Unsupervised classification-based hyperspectral data processing: lossy compression

2018 ◽  
Vol 50 (12) ◽  
Author(s):  
Xiao-Yu Cheng ◽  
Yue-Ming Wang ◽  
Ran Guo ◽  
Jun-Ze Huang
Keyword(s):  
Data Processing ◽  
Unsupervised Classification ◽  
Lossy Compression ◽  
Hyperspectral Data

AN AUTOMATIC APPROACH TO LOSSY COMPRESSION OF AVIRIS HYPERSPECTRAL DATA

2010 ◽  
Vol 69 (6) ◽  
pp. 537-563 ◽  
Author(s):  
N. N. Ponomarenko ◽  
M. S. Zriakhov ◽  
A. Kaarna
Keyword(s):  
Lossy Compression ◽  
Hyperspectral Data

scholarly journals Flight Considerations and Hyperspectral Image Classifications for Dryland Vegetation Management from a Fixed-wing UAS

2016 ◽  
Vol 5 (2) ◽  
pp. 41 ◽  
Author(s):  
Jessica Mitchell ◽  
Nancy Glenn ◽  
Matthew Anderson ◽  
Ryan Hruska
Keyword(s):  
Hyperspectral Image ◽  
Distribution Patterns ◽  
Unsupervised Classification ◽  
Vegetation Management ◽  
Geometric Error ◽  
Hyperspectral Data ◽  
Unmanned Aerial Systems ◽  
Native Grasses ◽  
Management Objectives ◽  
Aerial Systems

<p class="emsd"><span lang="EN-GB">Unmanned Aerial Systems (UAS)-based hyperspectral remote sensing capabilities developed by the Idaho National Lab and Boise Center Aerospace Lab were tested via demonstration flights that explored the influence of altitude on geometric error, image mosaicking, and dryland vegetation classification. The motivation for this study was to better understand the challenges associated with UAS-based hyperspectral data for distinguishing native grasses such as Sandberg bluegrass (<em>Poa secunda</em>) from invasives such as burr buttercup (<em>Ranunculus testiculatus)</em> in a shrubland environment. The test flights successfully acquired usable flightline data capable of supporting classifiable composite images. Unsupervised classification results support vegetation management objectives that rely on mapping shrub cover and distribution patterns. However, supervised classifications performed poorly despite spectral separability in the image-derived endmember pixels. In many cases, the supervised classifications accentuated noise or features in the mosaic that were artifacts of color balancing and feathering in areas of flightline overlap. Future UAS flight missions that optimize flight planning; minimize illumination differences between flightlines; and leverage ground reference data and time series analysis should be able to effectively distinguish native grasses such as Sandberg bluegrass from burr buttercup. </span></p>

Sign in / Sign up

Export Citation Format

Share Document