Deep cross-domain building extraction for selective depth estimation from oblique aerial imagery

04/23/2018
by   Boitumelo Ruf, et al.
0

With the technological advancements of aerial imagery and accurate 3d reconstruction of urban environments, more and more attention has been paid to the automated analyses of urban areas. In our work, we examine two important aspects that allow live analysis of building structures in city models given oblique aerial imagery, namely automatic building extraction with convolutional neural networks (CNNs) and selective real-time depth estimation from aerial imagery. We use transfer learning to train the Faster R-CNN method for real-time deep object detection, by combining a large ground-based dataset for urban scene understanding with a smaller number of images from an aerial dataset. We achieve an average precision (AP) of about 80 building extraction on a selected evaluation dataset. Our evaluation focuses on both dataset-specific learning and transfer learning. Furthermore, we present an algorithm that allows for multi-view depth estimation from aerial imagery in real-time. We adopt the semi-global matching (SGM) optimization strategy to preserve sharp edges at object boundaries. In combination with the Faster R-CNN, it allows a selective reconstruction of buildings, identified with regions of interest (RoIs), from oblique aerial imagery.

READ FULL TEXT

page 3

page 4

page 6

research
08/17/2020

Self-Supervised Learning for Monocular Depth Estimation from Aerial Imagery

Supervised learning based methods for monocular depth estimation usually...
research
11/10/2016

Variables effecting photomosaic reconstruction and ortho-rectification from aerial survey datasets

Unmanned aerial vehicles now make it possible to obtain high quality aer...
research
12/07/2020

An Enriched Automated PV Registry: Combining Image Recognition and 3D Building Data

While photovoltaic (PV) systems are installed at an unprecedented rate, ...
research
10/08/2018

Bootstrapped CNNs for Building Segmentation on RGB-D Aerial Imagery

Detection of buildings and other objects from aerial images has various ...
research
07/21/2021

Window Detection In Facade Imagery: A Deep Learning Approach Using Mask R-CNN

The parsing of windows in building facades is a long-desired but challen...
research
03/25/2019

Accurate Global Trajectory Alignment using Poles and Road Markings

Currently, digital maps are indispensable for automated driving. However...
research
05/03/2023

On procedural urban digital twin generation and visualization of large scale data

The desired outcome for urban digital twins is an automatically generate...

Please sign up or login with your details

Forgot password? Click here to reset