Decision Fusion for the Classification of Hyperspectral Data: Outcome of the 2008 GRS-S Data Fusion Contest

Licciardi, Giorgio; Pacifici, Fabio; Tuia, Devis; Prasad, Saurabh; West, T.; Giacco, Ferdinando; Thiel, Christian; Inglada, Jordi; Christophe, Emmanuel; Chanussot, Jocelyn; Gamba, Paolo

doi:10.1109/tgrs.2009.2029340

Cited by 161 publications

(81 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Moreover, nonlinear relationships can be accounted for due to the kernel trick. SVMs are now widely used in the field of remote sensing not only for the purpose of hyperspectral image processing [12] but also for continuous variable estimation [10], [13]- [16].…”

mentioning

confidence: 99%

Support Vector Regression for the Estimation of Forest Stand Parameters Using Airborne Laser Scanning

Monnet¹,

Chanussot

Berger³

2011

IEEE Geosci. Remote Sensing Lett.

View full text Add to dashboard Cite

Abstract-Airborne laser scanning is nowadays widely used for the estimation of forest stand parameters. Prediction models have to deal with high-dimensional laser data sets as well as limited field calibration data. This problem is enhanced in mountainous areas where forest is highly heterogeneous and field data collection is costly. Artificial neural network models and support vector regression (SVR) have already demonstrated their ability to address such issues for species-specific plot volume prediction. In this letter, we compare the stand parameter prediction accuracies of support vector machines and ordinary least squares multiple-regression models for dominant height, basal area, mean diameter, and stem density. The sensitivity of these techniques to the input variables is investigated by testing data sets which include different numbers and types of laser metrics, and by reducing their dimension with principal component and independent component analyses. Whereas usual variables only reflect the vertical distribution, we also integrate the entropy of the horizontal distribution of the point cloud in the laser metrics. The results show that SVR prediction models are of similar accuracy with multiple-regression models but are more robust regarding the metrics included in the data sets. Preliminary dimension reduction of the data set by principal component analysis generally benefits more to SVR than to multiple regression. The optimal combination of laser metrics to be included in the data sets mainly depends on the forest parameter to be estimated.

show abstract

mentioning

confidence: 99%

Support Vector Regression for the Estimation of Forest Stand Parameters Using Airborne Laser Scanning

Monnet¹,

Chanussot

Berger³

2011

IEEE Geosci. Remote Sensing Lett.

View full text Add to dashboard Cite

show abstract

“…22 The overall result showed that SVM classification process employed has got very promising potential to discriminate crops and tree classes, with high classification accuracies, when combined with high spectral resolution hyperspectral remote sensing data. The high accuracy produced by the SVM classifier may be due to the ability of the algorithm to identify the optimally separating hyperplanes for classes in comparison to other pixel-based techniques (e.g., artificial neural networks) 14 which may not be able to find such optimal hyperplanes. Table 4.…”

Section: Classification Accuracy Assessmentmentioning

confidence: 99%

Land-Cover Classification for East Suez Canal Region Using Hyperspectral Eo-1 Data

Afify¹,

Sheta²,

Arafat³

et al. 2017

ECB

View full text Add to dashboard Cite

Earth Observation (EO-1) data provides a highest spectral resolution to get spectral information of Earth's Surface targets within 242 spectral bands at 30 m spatial resolution. In this context, the main objective of this paper is to produce a land cover map using hyperspectral data acquired by EO-1 Hyperion instrument over one test site. Atmospheric correction on the hyperspectral data was performed using ENVI's Fast Line-of-sight Atmospheric Analysis of Spectral Hyper-cubes (FLAASH) module. Support Vector Machine (SVM) classification was implemented on the dominant elements to produce a land cover map for test site. SVM is carried out in this research to deal with the multi-class issue of Hyperion data. Classification using the kernel functions in classification made the classifier robust against the outliers. The Land Cover Classification System (LCCS) was used to know the land cover classes. The result showed high accuracy for land cover map with machine learning classifier like SVM using hyperspectral remote sensing data. The overall classification accuracy obtained was 97.85.

show abstract

“…The overall result showed that SVM classification approach employed has got very promising potential to discriminate various soil salinity severity classes, with high classification accuracies, when combined with high spectral resolution hyperspectral remote sensing data. The overall high accuracy produced by the SVM classifier may be attributed to the ability of the algorithm to identify the optimally separating hyperplanes for classes in comparison to other pixel-based techniques (e.g., artificial neural networks) (Licciardi, et al, 2009) which may not be able to find such optimal hyperplanes. SVMs are also able to generalize this optimal separating hyperplane to unseen samples with the least errors among all separating hyperplanes.…”

Section: Accuracy Assessmentmentioning

confidence: 99%

Hyperspectral Remote Sensing in Characterizing Soil Salinity Severity using SVM Technique - A Case Study of Alluvial Plains

K¹,

Kumar²

2015

IJARSG

View full text Add to dashboard Cite

Hyperspectral remote sensing is widely used for analyzing and estimating the severity of soil salinity in arid and semi-arid regions, throughout the world. The present study is an attempt to map the various soil salinity severity classes using different hyperspectral indices generated using EO-1 Hyperion data and Support Vector Machine (SVM) method, in the Mathura region of Indo-Gangetic plain of India. Various hyperspectral indices such as Soil Adjusted Vegetation Index (SAVI), Desertification Soil Index (DSI), Salinity Index (SI) and Normalized Difference Water Index (NDWI) were chosen, generated and effectively used for characterizing and mapping soil salinity severity. Salt infestation in the study area was categorized into four classes of normal, slight, moderate, high soil salinity. Hyperspectral indices helped in identification of various features like vegetation, waterlogged area and soil areas under various classes of soil salinity. The salinity index and desertification soil indices were found to respond well to varying degrees of soil salinity. The SVM technique generated soil salinity map with overall classification accuracy of 78.13 percent, with a kappa statistic of 0.71. The results indicated highest accuracy in high soil salinity class in comparison to other classes, attaining producers and users accuracies of 85.71% and 90.0% respectively. Slight saline class showed poor producers and users accuracy. The result showed high accuracy for mapping soil salinity severity with machine learning classifier like SVM using various indices generated from hyperspectral remote sensing data. These generated images can be effectively used in planning of various management practices and effective reclamation measures of salt affected soils.

show abstract

Decision Fusion for the Classification of Hyperspectral Data: Outcome of the 2008 GRS-S Data Fusion Contest

Cited by 161 publications

References 23 publications

Support Vector Regression for the Estimation of Forest Stand Parameters Using Airborne Laser Scanning

Support Vector Regression for the Estimation of Forest Stand Parameters Using Airborne Laser Scanning

Land-Cover Classification for East Suez Canal Region Using Hyperspectral Eo-1 Data

Hyperspectral Remote Sensing in Characterizing Soil Salinity Severity using SVM Technique - A Case Study of Alluvial Plains

Contact Info

Product

Resources

About