Fusion of Airborne LiDAR Point Clouds and Aerial Images for Heterogeneous Land-Use Urban Mapping

Yasmine Megahed,Ahmed Shaker,Wai Yeung Yan

doi:10.3390/rs13040814

Yasmine Megahed, Ahmed Shaker + Show 1 more

Open Access

https://doi.org/10.3390/rs13040814

Copy DOI

Abstract

The World Health Organization has reported that the number of worldwide urban residents is expected to reach 70% of the total world population by 2050. In the face of challenges brought about by the demographic transition, there is an urgent need to improve the accuracy of urban land-use mappings to more efficiently inform about urban planning processes. Decision-makers rely on accurate urban mappings to properly assess current plans and to develop new ones. This study investigates the effects of including conventional spectral signatures acquired by different sensors on the classification of airborne LiDAR (Light Detection and Ranging) point clouds using multiple feature spaces. The proposed method applied three machine learning algorithms—ML (Maximum Likelihood), SVM (Support Vector Machines), and MLP (Multilayer Perceptron Neural Network)—to classify LiDAR point clouds of a residential urban area after being geo-registered to aerial photos. The overall classification accuracy passed 97%, with height as the only geometric feature in the classifying space. Misclassifications occurred among different classes due to independent acquisition of aerial and LiDAR data as well as shadow and orthorectification problems from aerial images. Nevertheless, the outcomes are promising as they surpassed those achieved with large geometric feature spaces and are encouraging since the approach is computationally reasonable and integrates radiometric properties from affordable sensors.

Highlights

IntroductionIn 1980, around 40% of the total world population lived in cities
The world urban population began to increase significantly since the 1950s
With affordable sensors and computationally inexpensive feature spaces that include only I and H from LiDAR data and RGB, NIR, and NDVI from aerial photos, we achieved a mapping accuracy over 95% with a conventional classifier as Maximum Likelihood (ML) and over 97% with Multilayer Perceptron (MLP)

Summary

Introduction

In 1980, around 40% of the total world population lived in cities. The growth rate of the urban population is expected to be approximately 1.63% and 1.44% per year between 2020 and 2025 and between 2025 and. By 2050, the urban population is expected to almost double, increasing from approximately 3.4 billion (American billion = 109 ) in 2009 to 6.4 billion [1]. This tangible demographic transition has environmental impacts, such as the loss of agricultural lands, reduction in wildlife habitats, air pollution, and a worsening of water quality and accessibility, leading to a deterioration of regional hydrology. To bridge the gap between the available resources and the needs of an urban population, a thorough urban land-use classification becomes an urgent necessity for further urban assessment, and future city planning and management [1]

Methods

Results

Discussion

Conclusion