Szczegóły publikacji
Opis bibliograficzny
Two-stage subpixel impervious surface coverage estimation: comparing classification and regression trees and regression trees and artificial neural networks : [abstract] / Katarzyna K. BERNAT, Wojciech DRZEWIECKI // W: Image and signal processing for remote sensing [Dokument elektroniczny] : Amsterdam, Netherlands, 22–25 September 2014 / SPIE. — Wersja do Windows. — Dane tekstowe. — [Amsterdam : s. n.], [2014]. — e-ISBN: 978-1-62841-307-6. — 1 ekran. — Tryb dostępu: http://spie.org/ERS/conferencedetails/image-and-signal-proces... [2014-09-15]. — Pełny tekst W: Image and Signal Processing for Remote Sensing XX [Dokument elektroniczny] : Amsterdam, Netherlands, September 22,2014. — Wersja do Windows. — Dane tekstowe / ed. Lorenzo Bruzzone. — [Netherlands : s. n., 2014]. . — (Proceedings of SPIE ; vol. 9244). — S. 92441I-1–92441I-12. — Tryb dostępu: http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=1920279 [2014-10-30]. — Bibliogr. s. 92441I-11–92441I-12, Abstr. — Tekst dostępny po zalogowaniu
Autorzy (2)
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 83816 |
|---|---|
| Data dodania do BaDAP | 2014-09-16 |
| DOI | 10.1117/12.2067308 |
| Rok publikacji | 2014 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Konferencja | Image and signal processing for remote sensing |
Abstract
The paper presents accuracy comparison of subpixel classification based on medium resolution Landsat images, performed using machine learning algorithms built on decision and regression trees method (C.5.0/Cubist and Random Forest) and artificial neural networks. The aim of the study was to obtain the pattern of percentage impervious surface coverage, valid for the period of 2009-2010. Imperviousness index map generation was a two-stage procedure. The first step was classification, which divided the study area into categories: i) completely permeable (imperviousness index less than 1%) and ii) fully or partially impervious areas. For pixels classified as impervious, the percentage of impervious surface coverage in pixel area was estimated. The root mean square errors (RMS) of determination of the percentage of the impervious surfaces within a single pixel were 11.0% for C.5.0/Cubist method, 11.3% for Random Forest method and 12.6% using artificial neural networks. The introduction of the initial hard classification into completely permeable areas (with imperviousness index <1%) and impervious areas, allowed to improve the accuracy of imperviousness index estimation on poorly urbanized areas covering large areas of the Dobczyce Reservoir catchment. The effect is also visible on final imperviousness index maps.
