Processing

Please wait...

Settings

Settings

Goto Application

1. WO2021027238 - IMAGE COMPRESSION SYSTEM AND METHOD BASED ON FLASH STORAGE AND CALCULATION ARRAY

Publication Number WO/2021/027238
Publication Date 18.02.2021
International Application No. PCT/CN2019/130472
International Filing Date 31.12.2019
IPC
H04N 19/42 2014.01
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
NPICTORIAL COMMUNICATION, e.g. TELEVISION
19Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
42characterised by implementation details or hardware specially adapted for video compression or decompression, e.g. dedicated software implementation
G06N 3/08 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
CPC
G06N 3/0445
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architectures, e.g. interconnection topology
0445Feedback networks, e.g. hopfield nets, associative networks
G06N 3/0454
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architectures, e.g. interconnection topology
0454using a combination of multiple neural nets
G06N 3/084
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
084Back-propagation
H04N 19/124
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
NPICTORIAL COMMUNICATION, e.g. TELEVISION
19Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
10using adaptive coding
102characterised by the element, parameter or selection affected or controlled by the adaptive coding
124Quantisation
H04N 19/182
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
NPICTORIAL COMMUNICATION, e.g. TELEVISION
19Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
10using adaptive coding
169characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding
182the unit being a pixel
H04N 19/42
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
NPICTORIAL COMMUNICATION, e.g. TELEVISION
19Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
42characterised by implementation details or hardware specially adapted for video compression or decompression, e.g. dedicated software implementation
Applicants
  • 北京大学 PEKING UNIVERSITY [CN]/[CN]
Inventors
  • 康晋锋 KANG, Jinfeng
  • 项亚臣 XIANG, Yachen
  • 黄鹏 HUANG, Peng
  • 刘晓彦 LIU, Xiaoyan
  • 韩润泽 HAN, Runze
Agents
  • 中科专利商标代理有限责任公司 CHINA SCIENCE PATENT & TRADEMARK AGENT LTD.
Priority Data
201910738965.312.08.2019CN
Publication Language Chinese (ZH)
Filing Language Chinese (ZH)
Designated States
Title
(EN) IMAGE COMPRESSION SYSTEM AND METHOD BASED ON FLASH STORAGE AND CALCULATION ARRAY
(FR) SYSTÈME ET PROCÉDÉ DE COMPRESSION D'IMAGE BASÉS SUR UN RÉSEAU DE STOCKAGE ET DE CALCUL FLASH
(ZH) 基于FLASH存算阵列的图像压缩系统和方法
Abstract
(EN)
The present disclosure provides an image compression system and method based on a FLASH storage and calculation array. The image compression system comprises a coding convolutional neural network based on a FLASH storage and calculation array, a decoding convolutional neural network based on a FLASH storage and calculation array, and a quantization module. The coding convolutional neural network based on a FLASH storage and calculation array codes an original image to obtain a feature image; the quantization module quantizes the feature image to obtain a quantized image; the decoding convolutional neural network based on a FLASH storage array decodes the quantized image to obtain a compressed image.
(FR)
La présente invention concerne un système et un procédé de compression d'image basés sur un réseau de stockage et de calcul FLASH. Le système de compression d'image comprend un réseau neuronal convolutif de codage basé sur un réseau de stockage et de calcul FLASH, un réseau neuronal convolutif de décodage basé sur un réseau de stockage et de calcul FLASH, et un module de quantification. Le réseau neuronal convolutif de codage basé sur un réseau de stockage et de calcul FLASH code une image d'origine pour obtenir une image caractéristique ; le module de quantification quantifie l'image caractéristique pour obtenir une image quantifiée ; le réseau neuronal convolutif de décodage basé sur un réseau de stockage et de calcul FLASH décode l'image quantifiée pour obtenir une image compressée.
(ZH)
本公开提供了一种基于FLASH存算阵列的图像压缩系统和方法,图像压缩系统包括:基于FLASH存算阵列的编码卷积神经网络、基于FLASH存算阵列的解码卷积神经网络和量化模块;所述基于FLASH存算阵列的编码卷积神经网络对原始图像进行编码,得到特征图像;所述量化模块对所述特征图像进行量化,得到量化图像;所述基于FLASH存算阵列的解码卷积神经网络对所述量化图像进行解码,得到压缩图像。
Also published as
Latest bibliographic data on file with the International Bureau