Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Video retargeting, or the challenge of transforming a video from one aspect ratio to another, has become a source of great interest in recent years. While the de-facto standard for filming productions has been 16:9 for a long time, the growth of social media and the broadening of screen sizes demand for an automatic conversion procedure. With this thesis, we provide an overview of the current practices for this field both in the literature and in the industry. We discuss why one dimensional cropping should be preferred over other hybrid techniques in the context of the broadcast industry. 

Resulting from this study, we introduce our own modular framework composed of two subsequent computational blocs. On one hand, the first module comprises a state-of-the-art video saliency detection model which locates and quantifies relevant information. As part of our contributions, we build our own saliency dataset called EVS-Sal and fine-tune the deep network to specialize its detections for soccer content. On the other hand, the second module is responsible for the selection of cropped salient information while ensuring temporal consistency. For this purpose, we explore both global and local optimizations respectively with the dynamic programming paradigm and with a “select and filter” approach. 

Finally, we show that our methods outperform current one dimensional retargeting algorithms on a variety of general videos. Additionally, we extend this analysis with the creation of our own soccer retargeting dataset called EVS-Ret. With the latter, we demonstrate that our framework brings results near inter-human agreement and that the semantics of soccer are correctly captured by the re-trained saliency model.

Video retargeting --- Video saliency detection --- One dimensional cropping --- Dynamic programming --- Ingénierie, informatique & technologie > Sciences informatiques

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

This Special Issue focused on novel vision-based approaches, mainly related to computer vision and machine learning, for the automatic analysis of human behaviour. We solicited submissions on the following topics: information theory-based pattern classification, biometric recognition, multimodal human analysis, low resolution human activity analysis, face analysis, abnormal behaviour analysis, unsupervised human analysis scenarios, 3D/4D human pose and shape estimation, human analysis in virtual/augmented reality, affective computing, social signal processing, personality computing, activity recognition, human tracking in the wild, and application of information-theoretic concepts for human behaviour analysis. In the end, 15 papers were accepted for this special issue. These papers, that are reviewed in this editorial, analyse human behaviour from the aforementioned perspectives, defining in most of the cases the state of the art in their corresponding field.

History of engineering & technology --- multi-objective evolutionary algorithms --- rule-based classifiers --- interpretable machine learning --- categorical data --- hand sign language --- deep learning --- restricted Boltzmann machine (RBM) --- multi-modal --- profoundly deaf --- noisy image --- ensemble methods --- adaptive classifiers --- recurrent concepts --- concept drift --- stock price direction prediction --- toe-off detection --- gait event --- silhouettes difference --- convolutional neural network --- saliency detection --- foggy image --- spatial domain --- frequency domain --- object contour detection --- discrete stationary wavelet transform --- attention allocation --- attention behavior --- hybrid entropy --- information entropy --- single pixel single photon image acquisition --- time-of-flight --- action recognition --- fibromyalgia --- Learning Using Concave and Convex Kernels --- Empatica E4 --- self-reported survey --- speech emotion recognition --- 3D convolutional neural networks --- k-means clustering --- spectrograms --- context-aware framework --- accuracy --- false negative rate --- individual behavior estimation --- statistical-based time-frequency domain and crowd condition --- emotion recognition --- gestures --- body movements --- Kinect sensor --- neural networks --- face analysis --- face segmentation --- head pose estimation --- age classification --- gender classification --- singular point detection --- boundary segmentation --- blurring detection --- fingerprint image enhancement --- fingerprint quality --- speech --- committee of classifiers --- biometric recognition --- multimodal-based human identification --- privacy --- privacy-aware

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

With the recent advances in remote sensing technologies for Earth observation, many different remote sensors are collecting data with distinctive properties. The obtained data are so large and complex that analyzing them manually becomes impractical or even impossible. Therefore, understanding remote sensing images effectively, in connection with physics, has been the primary concern of the remote sensing research community in recent years. For this purpose, machine learning is thought to be a promising technique because it can make the system learn to improve itself. With this distinctive characteristic, the algorithms will be more adaptive, automatic, and intelligent. This book introduces some of the most challenging issues of machine learning in the field of remote sensing, and the latest advanced technologies developed for different applications. It integrates with multi-source/multi-temporal/multi-scale data, and mainly focuses on learning to understand remote sensing images. Particularly, it presents many more effective techniques based on the popular concepts of deep learning and big data to reach new heights of data understanding. Through reporting recent advances in the machine learning approaches towards analyzing and understanding remote sensing images, this book can help readers become more familiar with knowledge frontier and foster an increased interest in this field.

metadata --- image classification --- sensitivity analysis --- ROI detection --- residual learning --- image alignment --- adaptive convolutional kernels --- Hough transform --- class imbalance --- land surface temperature --- inundation mapping --- multiscale representation --- object-based --- convolutional neural networks --- scene classification --- morphological profiles --- hyperedge weight estimation --- hyperparameter sparse representation --- semantic segmentation --- vehicle classification --- flood --- Landsat imagery --- target detection --- multi-sensor --- building damage detection --- optimized kernel minimum noise fraction (OKMNF) --- sea-land segmentation --- nonlinear classification --- land use --- SAR imagery --- anti-noise transfer network --- sub-pixel change detection --- Radon transform --- segmentation --- remote sensing image retrieval --- TensorFlow --- convolutional neural network --- particle swarm optimization --- optical sensors --- machine learning --- mixed pixel --- optical remotely sensed images --- object-based image analysis --- very high resolution images --- single stream optimization --- ship detection --- ice concentration --- online learning --- manifold ranking --- dictionary learning --- urban surface water extraction --- saliency detection --- spatial attraction model (SAM) --- quality assessment --- Fuzzy-GA decision making system --- land cover change --- multi-view canonical correlation analysis ensemble --- land cover --- semantic labeling --- sparse representation --- dimensionality expansion --- speckle filters --- hyperspectral imagery --- fully convolutional network --- infrared image --- Siamese neural network --- Random Forests (RF) --- feature matching --- color matching --- geostationary satellite remote sensing image --- change feature analysis --- road detection --- deep learning --- aerial images --- image segmentation --- aerial image --- multi-sensor image matching --- HJ-1A/B CCD --- endmember extraction --- high resolution --- multi-scale clustering --- heterogeneous domain adaptation --- hard classification --- regional land cover --- hypergraph learning --- automatic cluster number determination --- dilated convolution --- MSER --- semi-supervised learning --- gate --- Synthetic Aperture Radar (SAR) --- downscaling --- conditional random fields --- urban heat island --- hyperspectral image --- remote sensing image correction --- skip connection --- ISPRS --- spatial distribution --- geo-referencing --- Support Vector Machine (SVM) --- very high resolution (VHR) satellite image --- classification --- ensemble learning --- synthetic aperture radar --- conservation --- convolutional neural network (CNN) --- THEOS --- visible light and infrared integrated camera --- vehicle localization --- structured sparsity --- texture analysis --- DSFATN --- CNN --- image registration --- UAV --- unsupervised classification --- SVMs --- SAR image --- fuzzy neural network --- dimensionality reduction --- GeoEye-1 --- feature extraction --- sub-pixel --- energy distribution optimizing --- saliency analysis --- deep convolutional neural networks --- sparse and low-rank graph --- hyperspectral remote sensing --- tensor low-rank approximation --- optimal transport --- SELF --- spatiotemporal context learning --- Modest AdaBoost --- topic modelling --- multi-seasonal --- Segment-Tree Filtering --- locality information --- GF-4 PMS --- image fusion --- wavelet transform --- hashing --- machine learning techniques --- satellite images --- climate change --- road segmentation --- remote sensing --- tensor sparse decomposition --- Convolutional Neural Network (CNN) --- multi-task learning --- deep salient feature --- speckle --- canonical correlation weighted voting --- fully convolutional network (FCN) --- despeckling --- multispectral imagery --- ratio images --- linear spectral unmixing --- hyperspectral image classification --- multispectral images --- high resolution image --- multi-objective --- convolution neural network --- transfer learning --- 1-dimensional (1-D) --- threshold stability --- Landsat --- kernel method --- phase congruency --- subpixel mapping (SPM) --- tensor --- MODIS --- GSHHG database --- compressive sensing

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Radar-related technology is mainly processed within the time and frequency domains but, at the same time, is a multi-dimensional integrated system including a spatial domain for transmitting and receiving electromagnetic waves. As a result of the enormous technological advancements of the pioneers actively discussed in this book, research and development in multi-dimensional undeveloped areas is expected to continue. This book contains state-of-the-art work that should guide your research.

History of engineering & technology --- inverse synthetic aperture ladar (ISAL) --- maneuvering target --- integral cubic phase function (ICPF) --- fractional Fourier transform (FRFT) --- non-uniform fast Fourier transform (NUFFT) --- CLEAN technique --- simultaneous polarimetric radar --- constant modulus sequences --- correlation properties --- doppler tolerance --- saliency preprocessing LLC --- saliency detection --- image processing --- scene classification --- antenna array --- automatic guided vehicle --- DoA/DoD estimation --- MIMO radar --- direct position determination --- Doppler --- Doppler rate --- maximum likelihood estimator --- coherent pulse trains --- single moving sensor --- Cramer–Rao lower bound --- bistatic MIMO radar --- DOD/DOA estimation --- mutual coupling --- off-grid sparse problem --- unmanned aerial vehicle --- clustering methods --- man-made targets --- synthetic aperture radar (SAR) --- inverse synthetic aperture radar (ISAR) --- polarimetric decomposition --- Synthetic Aperture Radar (SAR) --- microwave imaging --- constitutive parameters --- conductivity --- permittivity --- tomography --- RF MEMS --- switch --- analytical approach --- low control voltage --- high switching speed --- high reliability --- radar echo cancellation --- frequency shifting modulation --- interrupted sampling --- radar jamming --- deception jamming --- remote sensing --- SAR --- radon transform --- speckle noise filtering --- maritime traffic monitoring --- wake detection and analysis --- synthetic aperture radar --- differential SAR tomography --- squinted SAR --- 3-D deformation --- 2-D PPS --- maneuvering target detection --- coherent integration --- motion parameter estimation --- second-order phase difference (SoPD) --- time-frequency analysis --- image fusion --- sparse representation --- hyperbolic tangent function --- guided filter --- narrowband interference separation --- block sparse Bayesian learning --- sensing matrix optimization --- block coherence measure --- bistatic inverse synthetic aperture radar --- linear geometry distortion --- prior information --- least square error --- lunar penetrating radar --- local correlation --- SNR --- K-L transform --- seislet transform --- generative adversarial nets --- through-wall radar imaging --- multipath ghost suppression --- generator and discriminator --- ultrahigh resolution --- spaceborne --- curved orbit --- series reversion --- singular value decomposition (SVD) --- deramping-based approach --- crosshole ground penetrating radar (GPR) --- Bayesian inversion --- Markov chain Monte Carlo (MCMC) --- forward model --- modeling error --- discrete cosine transform (DCT) --- through-wall imaging --- contrast target detection --- clutter reduction --- entropy thresholding --- low-rank approximation --- S-transformation --- ISAR --- micro-Doppler --- synchrosqueezing --- PBR (passive bistatic radar) --- clutter suppression --- non-uniform grid --- dilation morphology --- passive bistatic radar --- phased array radar --- parameter estimation --- aircraft surveillance --- GPR --- seasonal permafrost --- electromagnetic wave attribute --- relative water content --- marine radar --- wind direction retrieval --- small wind streak --- local gradient method --- adaptive reduced method --- energy spectrum method --- metamaterial absorber --- double negative --- dual-band --- FMCW radio altimeter --- methodological error --- critical height --- altitude measurement accuracy --- height pulses --- ultra-wide frequency deviation --- sparse recovery --- wideband noise interference --- dechirping --- subspace extraction --- denoising detection --- orthogonal matching pursuit --- pulse radar --- rotating target --- micro-motion feature extraction --- interrupted transmitting and receiving (ITR) --- dual-polarized radar --- DOA estimation --- atomic norm --- comprehensive SAR --- multiparametric SAR observation --- discrete scatterer model --- n/a --- Cramer-Rao lower bound

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Radar-related technology is mainly processed within the time and frequency domains but, at the same time, is a multi-dimensional integrated system including a spatial domain for transmitting and receiving electromagnetic waves. As a result of the enormous technological advancements of the pioneers actively discussed in this book, research and development in multi-dimensional undeveloped areas is expected to continue. This book contains state-of-the-art work that should guide your research.

History of engineering & technology --- inverse synthetic aperture ladar (ISAL) --- maneuvering target --- integral cubic phase function (ICPF) --- fractional Fourier transform (FRFT) --- non-uniform fast Fourier transform (NUFFT) --- CLEAN technique --- simultaneous polarimetric radar --- constant modulus sequences --- correlation properties --- doppler tolerance --- saliency preprocessing LLC --- saliency detection --- image processing --- scene classification --- antenna array --- automatic guided vehicle --- DoA/DoD estimation --- MIMO radar --- direct position determination --- Doppler --- Doppler rate --- maximum likelihood estimator --- coherent pulse trains --- single moving sensor --- Cramer-Rao lower bound --- bistatic MIMO radar --- DOD/DOA estimation --- mutual coupling --- off-grid sparse problem --- unmanned aerial vehicle --- clustering methods --- man-made targets --- synthetic aperture radar (SAR) --- inverse synthetic aperture radar (ISAR) --- polarimetric decomposition --- Synthetic Aperture Radar (SAR) --- microwave imaging --- constitutive parameters --- conductivity --- permittivity --- tomography --- RF MEMS --- switch --- analytical approach --- low control voltage --- high switching speed --- high reliability --- radar echo cancellation --- frequency shifting modulation --- interrupted sampling --- radar jamming --- deception jamming --- remote sensing --- SAR --- radon transform --- speckle noise filtering --- maritime traffic monitoring --- wake detection and analysis --- synthetic aperture radar --- differential SAR tomography --- squinted SAR --- 3-D deformation --- 2-D PPS --- maneuvering target detection --- coherent integration --- motion parameter estimation --- second-order phase difference (SoPD) --- time-frequency analysis --- image fusion --- sparse representation --- hyperbolic tangent function --- guided filter --- narrowband interference separation --- block sparse Bayesian learning --- sensing matrix optimization --- block coherence measure --- bistatic inverse synthetic aperture radar --- linear geometry distortion --- prior information --- least square error --- lunar penetrating radar --- local correlation --- SNR --- K-L transform --- seislet transform --- generative adversarial nets --- through-wall radar imaging --- multipath ghost suppression --- generator and discriminator --- ultrahigh resolution --- spaceborne --- curved orbit --- series reversion --- singular value decomposition (SVD) --- deramping-based approach --- crosshole ground penetrating radar (GPR) --- Bayesian inversion --- Markov chain Monte Carlo (MCMC) --- forward model --- modeling error --- discrete cosine transform (DCT) --- through-wall imaging --- contrast target detection --- clutter reduction --- entropy thresholding --- low-rank approximation --- S-transformation --- ISAR --- micro-Doppler --- synchrosqueezing --- PBR (passive bistatic radar) --- clutter suppression --- non-uniform grid --- dilation morphology --- passive bistatic radar --- phased array radar --- parameter estimation --- aircraft surveillance --- GPR --- seasonal permafrost --- electromagnetic wave attribute --- relative water content --- marine radar --- wind direction retrieval --- small wind streak --- local gradient method --- adaptive reduced method --- energy spectrum method --- metamaterial absorber --- double negative --- dual-band --- FMCW radio altimeter --- methodological error --- critical height --- altitude measurement accuracy --- height pulses --- ultra-wide frequency deviation --- sparse recovery --- wideband noise interference --- dechirping --- subspace extraction --- denoising detection --- orthogonal matching pursuit --- pulse radar --- rotating target --- micro-motion feature extraction --- interrupted transmitting and receiving (ITR) --- dual-polarized radar --- DOA estimation --- atomic norm --- comprehensive SAR --- multiparametric SAR observation --- discrete scatterer model --- inverse synthetic aperture ladar (ISAL) --- maneuvering target --- integral cubic phase function (ICPF) --- fractional Fourier transform (FRFT) --- non-uniform fast Fourier transform (NUFFT) --- CLEAN technique --- simultaneous polarimetric radar --- constant modulus sequences --- correlation properties --- doppler tolerance --- saliency preprocessing LLC --- saliency detection --- image processing --- scene classification --- antenna array --- automatic guided vehicle --- DoA/DoD estimation --- MIMO radar --- direct position determination --- Doppler --- Doppler rate --- maximum likelihood estimator --- coherent pulse trains --- single moving sensor --- Cramer-Rao lower bound --- bistatic MIMO radar --- DOD/DOA estimation --- mutual coupling --- off-grid sparse problem --- unmanned aerial vehicle --- clustering methods --- man-made targets --- synthetic aperture radar (SAR) --- inverse synthetic aperture radar (ISAR) --- polarimetric decomposition --- Synthetic Aperture Radar (SAR) --- microwave imaging --- constitutive parameters --- conductivity --- permittivity --- tomography --- RF MEMS --- switch --- analytical approach --- low control voltage --- high switching speed --- high reliability --- radar echo cancellation --- frequency shifting modulation --- interrupted sampling --- radar jamming --- deception jamming --- remote sensing --- SAR --- radon transform --- speckle noise filtering --- maritime traffic monitoring --- wake detection and analysis --- synthetic aperture radar --- differential SAR tomography --- squinted SAR --- 3-D deformation --- 2-D PPS --- maneuvering target detection --- coherent integration --- motion parameter estimation --- second-order phase difference (SoPD) --- time-frequency analysis --- image fusion --- sparse representation --- hyperbolic tangent function --- guided filter --- narrowband interference separation --- block sparse Bayesian learning --- sensing matrix optimization --- block coherence measure --- bistatic inverse synthetic aperture radar --- linear geometry distortion --- prior information --- least square error --- lunar penetrating radar --- local correlation --- SNR --- K-L transform --- seislet transform --- generative adversarial nets --- through-wall radar imaging --- multipath ghost suppression --- generator and discriminator --- ultrahigh resolution --- spaceborne --- curved orbit --- series reversion --- singular value decomposition (SVD) --- deramping-based approach --- crosshole ground penetrating radar (GPR) --- Bayesian inversion --- Markov chain Monte Carlo (MCMC) --- forward model --- modeling error --- discrete cosine transform (DCT) --- through-wall imaging --- contrast target detection --- clutter reduction --- entropy thresholding --- low-rank approximation --- S-transformation --- ISAR --- micro-Doppler --- synchrosqueezing --- PBR (passive bistatic radar) --- clutter suppression --- non-uniform grid --- dilation morphology --- passive bistatic radar --- phased array radar --- parameter estimation --- aircraft surveillance --- GPR --- seasonal permafrost --- electromagnetic wave attribute --- relative water content --- marine radar --- wind direction retrieval --- small wind streak --- local gradient method --- adaptive reduced method --- energy spectrum method --- metamaterial absorber --- double negative --- dual-band --- FMCW radio altimeter --- methodological error --- critical height --- altitude measurement accuracy --- height pulses --- ultra-wide frequency deviation --- sparse recovery --- wideband noise interference --- dechirping --- subspace extraction --- denoising detection --- orthogonal matching pursuit --- pulse radar --- rotating target --- micro-motion feature extraction --- interrupted transmitting and receiving (ITR) --- dual-polarized radar --- DOA estimation --- atomic norm --- comprehensive SAR --- multiparametric SAR observation --- discrete scatterer model