Classification of VHR Multispectral Images Using ExtraTrees and Maximally Stable Extremal Region-Guided Morphological Profile

Alim Samat*, C. Persello, Sicong Liu, Erzhu Li, Zelang Miao, Jilili Abuduwaili

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

6 Citations (Scopus)

Abstract

Pixel-based contextual classification methods, including morphological profiles (MPs), extended MPs, attribute profiles (APs), and MPs with partial reconstruction (MPPR), have shown the benefits of using geometrical features extracted from very-high resolution (VHR) images. However, the structural element sequence or the attribute filters that are necessarily adopted in the above solutions always result in computationally inefficient and redundant high-dimensional features. To solve the second problem, we introduce maximally stable extremal regions (MSER) guided MPs (MSER-MPs) and MSER-MPs(M), which contains mean pixel values within regions, to foster effective and efficient spatial feature extraction. In addition, the extremely randomized decision tree (ERDT) and its ensemble version, ExtraTrees, are introduced and investigated. An extremely randomized rotation forest (ERRF) is proposed by simply replacing the conventional C4.5 decision tree in a rotation forest (RoF) with an ERDT. Finally, the proposed spatial feature extractors, ERDT, ExtraTrees, and ERRF are evaluated for their ability to classify three VHR multispectral images acquired over urban areas, and compared against C4.5, Bagging(C4.5), random forest, support vector machine, and RoF in terms of classification accuracy and computational efficiency. The experimental results confirm the superior performance of MSER-MPs(M) and MSER-MPs compared to MPPR and MPs, respectively, and ExtraTrees is better for spectral-spatial classification of VHR multispectral images using the original spectra stacked with MSER-MPs(M) features.

Original languageEnglish
Article number8353860
Pages (from-to)3179-3195
Number of pages17
JournalIEEE Journal of selected topics in applied earth observations and remote sensing
Volume11
Issue number9
DOIs
Publication statusPublished - 1 Sep 2018

Keywords

  • ExtraTrees
  • extremely randomized decision tree (ERDT)
  • extremely randomized rotation forest (ERRF)
  • maximally stable extremal regions (MSER) guided morphological profiles (MSER-MPs)
  • morphological profiles (MPs)
  • very-high resolution (VHR) image classification
  • ITC-ISI-JOURNAL-ARTICLE

Fingerprint Dive into the research topics of 'Classification of VHR Multispectral Images Using ExtraTrees and Maximally Stable Extremal Region-Guided Morphological Profile'. Together they form a unique fingerprint.

  • Cite this