Filters








746 Hits in 5.6 sec

Automatic Feature Learning for Spatio-Spectral Image Classification With Sparse SVM

Devis Tuia, Michele Volpi, Mauro Dalla Mura, Alain Rakotomamonjy, Remi Flamary
2014 IEEE Transactions on Geoscience and Remote Sensing  
Including spatial information is a key step for successful remote sensing image classification.  ...  Instead of imposing a filterbank with pre-defined filter types and parameters, we let the model figure out which set of filters is optimal for class separation.  ...  , Agricultural Research Service, for the access to the "Indian Pines 2010" SpecTIR image.  ... 
doi:10.1109/tgrs.2013.2294724 fatcat:dst6lhr7vfhnbbhs2wfaahjcl4

Sparse Concept Coded Tetrolet Transform for Unconstrained Odia Character Recognition [article]

Kalyan S Dash, N B Puhan, G Panda
2020 arXiv   pre-print
Feature representation in the form of spatio-spectral decomposition is one of the robust techniques adopted in automatic handwritten character recognition systems.  ...  In this regard, we propose a new image representation approach for unconstrained handwritten alphanumeric characters using sparse concept coded Tetrolets.  ...  The issue with existing spectral domain or spatio-spectral decomposition based feature extraction techniques such as wavelets is that of their fixed block dyadic structures.  ... 
arXiv:2004.01551v1 fatcat:paj4fpnatngddmy7eogk6fmfve

3D Convolutional Neural Networks for Crop Classification with Multi-Temporal Remote Sensing Images

Shunping Ji, Chi Zhang, Anjian Xu, Yun Shi, Yulin Duan
2018 Remote Sensing  
Deep learning is a representation-learning method that can automatically learn internal feature representations with multiple levels from original images instead of empirical feature design, and has proved  ...  Secondly, the 3D CNN framework with fine-tuned parameters is designed for training 3D crop samples and learning spatio-temporal discriminative representations, with the full crop growth cycles being preserved  ...  We appreciate Meng Lu from Utrecht University for editing the manuscript and Kebao Liu  ... 
doi:10.3390/rs10010075 fatcat:izqaipqm2zcu3ioocik7p7lwku

Transductive hyperspectral image classification: toward integrating spectral and relational features via an iterative ensemble system

Annalisa Appice, Pietro Guccione, Donato Malerba
2016 Machine Learning  
Classification is performed with an ensemble comprising a classifier learned by considering the available spectral information (associated with the pixel) and the classifiers learned by considering the  ...  For every pixel of a hyperspectral image, spatial neighborhoods are constructed and used to build application-specific relational features.  ...  using SGT, Vikas Sindhwani for his support in using SVMLin, Lynn Rudd for her help in reading the manuscript and Luigi Mascolo for his useful discussions on studies investigating SVMs.  ... 
doi:10.1007/s10994-016-5559-7 fatcat:ims577xfwrgspcyntnngwztfxa

A REVIEW ON MULTIPLE-FEATURE-BASED ADAPTIVE SPARSE REPRESENTATION (MFASR) AND OTHER CLASSIFICATION TYPES

S. Srinivasan, Dr. K. Rajakumar
2017 International Journal on Smart Sensing and Intelligent Systems  
The spectral and spatial information reflected from the original Hyperspectral Images with four various features.  ...  A new technique Multiple-feature-based adaptive sparse representation (MFASR) has been demonstrated for Hyperspectral Images (HSI's) classification.  ...  HSI, a method named Sparse Spatio -Spectral -LapSVM is implemented.  ... 
doi:10.21307/ijssis-2017-224 fatcat:k2x24hgfkjctxh3jwjssq5esle

Deep Feature Extraction and Feature Fusion for Bi-temporal Satellite Image Classification

Anju Asokan, J Anitha, Bogdan Patrut, Dana Danciulescu, D Jude Hemanth
2020 Computers Materials & Continua  
This method uses CNN to extract the spatio-spectral features from individual channels and fuse them with the textural features. Then the fused image is classified into change and unchanged regions.  ...  Deep feature extraction is important for multispectral image classification and is evolving as an interesting research area in change detection.  ...  Spatio-Spectral Feature Extraction Using CNN Spatio-spectral features are of great significance in detecting changes.  ... 
doi:10.32604/cmc.2020.012364 fatcat:jioaubmsrrhrhmfh5kkpjsfrbq

A Novel Multitemporal Deep Fusion Network (MDFN) for Short-term Multitemporal HR Images Classification

Yongjie Zheng, Sicong Liu, Qian Du, Hui Zhao, Xiaohua Tong, Michele Dalponte
2021 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
The LSTM branch is mainly used to learn the joint expression of different temporal-spectral features.  ...  High-resolution (HR) satellite images, due to the technical constraints on spectral and spatial resolutions, usually contain only several broad spectral bands but with a very high spatial resolution.  ...  ACKNOWLEDGMENT We would like to thank Planet Labs for providing the Dove images, and also thank the China Centre for Resources Satellite Data and Application for providing the Gaofen images.  ... 
doi:10.1109/jstars.2021.3119942 fatcat:edgi3fvdf5d5pf7yn2fo4bqv7q

Spatio-temporal Feature Classifier

Yun Wang, Suxing Liu
2015 Open Automation and Control Systems Journal  
We slide the temporal chunk along time axis to obtain samples from videos, and train the Support Vector Machine (SVM) with feature vectors.  ...  , instead we proposed a spatio-temporal feature classifier to obtain the union region of object from natural videos as the interest points.  ...  Spatio-temporal classifier algorithm. Fig. ( 4 4 ). Feature classification result of KTH dataset.Fig. (5). Contd…. Fig. ( 5 5 ). Feature classification result of Weizmann dataset.  ... 
doi:10.2174/1874444301507010001 fatcat:q566f3ootjg4jo267cwpychdeq

Multisource and Multitemporal Data Fusion in Remote Sensing [article]

Pedram Ghamisi, Behnood Rasti, Naoto Yokoya, Qunming Wang, Bernhard Hofle, Lorenzo Bruzzone, Francesca Bovolo, Mingmin Chi, Katharina Anders, Richard Gloaguen, Peter M. Atkinson, Jon Atli Benediktsson
2018 arXiv   pre-print
Moreover, thanks to the revisit capability of several spaceborne sensors, the integration of the temporal information with the spatial and/or spectral/backscattering information of the remotely sensed  ...  The sharp and recent increase in the availability of data captured by different sensors combined with their considerably heterogeneous natures poses a serious challenge for the effective and efficient  ...  The SVM model with the RBF kernels is adopted for a further comparison. Fig. 15 illustrates Several classification maps obtained by SVM, CNN, and FCN with or without using SMPs.  ... 
arXiv:1812.08287v1 fatcat:hmojxdoaybc6vjeto5s3x7b6z4

Latent semantic learning with structured sparse representation for human action recognition

Zhiwu Lu, Yuxin Peng
2013 Pattern Recognition  
In the new embedding space, we learn latent semantics automatically from abundant mid-level features through spectral clustering.  ...  The learnt latent semantics can be readily used for human action recognition with SVM by defining a histogram intersection kernel.  ...  by k-means clustering, extraction of high-level latent semantics by spectral embedding based on L 1 -graph, and action classification with SVM.  ... 
doi:10.1016/j.patcog.2012.09.027 fatcat:tkjtzttzc5gfjhxvuirai4oz5m

Automated Epileptic Seizure Detection in Pediatric Subjects of CHB-MIT EEG Database—A Survey

J. Prasanna, M. S. P. Subathra, Mazin Abed Mohammed, Robertas Damaševičius, Nanjappan Jothiraj Sairamya, S. Thomas George
2021 Journal of Personalized Medicine  
Performance metrics such as classification accuracy, sensitivity, and specificity were examined, and challenges in automatic seizure detection using the CHB-MIT database were addressed.  ...  This review paper focuses on the features of four domains, such as time, frequency, time-frequency, and nonlinear features, extracted from the EEG records, which were fed into several classifiers to classify  ...  The machine learning algorithm was applied to extract spatial, spectral, and temporal features for EEG classification [45] .  ... 
doi:10.3390/jpm11101028 pmid:34683169 fatcat:6hoqpkfzerbnzla7xfvznbgatq

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.  ...  learning of sparse features for aerial image classification [14] .  ... 
doi:10.1109/whispers.2014.8077647 dblp:conf/whispers/RomeroGC14 fatcat:2wpbpmki55bevfm22mp3vajmfq

Feature Learning from Spectrograms for Assessment of Personality Traits

Marc-Andre Carbonneau, Eric Granger, Yazid Attabi, Ghyslain Gagnon
2017 IEEE Transactions on Affective Computing  
The number of features, and difficulties linked to the feature extraction process are greatly reduced as only one type of descriptors is used, for which the 6 parameters can be tuned automatically.  ...  Each speech segment is then encoded using the dictionary, and the resulting feature set is used to perform classification of personality traits.  ...  In this paper, a method inspired by the recent developments in feature learning and image classification is proposed to alleviate these design choices for automatic assessment of personality traits.  ... 
doi:10.1109/taffc.2017.2763132 fatcat:kipic2crlvga5g3z2ge7fr3c6a

COMPARATIVE ANALYSIS OF SVM, ANN AND CNN FOR CLASSIFYING VEGETATION SPECIES USING HYPERSPECTRAL THERMAL INFRARED DATA

M. Hasan, S. Ullah, M. J. Khan, K. Khurshid
2019 The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
Each classifier was also tested for the advantage associated with increase in training samples or object segmentation size. Increase in the training samples improved the performance of SVM.  ...  This research examines the thermal infrared (2.5 to 14.0 μm) hyperspectral emissivity spectra (comprised of 3456 spectral bands) for the classification of thirteen different plant species  ...  Convolutional Neural Network (CNN) Deep learning is a very effective method for learning optimum features from large amount of training datasets automatically.  ... 
doi:10.5194/isprs-archives-xlii-2-w13-1861-2019 fatcat:xwc4dc7nzzfx3e7in3l5euuyjm

HybridSN: Exploring 3D-2D CNN Feature Hierarchy for Hyperspectral Image Classification [article]

Swalpa Kumar Roy, Gopal Krishna, Shiv Ram Dubey, Bidyut B. Chaudhuri
2019 arXiv   pre-print
Hyperspectral image (HSI) classification is widely used for the analysis of remotely sensed images. Hyperspectral imagery includes varying bands of images.  ...  The 3D-CNN facilitates the joint spatial-spectral feature representation from a stack of spectral bands. The 2D-CNN on top of the 3D-CNN further learns more abstract level spatial representation.  ...  Convolutional neural network (CNN) is a deep learning model designed for the automatic feature extraction from the images for different tasks [15] .  ... 
arXiv:1902.06701v3 fatcat:dsrxyewgmngs5lgmtrcod5t33u
« Previous Showing results 1 — 15 out of 746 results