Info
- Utilizzare la checkbox di selezione a fianco di ciascun documento per attivare le funzionalità di stampa, invio email, download nei formati disponibili del (i) record.
Digital Signal, Image and Video Processing for Emerging Multimedia Technology
| Digital Signal, Image and Video Processing for Emerging Multimedia Technology |
| Autore | Kim Byung-Gyu |
| Pubbl/distr/stampa | Basel, Switzerland, : MDPI - Multidisciplinary Digital Publishing Institute, 2021 |
| Descrizione fisica | 1 online resource (392 p.) |
| Soggetto topico | History of engineering and technology |
| Soggetto non controllato |
3D
acauisition function adversarial loss aerial imagery affine motion model bayesian optimization bit allocation block-compressive sensing (BCS) capacitive touchscreen CenterNet channel allocation character order preserving classification closed circuit television (CCTV) cloud computing cloud system coefficient of variation content-based image retrieval convolution neural network convolutional neural network (CNN) convolutional neural networks de-noising deep leaning deep learning deep neural architecture denoise dependency detection depth map edge preserving electrical insulator error analysis Faster R-CNN fire and smoke detection flexible partitioning focus maps frame complexity gaussian process generative adversarial network genetic algorithms image classification image deblurring image fusion image processing image restoration image retrieval image similarity image stabilization image steganalysis inter-component prediction learning rate lexicon low light machine learning marine leisure activities MCV and MLV filters motion compensation motion estimation moving object multi-focus multi-scale analysis multiple feature multiview high efficiency video coding MVD n/a noise reduction noise removal non-linear filters object detection optical flow pattern mining pattern recognition perceptual loss perspective motion model privacy risk public key cryptography (PKC) quantization (signal) rate control RetinaNet reversible data hiding reversible data hiding (RDH) RFCN saliency scalable video coding scene recognition security sentiment analysis SNIPER social media spatial and temporal SSD step-less adaptive sampling super-resolution surveillance surveillance system ternary classification texture trimaps UAVs UNIWARD vector of locally aggregated descriptor video coding video surveillance VisDrone2019 VVC Wasserstein distance wavelet analysis wavelet transform weakly supervised attention map Wiener-Granger causality WOW wrist-mounted DiverPAD YOLOv3 ρ model |
| Formato | Materiale a stampa  |
| Livello bibliografico | Monografia |
| Lingua di pubblicazione | eng |
| Record Nr. | UNINA-9910557136003321 |
Kim Byung-Gyu
|
||
| Basel, Switzerland, : MDPI - Multidisciplinary Digital Publishing Institute, 2021 | ||
| Materiale a stampa | ||
| Lo trovi qui: Univ. Federico II | ||
| ||
Image and Video Processing and Recognition Based on Artificial Intelligence
| Image and Video Processing and Recognition Based on Artificial Intelligence |
| Autore | Park Kang Ryoung |
| Pubbl/distr/stampa | Basel, Switzerland, : MDPI - Multidisciplinary Digital Publishing Institute, 2021 |
| Descrizione fisica | 1 online resource (431 p.) |
| Soggetto topico | Technology: general issues |
| Soggetto non controllato |
action recognition
active learning armature artificial image generation artificial intelligence autoencoders bag of deep features binarized statistical image features biometrics body orientation bounding box regression brain computer interface building extraction camera position channel interaction character recognition common spatial patterns computer vision continuous wavelet transform convolutional neural network convolutional neural networks crowd counting cycle-consistent adversarial networks data augmentation deep convolutional neural networks deep learning depth map domain adaptation edges to photos emotion recognition entropy and response epidermis face image analysis face parsing face recognition facial attributes classification fast approximation feature distillation finger position finger-vein recognition fully convolutional networks GC-LSTM model generative adversarial net generative adversarial network generative adversarial network (GAN) generative models global context graph matching guidance helicopter footage heterogeneous database high-resolution remote sensing image HKPolyU-DB homotopy iterative hard thresholding image de-raining image processing image pyramid image-to-image conversion infrared circumferential scanning system joint attention K-nearest neighbors Krawtchouk polynomials label to photos lighting local context loss function malignant thyroid nodule Marr wavelets mask R-CNN medical image fusion monocular depth estimation multi resolution network multi-person multi-scale decomposition multi-task multitask learning normalized cross-correlation object recognition optimization orthogonal moments orthogonal polynomials pathology pose estimation prediction system presentation attack detection presentation attack face images RANSAC remote sensing residual network satellite image SDUMLA-HMT-DB semantic segmentation semi-supervised learning single-sample face recognition skin social robotics sparse coding super-resolution support vector machine surface defect detection surface inspection target recognition Tchebichef polynomials transfer learning typhoon ultrasound image unobserved database vehicle recognition weighted binary cross-entropy loss |
| Formato | Materiale a stampa |
| Livello bibliografico | Monografia |
| Lingua di pubblicazione | eng |
| Record Nr. | UNINA-9910557371203321 |
|
Park Kang Ryoung
|
||
| Basel, Switzerland, : MDPI - Multidisciplinary Digital Publishing Institute, 2021 | ||
| Materiale a stampa | ||
| Lo trovi qui: Univ. Federico II | ||
| ||