Abstract
Abstract. In this work, a novel automatic 3D building reconstruction approach is proposed to extract accurate LoD1 building models from multi-view aerial images. The proposed approach consists of three main parts. The first step is to generate digital surface models (DSMs) from aerial images, which is implemented with the Smart3D software and can be replaced by other open-source multi-view stereo (MVS) algorithms as well. The second step is to produce structured 2D building footprints using combined deep learning and regularization. The initial building segmentation maps are obtained by the multi-scale aggregation fully convolutional network (MA-FCN), which takes both the images and DSM as input, through supervised learning. The initial segmentation maps are further refined with another segmentation maps that are derived from the DSM. After that, the contour extraction and regularization technology are applied to produce structured building footprints. In the last step, the elevations of the top and base of each individual building are reliably estimated by adopting an adaptive terrain generation approach and the neighbourhood buffer analysis. The georeferenced building footprint polygons and the elevations of building top and base form the watertight LoD1 building models. The qualitative and quantitative evaluations in Jinghai District, Tianjin, China demonstrate the robustness and effectiveness of the proposed approach.
Highlights
Building is the most representative entity of a city on the Earth
The first step is generating digital surface models (DSMs) from multi-view aerial images, which were captured from a 5-view oblique camera, which is implemented with the Smart3D software in our study
The non-ground points of each building’s neighbourhood on the DSM, which would impact the correct estimation of the height of the building base, are filtered using a modified digital terrain model (DTM) extraction approach, we named it as adaptive network of ground points (NGPs) that developed from (Mousa et al, 2017)
Summary
Building is the most representative entity of a city on the Earth. Three-dimensional (3D) building reconstruction from overhead images or lasers is one of the most key tasks nowadays for smart city construction, urban planning, population density analysis, mobile telecommunication, and disaster management (Bulatov et al, 2014). Compared to the LiDAR-based or 2D building vector map assisted methods, there are fewer studies that started from accessed multiview aerial images. The latter is more challenging that elevation information and building footprints are both unavailable. The basic idea is to combine the image dense matching derived DSM and the CNNbased building segmentation algorithm to extract the 2D building polygons first, and the elevations of the base and. The reconstructed 3D entities were qualitatively and quantitatively evaluated according to completeness and robustness, the effectiveness of the proposed approach was demonstrated
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
