Pub Date : 2012-12-31DOI: 10.1109/PPRS.2012.6398320
S. Mikeš, M. Haindl, G. Scarpa
In this work we present the enrichment of the Prague texture segmentation data-generator and benchmark (PTSDB) also for the assessment of the remote sensing image segmenters. The PTSDB tool is a web based (http://mosaic.utia.cas.cz) service designed for real-time performance evaluation, mutual comparison, and ranking of various supervised or unsupervised static or dynamic image segmenters. PTSDB supports rapid verification and development of new segmentation approaches. The remote sensing datasets contain tenspectral ALI satellite images and their RGB subsets, with optional additive noise resistance checking. Alternative setting options allow to test also scale, rotation or illumination invariance. The benchmark functionality is demonstrated by testing and comparing six remote sensing segmentation algorithms.
{"title":"Remote sensing segmentation benchmark","authors":"S. Mikeš, M. Haindl, G. Scarpa","doi":"10.1109/PPRS.2012.6398320","DOIUrl":"https://doi.org/10.1109/PPRS.2012.6398320","url":null,"abstract":"In this work we present the enrichment of the Prague texture segmentation data-generator and benchmark (PTSDB) also for the assessment of the remote sensing image segmenters. The PTSDB tool is a web based (http://mosaic.utia.cas.cz) service designed for real-time performance evaluation, mutual comparison, and ranking of various supervised or unsupervised static or dynamic image segmenters. PTSDB supports rapid verification and development of new segmentation approaches. The remote sensing datasets contain tenspectral ALI satellite images and their RGB subsets, with optional additive noise resistance checking. Alternative setting options allow to test also scale, rotation or illumination invariance. The benchmark functionality is demonstrated by testing and comparing six remote sensing segmentation algorithms.","PeriodicalId":139043,"journal":{"name":"7th IAPR Workshop on Pattern Recognition in Remote Sensing (PRRS)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125688521","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 : 2012-12-31DOI: 10.1109/PPRS.2012.6398315
K. Takasaki, T. Kaneko, A. Yasuda, H. Den, S. Tanaka
Some volcanoes show a kind of periodicity through the time series of volcano temperature. Analyzing the satellite data observed in 2012 from 2006, there are found six volcanoes in which the high temperature occurs in a periodic interval from half year to two years. The activity pattern appears like some kind of pulse train. There is a possibility of the periodical event which occurs according to the characteristic cause belonging to individual volcano. The pulse train of the Bezymianny volcanic activity from 1955 to present was studied in detail. A short period like 15 months is found. However then, what is a large event excluded from the periodic event? Is it an event in a long periodicity related with the crustal movement of the Earth? The authors make a guess at a model of the volcanic activity that actual volcanic activity appears as a result of adding a few kinds of the pulse trains by each different cause. It is a kind of energy discharge pattern with some continuous energy supply typically seen in a geyser at the Yellow Stone National Park in U.S.
{"title":"Study for the periodicity of volcanic activity using satellite data","authors":"K. Takasaki, T. Kaneko, A. Yasuda, H. Den, S. Tanaka","doi":"10.1109/PPRS.2012.6398315","DOIUrl":"https://doi.org/10.1109/PPRS.2012.6398315","url":null,"abstract":"Some volcanoes show a kind of periodicity through the time series of volcano temperature. Analyzing the satellite data observed in 2012 from 2006, there are found six volcanoes in which the high temperature occurs in a periodic interval from half year to two years. The activity pattern appears like some kind of pulse train. There is a possibility of the periodical event which occurs according to the characteristic cause belonging to individual volcano. The pulse train of the Bezymianny volcanic activity from 1955 to present was studied in detail. A short period like 15 months is found. However then, what is a large event excluded from the periodic event? Is it an event in a long periodicity related with the crustal movement of the Earth? The authors make a guess at a model of the volcanic activity that actual volcanic activity appears as a result of adding a few kinds of the pulse trains by each different cause. It is a kind of energy discharge pattern with some continuous energy supply typically seen in a geyser at the Yellow Stone National Park in U.S.","PeriodicalId":139043,"journal":{"name":"7th IAPR Workshop on Pattern Recognition in Remote Sensing (PRRS)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121220017","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 : 2012-12-31DOI: 10.1109/PPRS.2012.6398323
V. Fursov, A. Nikonorov, P. Yakimov
This paper considers a GPU implementation of a two-dimensional infinite impulse-response filter. The presented flexible allocation approach makes it possible to efficiently implement the polytope model in a single GPU kernel. Some theoretical performance estimations of the proposed flexible allocation algorithm are given in the paper. The proposed IIR filtering technique is efficient when applied to de-blurring satellite images of large size.
{"title":"Flexible allocation approach for GPU implementation of 2D IIR filters in satellite images processing","authors":"V. Fursov, A. Nikonorov, P. Yakimov","doi":"10.1109/PPRS.2012.6398323","DOIUrl":"https://doi.org/10.1109/PPRS.2012.6398323","url":null,"abstract":"This paper considers a GPU implementation of a two-dimensional infinite impulse-response filter. The presented flexible allocation approach makes it possible to efficiently implement the polytope model in a single GPU kernel. Some theoretical performance estimations of the proposed flexible allocation algorithm are given in the paper. The proposed IIR filtering technique is efficient when applied to de-blurring satellite images of large size.","PeriodicalId":139043,"journal":{"name":"7th IAPR Workshop on Pattern Recognition in Remote Sensing (PRRS)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133951862","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 : 2012-12-31DOI: 10.1109/PPRS.2012.6398317
Z. Long, Q. Du, N. Younan
In this paper, we explore hyperspectral feature extraction using the contourlet transform (CT), a promising multireolution analysis technique emerging in recent years. Hyperspectral imagery is first processed in the spectral domain with some decorrelation techniques. Then the nonsubsampled CT (NSCT) is applied in the spatial domain. The resulting NSCT coefficients are used as features for hyperspectral analysis. The spectral processing techniques being explored include one-dimensional discrete wavelet transform, principal component analysis, and band selection. The extracted features are tested in classification using support vector machine, which yield promising results.
{"title":"Hyperspectral feature extraction using contourlet transform","authors":"Z. Long, Q. Du, N. Younan","doi":"10.1109/PPRS.2012.6398317","DOIUrl":"https://doi.org/10.1109/PPRS.2012.6398317","url":null,"abstract":"In this paper, we explore hyperspectral feature extraction using the contourlet transform (CT), a promising multireolution analysis technique emerging in recent years. Hyperspectral imagery is first processed in the spectral domain with some decorrelation techniques. Then the nonsubsampled CT (NSCT) is applied in the spatial domain. The resulting NSCT coefficients are used as features for hyperspectral analysis. The spectral processing techniques being explored include one-dimensional discrete wavelet transform, principal component analysis, and band selection. The extracted features are tested in classification using support vector machine, which yield promising results.","PeriodicalId":139043,"journal":{"name":"7th IAPR Workshop on Pattern Recognition in Remote Sensing (PRRS)","volume":"126 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126054235","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 : 2012-11-01DOI: 10.1109/PPRS.2012.6398318
N. Ly, Q. Du, J. Fowler
In this paper, we investigate the performance of a sparsity-preserving graph embedding based approach, called l1 graph, in hyperspectral image dimensionality reduction (DR), and propose noise-adjusted sparsity-preserving (NASP) based DR when training samples are unavailable. In conjunction with the state-of-the-art hyperspectral image classifier, support vector machine with composite kernels (SVM-CK), the experimental study show that NASP can significantly improve the classification accuracy, compared to other widely used DR methods.
{"title":"Noise-adjusted sparsity-preserving-based dimensionality reduction for hyperspectral image classification","authors":"N. Ly, Q. Du, J. Fowler","doi":"10.1109/PPRS.2012.6398318","DOIUrl":"https://doi.org/10.1109/PPRS.2012.6398318","url":null,"abstract":"In this paper, we investigate the performance of a sparsity-preserving graph embedding based approach, called l1 graph, in hyperspectral image dimensionality reduction (DR), and propose noise-adjusted sparsity-preserving (NASP) based DR when training samples are unavailable. In conjunction with the state-of-the-art hyperspectral image classifier, support vector machine with composite kernels (SVM-CK), the experimental study show that NASP can significantly improve the classification accuracy, compared to other widely used DR methods.","PeriodicalId":139043,"journal":{"name":"7th IAPR Workshop on Pattern Recognition in Remote Sensing (PRRS)","volume":"128 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121982471","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：