Learning aerial image segmentation from online maps

P Kaiser, JD Wegner, A Lucchi, M Jaggi… - … on Geoscience and …, 2017 - ieeexplore.ieee.org
This paper deals with semantic segmentation of high-resolution (aerial) images where a
semantic class label is assigned to each pixel via supervised classification as a basis for …

Fully convolutional networks for dense semantic labelling of high-resolution aerial imagery

J Sherrah - arXiv preprint arXiv:1606.02585, 2016 - arxiv.org
The trend towards higher resolution remote sensing imagery facilitates a transition from land-
use classification to object-level scene understanding. Rather than relying purely on spectral …

Effective semantic pixel labelling with convolutional networks and conditional random fields

S Paisitkriangkrai, J Sherrah, P Janney… - Proceedings of the …, 2015 - cv-foundation.org
Large amounts of available training data and increasing computing power have led to the
recent success of deep convolutional neural networks (CNN) on a large number of …

Semantic labeling of aerial and satellite imagery

S Paisitkriangkrai, J Sherrah, P Janney… - IEEE Journal of …, 2016 - ieeexplore.ieee.org
Inspired by the recent success of deep convolutional neural networks (CNNs) and feature
aggregation in the field of computer vision and machine learning, we propose an effective …

Oblique photogrammetry supporting 3D urban reconstruction of complex scenarios

I Toschi, MM Ramos, E Nocerino, F Menna… - … Archives of the …, 2017 - re.public.polimi.it
Accurate 3D city models represent an important source of geospatial information to support
various “smart city” applications, such as space management, energy assessment, 3D …

Building detection using enhanced HOG–LBP features and region refinement processes

D Konstantinidis, T Stathaki, V Argyriou… - IEEE Journal of …, 2016 - ieeexplore.ieee.org
Building detection from two-dimensional high-resolution satellite images is a computer
vision, photogrammetry, and remote sensing task that has arisen in the last decades with the …

3D building reconstruction from ALS data using unambiguous decomposition into elementary structures

M Jarząbek-Rychard, A Borkowski - ISPRS journal of photogrammetry and …, 2016 - Elsevier
The objective of the paper is to develop an automated method that enables for the
recognition and semantic interpretation of topological building structures. The novelty of the …

Geospatial data processing for 3D city model generation, management and visualization

I Toschi, E Nocerino… - … Archives of the …, 2017 - isprs-archives.copernicus.org
Recent developments of 3D technologies and tools have increased availability and
relevance of 3D data (from 3D points to complete city models) in the geospatial and geo …

Combining high-resolution optical and InSAR features for height estimation of buildings with flat roofs

JD Wegner, JR Ziehn, U Soergel - IEEE Transactions on …, 2013 - ieeexplore.ieee.org
In this paper, we contribute to answer the question: How accurately can we estimate heights
of buildings with flat roofs given one high-resolution single-pass interferometric synthetic …

Semantic segmentation of remote sensing image based on convolutional neural network and mask generation

B Niu - Mathematical Problems in Engineering, 2021 - Wiley Online Library
High‐resolution remote sensing images usually contain complex semantic information and
confusing targets, so their semantic segmentation is an important and challenging task. To …