Parcel-based urban land use classification in megacity using airborne LiDAR, high resolution orthoimagery, and Google Street View

Abstract

Urban land use information is increasingly important for a variety of purposes. With their increasing coverage and availability, airborne light detection and ranging (LiDAR) data, high resolution orthoimagery (HRO), and Google Street View (GSV) images are showing great potential for accurate land use classification. However, no study mapped land use in megacity using GSV-derived features or the three kinds of data together for land use classification. The main objectives of this study are (1) to test the performance of a parcel-based land use classification method using a Random Forest classifier with LiDAR data, HRO, and GSV images in a megacity, and (2) to explore the use of GSV in separating parcels of mixed residential & commercial buildings from other land use parcels. Two neighbouring community districts in Brooklyn, New York, were selected as the study area. Thirteen automaticallyderived parcel features, including nine common parcel features and four GSV-derived parcel features, were used in land use classification. The average overall classification accuracy was 77.5%, with producer's accuracies exceeding 92% for single-family housing. Comparing the results of classifications with and without GSV-derived parcel features shows that GSV-derived parcel features on average contribute to the classification accuracy of mixed residential & commercial buildings by 10 percentage points, improving it from 41.3% to 51.4%. In general, the results show that even in a complex megacity, the parcel-based land use classification technique, with parcel features extracted from airborne LiDAR, HRO, and GSV, is able to discriminate among different land use classes, such as single-family house, commercial & industrial building, and open space & park, with acceptable accuracies, and that integrating GSV into classification improves the classification accuracy of some urban land use classes, especially mixed residential & commercial building.

Semantic Segmentation of Urban Buildings from VHR Remote Sensing Imagery Using a Deep Convolutional Neural Network

“…In recent years, owing to the rapid development of sensor technology, very high resolution (VHR) images with spatial resolution from 5 to 30 cm have become available [4], making small-scale objects (e.g., cars, buildings and roads) distinguishable and identifiable via semantic segmentation methods. Semantic segmentation as an effective technique aims to assign each pixel in the target image into a given category [5]; therefore, it was quickly developed and extensively applied to urban planning and relevant studies including building/road detection [6][7][8], land use/cover mapping [9][10][11][12], and forest management [13,14] with the emergence of a large number of publicly available VHR images.…”

Identification of Industrial Land Parcels and Its Implications for Environmental Risk Management in the Beijing–Tianjin–Hebei Urban Agglomeration

“…Existing studies in China show that urbanization and industrial development were the two main factors affecting health risks of fine particle (PM 2.5 ) [21,22]. Meanwhile, the functions and environmental impacts differ greatly in various built-up land parcels [23]. Industrial land parcels are one of the most essential components, with the proportion from 15% to 30% in urban planning due to national regulations.…”

Estimates of landscape composition from terrestrial oblique photographs suggest homogenization of Rocky Mountain landscapes over the last century

“…; Zhang et al. ), but this field is relatively new and rapidly evolving. As such, oblique photographs present a useful but relatively untapped data source for studies of landscape change, particularly around mountains (Kaim ).…”

“…Fifth, photographs taken from the ground are abundant: Google Street View imagery, social media platforms and ground surveys are examples of widespread sources of oblique photographs. In recent years, numerous studies have sought to harness the enormous potential of these free or low-cost ground-level data for various applications such as urban planning, tree cataloging and land cover change detection (Li and Zhang 2016;Jiang et al 2017;Lef evre et al 2017;Liang et al 2017;Zhang et al 2017), but this field is relatively new and rapidly evolving. As such, oblique photographs present a useful but relatively untapped data source for studies of landscape change, particularly around mountains (Kaim 2017).…”