Filters








2,654 Hits in 2.8 sec

Unsupervised deep feature extraction of hyperspectral images

Adriana Romero, Carlo Gatta, Gustavo Camps-Valls
2014 2014 6th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS)  
Index Terms-Convolutional networks, deep learning, sparse learning, feature extraction, hyperspectral image classification * The work of A.  ...  This paper presents an effective unsupervised sparse feature learning algorithm to train deep convolutional networks on hyperspectral images.  ...  Extracting expressive spatial-spectral features from hyperspectral images is thus of paramount relevance.  ... 
doi:10.1109/whispers.2014.8077647 dblp:conf/whispers/RomeroGC14 fatcat:2wpbpmki55bevfm22mp3vajmfq

DEEP NO LEARNING APPROACH FOR UNSUPERVISED CHANGE DETECTION IN HYPERSPECTRAL IMAGES

S. Saha, L. Kondmann, X. X. Zhu
2021 ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
Unsupervised deep transfer-learning based change detection (CD) methods require pre-trained feature extractor that can be used to extract semantic features from the target bi-temporal scene.  ...  Thus, we couple an untrained network with Deep Change Vector Analysis (DCVA), a popular method for unsupervised CD, to propose an unsupervised CD method for hyperspectral images.  ...  ACKNOWLEDGEMENTS The work is funded by the German Federal Ministry of Education and Research (BMBF) in the framework of the international future AI lab "AI4EO -Artificial Intelligence for Earth Observation  ... 
doi:10.5194/isprs-annals-v-3-2021-311-2021 fatcat:bllx2gqeb5hgllh43tmtp6zko4

Contrastive Learning Based on Transformer for Hyperspectral Image Classification

Xiang Hu, Teng Li, Tong Zhou, Yu Liu, Yuanxi Peng
2021 Applied Sciences  
The experimental results prove that our model can efficiently extract hyperspectral image features in unsupervised situations.  ...  Recently, deep learning has achieved breakthroughs in hyperspectral image (HSI) classification.  ...  Acknowledgments: The authors acknowledge the State Key Laboratory of High-Performance Computing, College of Computer, National University of Defense Technology, China.  ... 
doi:10.3390/app11188670 fatcat:vq4s7lw6hbgffjipaw2cwypkmq

Table of contents

2021 IEEE Transactions on Geoscience and Remote Sensing  
Results obtained on the same images by the unsupervised deep transcoding based method in terms of (e) increase and decrease of backscattering identified in the deep feature space and (f) changed buildings  ...  Franz 2562 Automatic Extraction of Sargassum Features From Sentinel-2 MSI Images ....................... M. Wang and C.  ... 
doi:10.1109/tgrs.2021.3052119 fatcat:obk5h6sp2nh47ounq4jqlhukcu

Unsupervised Feature Learning by Autoencoder and Prototypical Contrastive Learning for Hyperspectral Classification [article]

Zeyu Cao, Xiaorun Li, Liaoying Zhao
2020 arXiv   pre-print
Unsupervised learning methods for feature extraction are becoming more and more popular.  ...  of the two to learn more representative features.  ...  To apply the unsupervised contrastive learning to hyperspectral classification, we addressed the two problems and proposed ContrastNet, a deep learning model for unsupervised feature learning of hyperspectral  ... 
arXiv:2009.00953v1 fatcat:adwd6djgsjeo5fjv4maejgzs7m

Unsupervised Change Detection in Hyperspectral Images using Feature Fusion Deep Convolutional Autoencoders [article]

Debasrita Chakraborty, Ashish Ghosh
2021 arXiv   pre-print
The proposed work aims to build a novel feature extraction system using a feature fusion deep convolutional autoencoder for detecting changes between a pair of such bi-temporal co-registered hyperspectral  ...  Different methods have been applied to the extracted features to find the changes in the two images and it is found that the proposed method clearly outperformed the state of the art methods in unsupervised  ...  This manuscript also has not explored the capabilities of FFCAE feature extraction in a supervised or semi-supervised setting and concerns only with unsupervised binary change detection.  ... 
arXiv:2109.04990v1 fatcat:24xkanhlebdmzoem73ntjjobny

Change Detection in Hyperdimensional Images using Untrained Models

Sudipan Saha, Lukas Kondmann, Qian Song, Xiaoxiang Zhu
2021 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
Such feature extractors are not always available due to lack of training data, especially for hyperspectral sensors and other hyperdimensional images.  ...  Based on this proposition, we design a novel change detection framework for hyperdimensional images by extracting bi-temporal features using an untrained model and further comparing the extracted features  ...  at t 1 (X 1 ) image at t 2 (X 2 ) Pre-processing Pre-processing Deep feature extraction Deep feature extraction with untrained model with untrained model Deep feature comparison & analysis G Binary CD  ... 
doi:10.1109/jstars.2021.3121556 fatcat:6hyau7xirnfzzepmy45oa5nhxa

Advances in Deep Learning for Hyperspectral Image Analysis—Addressing Challenges Arising in Practical Imaging Scenarios [chapter]

Xiong Zhou, Saurabh Prasad
2020 Advances in Computer Vision and Pattern Recognition  
In this chapter, we will review recent advances in the community that leverage deep learning for robust hyperspectral image analysis despite these unique challenges -- specifically, we will review unsupervised  ...  In recent years, there has been an emergence of deep learning algorithms being applied to hyperspectral and multispectral imagery for remote sensing and biomedicine tasks.  ...  In this chapter, whenever the feature extraction component of a network is unsupervised (whether the backend model is supervised or unsupervised), we refer to this class of methods as carrying out "unsupervised  ... 
doi:10.1007/978-3-030-38617-7_5 fatcat:23ibk4ojbvepbpikxgjxan4i6e

SPATIAL-SPECTRAL CLASSIFICATION BASED ON THE UNSUPERVISED CONVOLUTIONAL SPARSE AUTO-ENCODER FOR HYPERSPECTRAL REMOTE SENSING IMAGERY

Xiaobing Han, Yanfei Zhong, Liangpei Zhang
2016 ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
Convolution mechanism is applied after the SAE feature extraction stage with the SAE features upon the larger outer window.  ...  To efficiently represent the spatial-spectral feature information around the central pixel within a neighbourhood window, the unsupervised convolutional sparse auto-encoder (UCSAE) with window-in-window  ...  Deep learning consists of two types of feature extraction and feature representation modelssupervised feature learning models and unsupervised feature learning models.  ... 
doi:10.5194/isprs-annals-iii-7-25-2016 fatcat:2uxpc3yz7bfmvhc3yqyp2hp7ni

Adversarial Learning based Discriminative Domain Adaptation for Geospatial Image Analysis

Nikhil Makkar, Hsiuhan Lexie Yang, Saurabh Prasad
2021 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
We are using adversarial learning to extract discriminative target domain features that are aligned with source domain.  ...  We test our framework for two very different applications of remote sensing imagery, multiclass classification in hyperspectral images and semantic segmentation in large scale satellite images.  ...  For hyperspectral image analysis application we used 3D-CNNs to extract better features by using both spatial and spectral data from hyperspectral data cubes, which is not possible with 1D-or 2D-CNNs.  ... 
doi:10.1109/jstars.2021.3132259 fatcat:5ppi25cwirc2bmnlgolauiwga4

Fully conv-deconv network for unsupervised spectral-spatial feature extraction of hyperspectral imagery via residual learning

Lichao Mou, Pedram Ghamisi, Xiao Xiang Zhu
2017 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)  
In this paper, we propose a novel network architecture, fully Conv-Deconv network with residual learning, for unsupervised spectral-spatial feature learning of hyperspectral images, which is able to be  ...  Hence, unsupervised feature learning, which has a quick access to arbitrary amount of unlabeled data, is conceptually of high interest.  ...  CONCLUSION In this paper, we proposed a novel end-to-end fully Conv-Deconv residual network architecture for unsupervised spectralspatial feature extraction of hyperspectral images.  ... 
doi:10.1109/igarss.2017.8128169 dblp:conf/igarss/MouGZ17 fatcat:alqnratpyfhihddgj2unpzm2v4

Salient object detection on hyperspectral images using features learned from unsupervised segmentation task [article]

Nevrez Imamoglu, Guanqun Ding, Yuming Fang, Asako Kanezaki, Toru Kouyama, Ryosuke Nakamura
2019 arXiv   pre-print
from unsupervised image segmentation task.  ...  A few studies using low-level features on hyperspectral images demonstrated that salient object detection can be achieved.  ...  Fig. 1 . 1 Proposed hyperspectral salient object detection model with unsupervised deep features .  ... 
arXiv:1902.10993v1 fatcat:xhympm5ifncrdg2f7i2ocdkmji

Approaches for Hyperspectral Image Classification Detailed Review

Kushalatha M R, Assistant Professor, Department of Electronics and communication Engineering, Nitte Meenakshi Institute of Technology, Bangalore, India., Prasantha H S, Beena R. Shetty, Professor, Department of Electronics and Communication Engineering, Nitte Meenakshi Institute of Technology (Affiliated to VTU, Belgaum), Bangalore., Assistant Professor, Department of Electronics and Communication in Nitte Meenakshi Institute of Technology, Bangalore
2021 International journal of soft computing and engineering  
Hyperspectral Image Classification of materials is the critical application of HSI using Hyperspectral sensors.  ...  The main reason behind the successful growth of the Hyperspectral imaging field is due to the enormous amount of spectral and spatial information that the imagery contains.  ...  Deep Learning in HSI Classification: The DL is the type of unsupervised feature learning technique which makes use of a large amount of image dataset.  ... 
doi:10.35940/ijsce.a3522.0911121 fatcat:dcgye2strbbatggko2sppc7cbm

Dimensionality Reduction Techniques For Hyperspectral Image using Deep Learning

2019 VOLUME-8 ISSUE-10, AUGUST 2019, REGULAR ISSUE  
This Research proposal addresses the issues of dimension reduction algorithms in Deep Learning(DL) for Hyperspectral Imaging (HSI) classification, to reduce the size of training dataset and for feature  ...  It includes CNN layers for feature extraction of input datasets that have better accuracy with minimum computational cost  ...  Here finds the purpose of dimensional reduction of hyperspectral images some techniques to reduce data dimensionality with effect to linear unsupervised leads to well known spectral feature extraction  ... 
doi:10.35940/ijitee.b1033.1292s319 fatcat:hillxk55sngt7o42xbtxpm4ea4

Unsupervised spectral sub-feature learning for hyperspectral image classification

Viktor Slavkovikj, Steven Verstockt, Wesley De Neve, Sofie Van Hoecke, Rik Van de Walle
2016 International Journal of Remote Sensing  
In this article, we propose an unsupervised feature learning method for classification of hyperspectral images.  ...  Our experimental results show that the proposed method outperforms other pixel-wise classification methods that make use of unsupervised feature extraction approaches.  ...  Unsupervised methods Some well-known unsupervised feature extraction methods used for hyperspectral images are based on principal component analysis (PCA) (Hotelling 1933; Chang et al. 1999) , independent  ... 
doi:10.1080/01431161.2015.1125554 fatcat:ef6tvu4qi5c3vnbqnygpe3rg6a
« Previous Showing results 1 — 15 out of 2,654 results