Imaging Spectroscopy and Light Detection and Ranging Data Fusion for Urban Features Extraction

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.

A comparison of ground-based hyperspectral imaging and red-edge multispectral imaging for façade material classification

“…For example, in a study by Idrees et al (2013), 4 sets of urban features (buildings, pavement, trees, and grass) were successfully classified to an accuracy of 84.6% by using hyperspectral imaging. In that study, accuracy increased to 90.2% after fusion with a digital surface model derived from LiDAR.…”

Automatic extraction of road features in urban environments using dense ALS data

“…While many effective strategies have been introduced for distinguishing buildings from vegetation and paved areas (e.g. Idrees et al, 2013;Vo et al, 2016), even in a Big Data context (Aljumaily et al, 2016(Aljumaily et al, , 2017, relatively little has been robustly and scalably achieved for the semantic labeling of smaller road features such as curbs and road markings. Yet, these are needed for systematic cataloguing and management.…”