IMAGING SPECTROSCOPY AND LIGHT DETECTION AND RANGING DATA FUSION FOR URBAN FEATURES EXTRACTION

Idrees Idrees

doi:10.3844/ajassp.2013.1575.1585

Abstract

This study presents our findings on the fusion of Imaging Spectroscopy (IS) and LiDAR data for urban feature extraction. We carried out necessary preprocessing of the hyperspectral image. Minimum Noise Fraction (MNF) transforms was used for ordering hyperspectral bands according to their noise. Thereafter, we employed Optimum Index Factor (OIF) to statistically select the three most appropriate bands combination from MNF result. The composite image was classified using unsupervised classification (k-mean algorithm) and the accuracy of the classification assessed. Digital Surface Model (DSM) and LiDAR intensity were generated from the LiDAR point cloud. The LiDAR intensity was filtered to remove the noise. Hue Saturation Intensity (HSI) fusion algorithm was used to fuse the imaging spectroscopy and DSM as well as imaging spectroscopy and filtered intensity. The fusion of imaging spectroscopy and DSM was found to be better than that of imaging spectroscopy and LiDAR intensity quantitatively. The three datasets (imaging spectrocopy, DSM and Lidar intensity fused data) were classified into four classes: building, pavement, trees and grass using unsupervised classification and the accuracy of the classification assessed. The result of the study shows that fusion of imaging spectroscopy and LiDAR data improved the visual identification of surface features. Also, the classification accuracy improved from an overall accuracy of 84.6% for the imaging spectroscopy data to 90.2% for the DSM fused data. Similarly, the Kappa Coefficient increased from 0.71 to 0.82. on the other hand, classification of the fused LiDAR intensity and imaging spectroscopy data perform poorly quantitatively with overall accuracy of 27.8% and kappa coefficient of 0.0988.

Highlights

The geometric expansion of urban population around the world and other geohazard related issues brought the need for sustainable urban planning and management for socioeconomic development and environmental protection into a limelight
This study presents our findings on the fusion of Imaging Spectroscopy (IS) and Light Detection and Ranging (LiDAR) data for urban feature extraction
This study assesses the effectiveness of unsupervised classification for urban feature extraction from fusion of imaging spectroscopy and LiDAR data through analysis of the following results: fused imaging spectroscopy with Digital Surface Model (DSM) and intensity image described (Fig. 5), qualitative assessment of fused imaging spectroscopy and DSM (Fig. 6), classification results (Fig. 7) and 3D view of the classified data to reveal spatial configuration of the study area (Fig. 8)

Summary

Introduction

The geometric expansion of urban population around the world and other geohazard related issues brought the need for sustainable urban planning and management for socioeconomic development and environmental protection into a limelight. Efficient urban management entails having an up-to-date infrastructural database that will enhance informed, timely and cost effective decision making. According to Blaschke (2010), one of the primary aims of remote sensing is to significantly provide accurate and up-to-date urban landscape. Since Landsat-1 was launched into the orbit in 1972 by the United States National Aeronautics and Space Agency (NASA), optical remote sensing data have been widely used to collect data over a wide coverage providing accurate and high spatial 2D information about the earth's surface for various applications (Chen et al, 2009; Yin et al, 2012). The advantages of optical imagery include rich spectral and textural information and clear feature boundaries delineation (Chen et al, 2009; Johansen et al, 2010).

Objectives

Methods

Results

Discussion

Conclusion