Comparison of hyperspectral and multi-spectral imagery to building a spectral library and land cover classification performance

Abstract

The main aim of this research work is to compare k-nearest neighbor algorithm (KNN) supervised classification with migrating means clustering unsupervised classification (MMC) method on the performance of hyperspectral and multispectral data for spectral land cover classes and develop their spectral library in Samara, Russia. Accuracy assessment of the derived thematic maps was based on the analysis of the classification confusion matrix statistics computed for each classified map, using for consistency the same set of validation points. We were analyzed and compared Earth Observing-1 (EO-1) Hyperion hyperspectral data to Landsat 8 Operational Land Imager (OLI) and Advance Land Imager (ALI) multispectral data. Hyperspectral imagers, currently available on airborne platforms, provide increased spectral resolution over existing space based sensors that can document detailed information on the distribution of land cover classes, sometimes species level. Results indicate that KNN (95, 94, 88 overall accuracy and .91, .89, .85 kappa coefficient for Hyp, ALI, OLI respectively) shows better results than unsupervised classification (93, 90, 84 overall accuracy and .89, .87, .81 kappa coefficient for Hyp, ALI, OLI respectively). Development of spectral library for land cover classes is a key component needed to facilitate advance analytical techniques to monitor land cover changes. Different land cover classes in Samara were sampled to create a common spectral library for mapping landscape from remotely sensed data. The development of these libraries provides a physical basis for interpretation that is less subject to conditions of specific data sets, to facilitate a global approach to the application of hyperspectral imagers to mapping landscape. In addition, it is demonstrated that the hyperspectral satellite image provides more accurate classification results than those extracted from the multispectral satellite image. The higher classification accuracy by KNN supervised was attributed principally to the ability of this classifier to identify optimal separating classes with low generalization error, thus producing the best possible classes' separation.

Vegetation Drought Dynamic Analysis in European Russia

“…To get a relationship between LST and VIs, we used Pearson correlation coefficient during two decades study period (figure 5) and find a clear negative correlation. The correlation coefficient of determination of each linear regression (r 2 ) exceeded more than 0.90 in all years [48,49]. Extreme temperature shows low vegetation and reducing temperature represent increasing high and healthy vegetation condition.…”

Analysis and object markup of hyperspectral images for machine learning methods

“…First, we insist on the complete preservation of the reference HSI pixel signatures, regardless of the number of channels that are necessary for the current classification in a particular application (perhaps with the exception of completely noisy channels). This will allow us to build a classification, which is not so much dependent on the conditions of a specific task and a specific HSI, but is reusable and is supported by reference (standard) signatures, which were confirmed in field tests, as in [3], [4], [6][7][8][9][10].…”

“…Publication [10], also in 2018, demonstrates the potential of hyperspectral and multispectral data for monitoring and assessing land cover across the Russian Federation region, and highlights the development of a spectral library for land cover classes with the construction of a standardized classification system.…”

“…In [10], an example of classification of 27 subclasses of 8 dissimilar classes is shown, showing the similarity of the signatures of all 27 subclasses in the range of 82-96 channels of the Hyperion spectrometer. This, on practical material, indicates the importance of detecting the fact of a linear relationship between signatures and using the scale factor of this relationship as a feature of a class and a subclass.…”

Multi-channel data storage format definition for visualization tasks on the example of SPOT-4 images

“…SPOT is a commercial high-resolution optical satellite earth observation system, which operated in 1998-2013 and aimed at solving environmental and agricultural problems, as well as used in such fundamental areas, as climatology and oceanography [1,2,3,4]. The SPOT-4 device was a multispectral observation system that carried out the survey in four spectral ranges (listed in table 1).…”