Filters








42 Hits in 7.3 sec

Large-Scale Semantic Classification: Outcome of the First Year of Inria Aerial Image Labeling Benchmark

Bohao Huang, Kangkang Lu, Nicolas Audeberr, Andrew Khalel, Yuliya Tarabalka, Jordan Malof, Alexandre Boulch, Bertr Le Saux, Leslie Collins, Kyle Bradbury, Sebastien Lefevre, Motaz El-Saban
2018 IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium  
In this paper, we discuss the outcomes of the first year of the Inria benchmark contest. We first briefly recall the composition of the dataset and give its use statistics.  ...  Finally, we conclude about the state-of-the-art in large-scale semantic labeling.  ... 
doi:10.1109/igarss.2018.8518525 dblp:conf/igarss/HuangLAKTMBSCBL18 fatcat:r5qsistsojb2zgreftjdbq7ldq

SatImNet: Structured and Harmonised Training Data for Enhanced Satellite Imagery Classification [article]

Vasileios Syrris, Ondrej Pesek, Pierre Soille
2020 arXiv   pre-print
This prevents the combination of two or more training datasets for improving image classification tasks based on machine learning.  ...  Automatic supervised classification of satellite images with complex modelling such as deep neural networks requires the availability of representative training datasets.  ...  Acknowledgement: The authors would like to thank Tomáš Kliment, Panagiotis Mavrogiorgos and Pier Valerio Tognoli for their contribution in data management and Docker images configuration and maintenance  ... 
arXiv:2006.10623v1 fatcat:g55uuyxgm5cpjccgc62u4xnyyi

A REVIEW OF BENCHMARKING IN PHOTOGRAMMETRY AND REMOTE SENSING

K. Bakuła, J. P. Mills, F. Remondino
2019 The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
The first part of the paper is a bibliographic analysis based on queries in Scopus and Web of Science databases which shows an increase in research activities based on benchmarking data.  ...  As hereafter reported, benchmarking has increased in recent years, with many benchmarks being presented in the photogrammetric and remote sensing communities.</p>  ...  Large-scale semantic classification: Outcome of the first year of inria aerial image labeling benchmark 2018 International Geoscience and Remote Sensing Symposium (IGARSS) Helber P., Bischke B., Dengel  ... 
doi:10.5194/isprs-archives-xlii-1-w2-1-2019 fatcat:f26tkpwl6rddlihiq3tvfjbkam

DISIR: Deep Image Segmentation with Interactive Refinement [article]

Gaston Lenczner, Bertrand Le Saux, Nicola Luminari, Adrien Chan Hon Tong, Guy Le Besnerais
2020 arXiv   pre-print
This paper presents an interactive approach for multi-class segmentation of aerial images. Precisely, it is based on a deep neural network which exploits both RGB images and annotations.  ...  Starting from an initial output based on the image only, our network then interactively refines this segmentation map using a concatenation of the image and user annotations.  ...  The INRIA Aerial Image Labelling dataset (Maggiori et al., 2017) is composed of two classes (buildings and not buildings) and covers more than 800 km 2 with a spatial resolution of 0.3m.  ... 
arXiv:2003.14200v1 fatcat:6d3hhib5xvavzj5ykreg7alx6e

DISIR: DEEP IMAGE SEGMENTATION WITH INTERACTIVE REFINEMENT

G. Lenczner, B. Le Saux, N. Luminari, A. Chan-Hon-Tong, G. Le Besnerais
2020 ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
This paper presents an interactive approach for multi-class segmentation of aerial images. Precisely, it is based on a deep neural network which exploits both RGB images and annotations.  ...  Starting from an initial output based on the image only, our network then interactively refines this segmentation map using a concatenation of the image and user annotations.  ...  ., 2019) assess these various strategies in the first large scale study of interactive instance segmentation with human annotators.  ... 
doi:10.5194/isprs-annals-v-2-2020-877-2020 fatcat:vn6drv76mnhhphjq2hvvb6w42m

Land-use Mapping for High Spatial Resolution Remote Sensing Image via Deep Learning: A Review

Ning Zang, Yun Cao, Yuebin Wang, Bo Huang, Liqiang Zhang, P Takis Mathiopoulos
2021 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
We then briefly review the fundamentals and the developments of the development of semantic segmentation and single object segmentation.  ...  With the emergence of new deep learning (DL) algorithms in recent years, methods to LUM with DL have achieved huge breakthroughs, which offers novel opportunities for the development of LUM for HSR-RSIs  ...  Buffalo dataset [39] is composed of 30 aerial images of Buffalo city at a resolution of 1 meter and all with a size of 609 × 914. Inria Aerial Image Labeling dataset [40] covers 810 Km 2 .  ... 
doi:10.1109/jstars.2021.3078631 fatcat:ubblvynhdvd2ndzhjablus22cy

AUTOMATED CHAIN FOR LARGE-SCALE 3D RECONSTRUCTION OF URBAN SCENES FROM SATELLITE IMAGES

S. Tripodi, L. Duan, F. Trastour, V. Poujad, L. Laurore, Y. Tarabalka
2019 The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
In this paper, we present an automated chain for large-scale 3D reconstruction of urban scenes with a Level of Detail 1 from satellite images. The proposed framework relies on two key ingredient.  ...  First, from a stereo pair of images, we estimate a digital terrain model and a digital height model, by using a novel set of feature descriptors based on multiscale morphological analysis.  ...  Inspired by the winning method of the Inria aerial image labeling benchmark (Huang et al., 2018) , we have adopted the original U-Net architecture from (Ronneberger et al., 2015) , with a single major  ... 
doi:10.5194/isprs-archives-xlii-2-w16-243-2019 fatcat:l634kjzeozcqrpiuxwwrz73bwm

Research Contribution and Comprehensive Review towards the Semantic Segmentation of Aerial Images Using Deep Learning Techniques

P. Anilkumar, P. Venugopal, Mamoun Alazab
2022 Security and Communication Networks  
The main aim of this review is to provide a clear algorithmic categorization and analysis of the diverse contribution of semantic segmentation of aerial images and expects to give the comprehensive details  ...  In recent years, semantic segmentation has been focused on different deep learning approaches in the area of computer vision, which has aimed for getting superior efficiency while analyzing the aerial  ...  Acknowledgments e authors acknowledge the help of the Vellore Institute of Technology, Vellore, India, for giving excellent assets to this work.  ... 
doi:10.1155/2022/6010912 fatcat:qxoogfb3zneypkh5w3m5p3ts3e

Semi-Supervised Semantic Segmentation in Earth Observation: The MiniFrance Suite, Dataset Analysis and Multi-task Network Study [article]

Javiera Castillo-Navarro, Bertrand Le Saux, Alexandre Boulch, Nicolas Audebert, Sébastien Lefèvre
2020 arXiv   pre-print
We introduce a novel large-scale dataset for semi-supervised semantic segmentation in Earth Observation, the MiniFrance suite.  ...  MiniFrance has several unprecedented properties: it is large-scale, containing over 2000 very high resolution aerial images, accounting for more than 200 billions samples (pixels); it is varied, covering  ...  The authors acknowledge the IGN for providing the BD ORTHO database under Open Licence v1.0 (https://www.etalab.gouv.fr/ licence-ouverte-open-licence) and the European Copernicus Program for providing  ... 
arXiv:2010.07830v1 fatcat:h7k5dnh5nnhffl2iy4o6yg67du

Automatic Building Extraction on Satellite Images Using Unet and ResNet50

Waleed Alsabhan, Turky Alotaiby, Gopal Chaudhary
2022 Computational Intelligence and Neuroscience  
This study proposes the differentiation of buildings by image segmentation on high-resolution satellite images with U-net architecture.  ...  It was aimed to remove buildings in the high-density city of Boston. In the U-net architecture, image segmentation is performed with different encoders and the results are compared.  ...  aerial image labeling dataset[45].  ... 
doi:10.1155/2022/5008854 pmid:35222630 pmcid:PMC8881177 fatcat:3jck52yfgrcg5jxuwiicsjy3yu

Arbitrary-Shaped Building Boundary-Aware Detection with Pixel Aggregation Network

Xin Jiang, Xinchang Zhang, Qinchuan Xin, Xu Xi, Pengcheng Zhang
2020 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
Large-scale building extraction is an essential work in the field of remote sensing image analysis.  ...  The high-resolution image extraction methods based on deep learning have achieved state-of-the-art performance.  ...  Maggiori et al. for providing the Inria Aerial Image Labeling Benchmark, and grateful to Volodymyr Mnih for providing the Massachusetts buildings dataset. We are also grateful to F.  ... 
doi:10.1109/jstars.2020.3017934 fatcat:cwjmgnvpkjeujalhy7vwniekre

Object Detection and Image Segmentation with Deep Learning on Earth Observation Data: A Review-Part I: Evolution and Recent Trends

Thorsten Hoeser, Claudia Kuenzer
2020 Remote Sensing  
Deep learning (DL) has great influence on large parts of science and increasingly established itself as an adaptive method for new challenges in the field of Earth observation (EO).  ...  To lower the barriers for researchers in EO, this review gives an overview of the evolution of DL with a focus on image segmentation and object detection in convolutional neural networks (CNN).  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/rs12101667 fatcat:vlqupucfrndexnyhrsgawshc2y

A Systematic Survey of ML Datasets for Prime CV Research Areas—Media and Metadata

Helder F. Castro, Jaime S. Cardoso, Maria T. Andrade
2021 Data  
The ever-growing capabilities of computers have enabled pursuing Computer Vision through Machine Learning (i.e., MLCV). ML tools require large amounts of information to learn from (ML datasets).  ...  We reveal the heterogeneous plethora that comprises the MLCV dataset tissue; their continuous growth in volume and complexity; the specificities of the evolution of their media and metadata components  ...  Those images have large variations in scale, pose, and lighting.  ... 
doi:10.3390/data6020012 fatcat:jov2btfknnet3bwpyn6txnrhda

Object Detection and Image Segmentation with Deep Learning on Earth Observation Data: A Review—Part II: Applications

Thorsten Hoeser, Felix Bachofer, Claudia Kuenzer
2020 Remote Sensing  
In Earth observation (EO), large-scale land-surface dynamics are traditionally analyzed by investigating aggregated classes.  ...  In this review, we provide a comprehensive overview of the impact of deep learning on EO applications by reviewing 429 studies on image segmentation and object detection with CNNs.  ...  Conflicts of Interest: The authors declare no conflict of interest. Appendix A.  ... 
doi:10.3390/rs12183053 doaj:56aade2b0b4243b1b45a6839cc85dc15 fatcat:jskmiupd4zaa5egsllib2oyioi

Synthetic Data for Deep Learning [article]

Sergey I. Nikolenko
2019 arXiv   pre-print
First, we discuss synthetic datasets for basic computer vision problems, both low-level (e.g., optical flow estimation) and high-level (e.g., semantic segmentation), synthetic environments and datasets  ...  In this work, we attempt to provide a comprehensive survey of the various directions in the development and application of synthetic data.  ...  opinion, define state of the art in the field for years to come.  ... 
arXiv:1909.11512v1 fatcat:qquxnw4dfvgmfeztbpdqhr44gy
« Previous Showing results 1 — 15 out of 42 results