|
|
|
Abstract
A Class Basis Classification Approach of Very High Resolution Imagery in Dense Urban Area – A Case Study in Kuala Lumpur City Center.
Low Tsuey Miin
RS/GIS Engineer
Cilix Corporation Sdn Bhd,
Malaysia
Email: lowtm@cilix.org
Low Tsuey Miin
RS/GIS Engineer
Cilix Corporation Sdn Bhd
Email: lowtm@cilix.org
The purpose of this paper is to explore a new procedure on a class basis approach to extract several land cover types. Kuala Lumpur City Centre, which is a dense urban area has been chosen as the study area. Multispectral QUICKBIRD imagery and high resolution LiDAR (Light Detection and Ranging) data are used in this study. LiDAR data enabled the identification of buildings and other elevated features from non-elevated urban features like roads and vacant lands. It is very complex to differentiate between roads and some of the vacant lands from VHR (Very High Resolution) imagery accurately especially using traditional classification methods due to the similarity of the reflectance of spectral and spatial characteristics. The eCognition software was used in this study to implement the fuzzy classification according to the shape feature of the image objects. Fuzzy classification is a simple technique, which basically translates feature values of arbitrary range into fuzzy values between 0 and 1, indicating the degree of membership to a specific class. The compactness feature has been used to distinguish the road and vacant lands. Accuracy assessment and visual interpretation proved that class-basis classification approach is providing a promising result.
|
|
|