High resolution image for forest classification

High resolution image for forest classification. Buletin Geospatial Sektor Awam, 1: 2. pp. 9-13. ISSN 1823-7762 (2008)


Unsupervised classification is also known as clustering because it is based on natural grouping of pixels in the image data when the pixels are plotted in the feature space. Clusters are defined with a clustering algorithm, which often uses all or many of the pixels in the input data file for its analysis. ISODATA (Iterative Self-Organizing Data Analysis Technique) are examples of unsupervised classification methods. The aim of this study was to apply the unsupervised classification method for forest mapping using high resolution QuickBird image. The study site was located at the Forest Research Institute Malaysia (FRIM), Kepong. The overall accuracy for the unsupervised classification was 77.50% while the kappa statistics, 0.8182.

Item Type: Article
Keywords: Forest mapping, Remote sensing
Taxonomy: By Subject > Architecture, Planning & Surveying > Surveying Sciences And Geomatics
Local Content Hub: Subjects > Architecture, Planning & Surveying
Depositing User: Nur Hayati Abdul Satar
Date Deposited: 17 Feb 2021 08:17
Last Modified: 17 Feb 2021 08:17
Related URLs:

Actions (login required)

View Item View Item