisotropy could be observed because different microwave polarizations show different propagation speeds in anisotropic snow. The depth of fresh snow as well as snow metamorphosis is discussed with respect to characteristic phase-shifts in the co-polar phase difference. Ground based radar observations from the Snow-scat instrument installed at a test site near Sodankylä, Finland, form the data basis for this paper.","PeriodicalId":125717,"journal":{"name":"2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)","volume":"146 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116445379","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 : 2015-11-12DOI: 10.1109/IGARSS.2015.7325961
Haris Ahmad Khan, M. Khan, K. Khurshid, J. Chanussot
The problem with visualization of hyper-spectral images on tri-stimulus displays arises from the fact that they contain hundreds of spectral bands while generally used display devices support only three bands/channels namely blue, green and red. Therefore, for visualization a hyper-spectral (HS) image has to be reduced to three bands. The main challenge while performing this band reduction is to retain and display the maximum information available in a hyper-spectral image. Human visual system focuses attention on certain regions in images called “salient regions”. Therefore to provide a comprehensive representation of hyper-spectral data on tri-stimulus displays we propose to use a weighted fusion method of saliency maps and hyper-spectral bands. The efficacy of the proposed algorithm has been demonstrated by tests on both urban and countryside images of AVIRIS and ROSIS sensors.
{"title":"Saliency based visualization of hyper-spectral images","authors":"Haris Ahmad Khan, M. Khan, K. Khurshid, J. Chanussot","doi":"10.1109/IGARSS.2015.7325961","DOIUrl":"https://doi.org/10.1109/IGARSS.2015.7325961","url":null,"abstract":"The problem with visualization of hyper-spectral images on tri-stimulus displays arises from the fact that they contain hundreds of spectral bands while generally used display devices support only three bands/channels namely blue, green and red. Therefore, for visualization a hyper-spectral (HS) image has to be reduced to three bands. The main challenge while performing this band reduction is to retain and display the maximum information available in a hyper-spectral image. Human visual system focuses attention on certain regions in images called “salient regions”. Therefore to provide a comprehensive representation of hyper-spectral data on tri-stimulus displays we propose to use a weighted fusion method of saliency maps and hyper-spectral bands. The efficacy of the proposed algorithm has been demonstrated by tests on both urban and countryside images of AVIRIS and ROSIS sensors.","PeriodicalId":125717,"journal":{"name":"2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132997865","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：