Evaluation of ForestPA for VHR RS image classification using spectral and superpixel-guided morphological profiles. Issue 1 (1st January 2019)

• Record Type: Journal Article
• Authors: Samat, Alim; Liu, Sicong; Persello, Claudio; Li, Erzhu; Miao, Zelang; Abuduwaili, Jilili
• Is Part Of: European journal of remote sensing. Volume 52:Issue 1(2019)
• Page Start: 107
• Page End: 121
• Publication Date: 2019-01-01
• Subjects: ForestPA -- MPs -- MPPR -- superpixel -- superpixel-guided morphological profiles -- VHR images -- image classification; Remote sensing -- Periodicals; Remote sensing; Electronic journals; Periodicals; 621.3678
• DOI: 10.1080/22797254.2019.1565418
• Languages: English
• ISSNs: 2279-7254

Abstract

ABSTRACT: In very high resolution (VHR) remote sensing (RS) classification tasks, conventional pixel-based contextual information extraction methods such as morphological profiles (MPs), extended MPs (EMPs) and MPs with partial reconstruction (MPPR) with limited numbers, sizes and shapes of structural elements (SEs) cannot perfectly match all sizes and shapes of the objects in an image. To overcome such limitation, we introduce novel spatial feature extractors, namely, the superpixel-guided morphological profiles (SPMPs), where the superpixels are used as SEs in opening by reconstruction and closing by reconstruction operations. Moreover, to avoid possible side effects from unusual maximum and minimum values within superpixels, the mean pixel value of superpixels is adopted (SPMPsM). Additionally, new decision forest based on penalizing the attributes in previous trees, the ForestPA is introduced and evaluated through a comparative investigation on three VHR multi-/hyperspectral RS image classification tasks. Support vector machine and benchmark ensemble classifiers, including bagging, AdaBoost, MultiBoost, ExtraTrees, Random Forest and Rotation Forest, are adopted. The experimental results confirm the effectiveness and superior performances of the proposed SPMPs and SPMPsM relative to those of the MPs and MPPR. Moreover, ForestPA outperforms only bagging and is not suitable for learning from large numbers of samples with high dimensionality from the computational efficiency and classification accuracy perspective.