Search Results for author:
Found 16 papers, 5 papers with code
3D detection of roof sections from a single satellite image and application to LOD2-building reconstruction
We here propose a method for urban 3D reconstruction named KIBS(\textit{Keypoints Inference By Segmentation}), which comprises two novel features: i) a full deep learning approach for the 3D detection of the roof sections, and ii) only one single (non-orthogonal) satellite raster image as model input.
Polygonal Building Extraction by Frame Field Learning
While state of the art image segmentation models typically output segmentations in raster format, applications in geographic information systems often require vector polygons.
Input Similarity from the Neural Network Perspective
We first exhibit a multimodal image registration task, for which a neural network trained on a dataset with noisy labels reaches almost perfect accuracy, far beyond noise variance.
Deep Neural Networks for automatic extraction of features in time series satellite images
Experimental results show that the temporal information provided by time series images allows increasing the accuracy of land cover classification, thus producing up-to-date maps that can help in identifying changes on earth.
DAugNet: Unsupervised, Multi-source, Multi-target, and Life-long Domain Adaptation for Semantic Segmentation of Satellite Images
We propose a novel approach, coined DAugNet, for unsupervised, multi-source, multi-target, and life-long domain adaptation of satellite images.
Polygonal Building Segmentation by Frame Field Learning
While state of the art image segmentation models typically output segmentations in raster format, applications in geographic information systems often require vector polygons.
StandardGAN: Multi-source Domain Adaptation for Semantic Segmentation of Very High Resolution Satellite Images by Data Standardization
However, these methods have limited practical real world applications, since usually one has multiple source domains with different data distributions.
SemI2I: Semantically Consistent Image-to-Image Translation for Domain Adaptation of Remote Sensing Data
Although convolutional neural networks have been proven to be an effective tool to generate high quality maps from remote sensing images, their performance significantly deteriorates when there exists a large domain shift between training and test data.
ColorMapGAN: Unsupervised Domain Adaptation for Semantic Segmentation Using Color Mapping Generative Adversarial Networks
Due to the various reasons such as atmospheric effects and differences in acquisition, it is often the case that there exists a large difference between spectral bands of satellite images collected from different geographic locations.
Noisy Supervision for Correcting Misaligned Cadaster Maps Without Perfect Ground Truth Data
In machine learning the best performance on a certain task is achieved by fully supervised methods when perfect ground truth labels are available.
Incremental Learning for Semantic Segmentation of Large-Scale Remote Sensing Data
The key points of the proposed approach are adapting the network to learn new as well as old classes on the new training data, and allowing it to remember the previously learned information for the old classes.
Multimodal image alignment through a multiscale chain of neural networks with application to remote sensing
We tackle here the problem of multimodal image non-rigid registration, which is of prime importance in remote sensing and medical imaging.
Coarse to fine non-rigid registration: a chain of scale-specific neural networks for multimodal image alignment with application to remote sensing
We tackle here the problem of multimodal image non-rigid registration, which is of prime importance in remote sensing and medical imaging.
Progressive Tree-like Curvilinear Structure Reconstruction with Structured Ranking Learning and Graph Algorithm
We propose a novel tree-like curvilinear structure reconstruction algorithm based on supervised learning and graph theory.
High-Resolution Semantic Labeling with Convolutional Neural Networks
We establish the desired properties of an ideal semantic labeling CNN, and assess how those methods stand with regard to these properties.
Recurrent Neural Networks to Correct Satellite Image Classification Maps
Instead, our goal is to directly learn the iterative process itself.
