64 Hits in 4.9 sec

Arctic Vegetation Mapping Using Unsupervised Training Datasets and Convolutional Neural Networks

Zachary L. Langford, Jitendra Kumar, Forrest M. Hoffman, Amy L. Breen, Colleen M. Iversen
2019 Remote Sensing  
We then developed convolutional neural networks (CNNs) using the multi-sensor fusion datasets to map vegetation distributions using the original classes and the classes produced by the unsupervised classification  ...  The fusion of hyperspectral, multispectral, and terrain datasets was performed using unsupervised and supervised classification techniques over a ∼343 km2 area, and a high-resolution (5 m) vegetation classification  ...  Acknowledgments: The Next-Generation Ecosystem Experiments (NGEE Arctic) project is supported by the Office of Biological and Environmental Research in the DOE Office of Science.  ... 
doi:10.3390/rs11010069 fatcat:32nfe6smnnamtoloaw2qm35ydy

Understanding Convolutional Neural Networks in Terms of Category-Level Attributes [chapter]

Makoto Ozeki, Takayuki Okatani
2015 Lecture Notes in Computer Science  
We conducted several experiments by using the dataset AwA (Animals with Attributes) and a CNN trained for ILSVRC-2012 in a fully supervised setting to examine this conjecture.  ...  It has been recently reported that convolutional neural networks (CNNs) show good performances in many image recognition tasks.  ...  Transfer learning by deep neural networks The recent advances in the study of deep neural networks are initiated by the study of Hinton et al. [7] on unsupervised pretraining of deep networks.  ... 
doi:10.1007/978-3-319-16808-1_25 fatcat:uxo6jvvpdvaglf53v7zxwvahi4

SAR Image Change Detection based on Data Optimization and Self-supervised Learning

Wenhui Meng, Liejun Wang, Anyu Du, Yongming Li
2020 IEEE Access  
CONVOLUTION WAVELET NEURAL NETWORK CWNN is a kind of neural network that combines the convolutional neural network and wavelet transform.  ...  In [31] , a convolutional wavelet neural network with two convolution layers is used.  ...  [31] and proposed method run longer because their networks are more complex and need longer training time.  ... 
doi:10.1109/access.2020.3042017 fatcat:by7q5ob3xjalbaqn74q4ozgjvq


J. Dvořák, M. Potůčková, V. Treml
2022 ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
Convolutional neural networks (CNNs) effectively classify standard datasets in remote sensing (RS).  ...  Instead of training a model on a smaller, human-labelled dataset, we semiautomatically created training data using an ancillary normalised Digital Surface Model (nDSM) and image spectral information.  ...  This fact allowed us to use aboveground heights (where nDSM is available) as a feature to create the training and validation dataset.  ... 
doi:10.5194/isprs-annals-v-3-2022-33-2022 fatcat:fspgdt6csvhcxk4yum7wscuvmy

Heterogeneous Change Detection on Remote Sensing Data with Self-Supervised Deep Canonically Correlated Autoencoders

Federico Figari Tomenotti
2021 Septentrio Reports  
The proposed method is based on deep learning - involving autoencoders of convolutional neural networks - and represents an exapmple of unsupervised change detection.  ...  Two different datasets were used for the experiments, and the results obtained on both of them show the effectiveness of the proposed method.  ...  Acknowledgements I want to thank the Machine Learning Group (MLG) at The Arctic University of Norway (UiT) for the warm welcome and the constant support throughout my stay.  ... 
doi:10.7557/7.5763 fatcat:gyvlp75pnzf2jpiy3i5ohpr2p4

2020 Index IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Vol. 13

2020 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
., +, JSTARS 2020 783-793 Pansharpening via Unsupervised Convolutional Neural Networks.  ...  ., +, JSTARS 2020 783-793 Pansharpening via Unsupervised Convolutional Neural Networks.  ... 
doi:10.1109/jstars.2021.3050695 fatcat:ycd5qt66xrgqfewcr6ygsqcl2y

SCG-Net: Self-Constructing Graph Neural Networks for Semantic Segmentation [article]

Qinghui Liu, Michael Kampffmeyer, Robert Jenssen, Arnt-Børre Salberg
2021 arXiv   pre-print
available ISPRS Potsdam and Vaihingen datasets is achieved, with much fewer parameters, and at a lower computational cost compared to related pure convolutional neural network (CNN) based models.  ...  Inspired by recent work on graph neural networks, we propose the Self-Constructing Graph (SCG) module that learns a long-range dependency graph directly from the image and uses it to propagate contextual  ...  In convolutional neural networks (CNNs), the long-range pixel dependencies are mainly modeled by deeply stacked convolutional layers.  ... 
arXiv:2009.01599v2 fatcat:vloxd7bip5gpzeznmx64surzoq

Using Deep Learning to Count Albatrosses from Space: Assessing Results in Light of Ground Truth Uncertainty

Ellen Bowler, Peter T. Fretwell, Geoffrey French, Michal Mackiewicz
2020 Remote Sensing  
We collect counts from six observers, and train a convolutional neural network (U-Net) using leave-one-island-out cross-validation and different combinations of ground truth labels.  ...  cover and habitat, which was not present in the training dataset.  ...  The authors thank Henri Weimerskirch for allowing the use of the AP and GC images, which were acquired as part of a separate study, and additionally thank all volunteers who kindly gave up their time to  ... 
doi:10.3390/rs12122026 fatcat:chcloyon3vgy5hir5wxylorfym

Geographic Object-Based Image Analysis: A Primer and Future Directions

Maja Kucharczyk, Geoffrey J. Hay, Salar Ghaffarian, Chris H. Hugenholtz
2020 Remote Sensing  
Building on this foundation, we then review recent research on the convergence of GEOBIA with deep convolutional neural networks, which we suggest is a new form of GEOBIA.  ...  Overall, this paper describes the past, present, and anticipated future of GEOBIA in a novice-accessible format, while providing innovation and depth to experienced practitioners.  ...  Acknowledgments: We sincerely thank three anonymous reviewers for their thoughtful and constructive feedback which has significantly improved this paper.  ... 
doi:10.3390/rs12122012 fatcat:am3boyrc3fcznfu3nwr7a5qk6a

Scientific X-ray [article]

Qi Li, Xinbing Wang, Luoyi Fu, Chenghu Zhou
2021 arXiv   pre-print
of 71431 topic networks from scratch.  ...  The rapid development of modern science and technology has spawned rich scientific topics to research and endless production of literature in them.  ...  The topics are led by 'Image Super-Resolution Using Deep Convolutional Networks' and 'The capacity of wireless networks' respectively.  ... 
arXiv:2108.03458v4 fatcat:z6j7vdvf4bholg2xdrgk6conku

2019 Index IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Vol. 12

2019 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
., and Lopez, J.F  ...  ., JSTARS Nov. 2019 4530-4542 Ship Velocity Estimation From Ship Wakes Detected Using Convolutional Neural Networks.  ...  ., +, JSTARS Nov. 2019 4351-4360 Deep learning A Super-Resolution Convolutional-Neural-Network-Based Approach for Subpixel Mapping of Hyperspectral Images.  ... 
doi:10.1109/jstars.2020.2973794 fatcat:sncrozq3fjg4bgjf4lnkslbz3u

Table of Contents

2020 IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium  
doi:10.1109/igarss39084.2020.9323828 fatcat:6aittajt35gufeaugcmemu5cya

A review of neural networks in plant disease detection using hyperspectral data

Kamlesh Golhani, Siva K. Balasundram, Ganesan Vadamalai, Biswajeet Pradhan
2018 Information Processing in Agriculture  
A B S T R A C T This paper reviews advanced Neural Network (NN) techniques available to process hyperspectral data, with a special emphasis on plant disease detection.  ...  Firstly, we provide a review on NN mechanism, types, models, and classifiers that use different algorithms to process hyperspectral data.  ...  We acknowledge the valuable comments and suggestions given by the reviewers of this paper.  ... 
doi:10.1016/j.inpa.2018.05.002 fatcat:gwoo3nwdwrdgvmeinlcfge6mma

Concept Discovery for The Interpretation of Landscape Scenicness

Pim Arendsen, Diego Marcos, Devis Tuia
2020 Machine Learning and Knowledge Extraction  
Using visual feature representations from a Convolutional Neural Network (CNN), we learn a number of Concept Activation Vectors (CAV) aligned with semantic concepts from ancillary datasets.  ...  Our results suggest that new and potentially useful concepts can be discovered by leveraging neighbourhood structures in the word vector spaces.  ...  In the experiments, we use a ResNet50 convolutional neural network [10] , pretrained on ImageNet, in combination with a large image/concept database (Broden, see Section 3).  ... 
doi:10.3390/make2040022 fatcat:ixjo55rgszfl3kjecakph5lceq

A review of machine learning applications in wildfire science and management [article]

Piyush Jain, Sean C P Coogan, Sriram Ganapathi Subramanian, Mark Crowley, Steve Taylor, Mike D Flannigan
2020 arXiv   pre-print
Artificial intelligence has been applied in wildfire science and management since the 1990s, with early applications including neural networks and expert systems.  ...  We identified 298 relevant publications, where the most frequently used ML methods included random forests, MaxEnt, artificial neural networks, decision trees, support vector machines, and genetic algorithms  ...  The authors would also like to thank Intact Insurance and the Western Partnership for Wildland Fire Science for their support.  ... 
arXiv:2003.00646v1 fatcat:5ufhtbwlsvd2rdk3ogbmqpnxuu
« Previous Showing results 1 — 15 out of 64 results