Improving hyperspectral image segmentation by applying inverse noise weighting and outlier removal for optimal scale selection

↓ Direkt till sidans innehåll
↓ Direkt till sidans sekundära innehåll (sidomenyn)

Sökning: WFRF:(Mantripragada K. K.) > Improving hyperspec...

Dao, P. D. (författare)

Improving hyperspectral image segmentation by applying inverse noise weighting and outlier removal for optimal scale selection

Artikel/kapitelEngelska2021

Förlag, utgivningsår, omfång ...

Elsevier B.V.2021
printrdacarrier

Nummerbeteckningar

LIBRIS-ID:oai:DiVA.org:miun-43454
https://urn.kb.se/resolve?urn=urn:nbn:se:miun:diva-43454URI
https://doi.org/10.1016/j.isprsjprs.2020.11.013DOI

Kompletterande språkuppgifter

Språk:engelska
Sammanfattning på:engelska

Ingår i deldatabas

SwePubSwePub

Klassifikation

Ämneskategori:ref swepub-contenttype
Ämneskategori:art swepub-publicationtype

Anmärkningar

Optimal scale selection for image segmentation is an essential component of the Object-Based Image Analysis (OBIA) and interpretation. An optimal segmentation scale is a scale at which image objects, overall, best represent real-world ground objects and features across the entire image. At this scale, the intra-object variance is ideally lowest and the inter-object spatial autocorrelation is ideally highest, and a change in the scale could cause an abrupt change in these measures. Unsupervised parameter optimization methods typically use global measures of spatial and spectral properties calculated from all image objects in all bands as the target criteria to determine the optimal segmentation scale. However, no studies consider the effect of noise in image spectral bands on the segmentation assessment and scale selection. Furthermore, these global measures could be affected by outliers or extreme values from a small number of objects. These issues may lead to incorrect assessment and selection of optimal scales and cause the uncertainties in subsequent segmentation and classification results. These issues become more pronounced when segmenting hyperspectral data with large spectral variability across the spectrum. In this study, we propose an enhanced method that 1) incorporates the band's inverse noise weighting in the segmentation and 2) detects and removes outliers before determining segmentation scale parameters. The proposed method is evaluated on three well-established segmentation approaches – k-means, mean-shift, and watershed. The generated segments are validated by comparing them with reference polygons using normalized over-segmentation (OS), under-segmentation (US), and the Euclidean Distance (ED) indices. The results demonstrate that this proposed scale selection method produces more accurate and reliable segmentation results. The approach can be applied to other segmentation selection criteria and are useful for automatic multi-parameter tuning and optimal scale parameter selections in OBIA methods in remote sensing. © 2020 International Society for Photogrammetry and Remote Sensing, Inc. (ISPRS)

Ämnesord och genrebeteckningar

Hyperspectral image classification
Image segmentation
Inverse noise weighting
Object-Based Image Analysis
Optimal scale selection
Outlier detection
Image denoising
Image enhancement
Inverse problems
Remote sensing
Scales (weighing instruments)
Spectroscopy
Statistics
Classification results
Object based image analysis (OBIA)
Optimal segmentation
Parameter optimization methods
Segmentation results
Spatial autocorrelations
Spectral properties
Spectral variability
autocorrelation
image analysis
optimization
segmentation
spectral analysis
United States

Biuppslag (personer, institutioner, konferenser, titlar ...)

Mantripragada, K. (författare)
He, Y. (författare)
Qureshi, F. Z. (författare)

Sammanhörande titlar

Ingår i:ISPRS journal of photogrammetry and remote sensing (Print): Elsevier B.V.171, s. 348-3660924-27161872-8235

Internetlänk

Hitta via bibliotek

ISPRS journal of photogrammetry and remote sensing (Print) (Sök värdpublikationen i LIBRIS)

Till lärosätets databas

Hitta mer i SwePub

Av författaren/redakt...: Dao, P. D.; Mantripragada, K ...; He, Y.; Qureshi, F. Z.

Artiklar i publikationen: ISPRS journal of ...

Av lärosätet: Mittuniversitetet

Sök utanför SwePub

Sök vidare i:: Google; Google Book Search; Google Scholar

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.

LIBRIS.kb.se