[go: up one dir, main page]

WO2018121798A1 - Dispositif et procédé de codage et de décodage vidéo basés sur un codeur automatique de profondeur - Google Patents

Dispositif et procédé de codage et de décodage vidéo basés sur un codeur automatique de profondeur Download PDF

Info

Publication number
WO2018121798A1
WO2018121798A1 PCT/CN2018/074719 CN2018074719W WO2018121798A1 WO 2018121798 A1 WO2018121798 A1 WO 2018121798A1 CN 2018074719 W CN2018074719 W CN 2018074719W WO 2018121798 A1 WO2018121798 A1 WO 2018121798A1
Authority
WO
WIPO (PCT)
Prior art keywords
video
layer
decoding
neural network
encoding
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2018/074719
Other languages
English (en)
Chinese (zh)
Inventor
陈天石
支天
罗宇哲
刘少礼
郭崎
陈云霁
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Cambricon Information Technology Co Ltd
Original Assignee
Shanghai Cambricon Information Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shanghai Cambricon Information Technology Co Ltd filed Critical Shanghai Cambricon Information Technology Co Ltd
Publication of WO2018121798A1 publication Critical patent/WO2018121798A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
    • H04N19/30—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using hierarchical techniques, e.g. scalability

Definitions

  • the present disclosure relates to the field of video compression and decompression, and in particular, to a video encoding and decoding apparatus and method based on a depth auto-encoder.
  • the traditional video coding technology is to eliminate the various types of redundancy existing in the video by different methods to achieve the purpose of compressing video.
  • techniques for temporal redundancy, spatial redundancy, visual redundancy, and coding redundancy for video use inter-frame coding, intra-frame coding, quantization, and entropy coding, respectively.
  • Transforming is also a common method of removing spatial redundancy.
  • Each video encoding method has a corresponding decoding method.
  • Complex coding standards achieve better compression ratios by combining different methods and using different implementations.
  • the main purpose of the present disclosure is to provide a video encoding and decoding apparatus and method based on a depth auto-encoder.
  • the depth codec-based video codec device of the present disclosure includes: a depth auto-encoder module, including a depth auto-encoder, the depth auto-encoder includes an encoding end, and the encoding end is used to compress the original video for the first time. Obtaining the first compressed data; the neural network codec module is configured to encode and compress the decoding end parameters to generate the encoded decoding end parameters; the hybrid codec module is configured to perform hybrid encoding on the first compressed data and the encoded decoding end parameters. , get video compression data.
  • the encoding end is an N-layer artificial neural network structure.
  • the first layer of the N-layer artificial neural network structure is an input layer
  • the second to N layers are hidden layers
  • the inter-layer units are fully connected
  • the intra-layer elements are not connected
  • the N-th layer is implicit.
  • the number of hidden cells in the layer is less than the number of input cells in the input layer.
  • the hybrid encoding comprises entropy encoding.
  • the entropy encoding comprises Huffman encoding.
  • the method further includes: a storage module, configured to store the first compressed data, the decoding end parameter, and the video compressed data.
  • the neural network codec module is configured to read the decoding end parameter from the storage module to encode and compress the decoding end parameter.
  • the hybrid codec module is configured to read the first compressed data from the storage module, and read the encoded decoding end parameters from the neural network codec module to perform The hybrid encoding and storing the video compressed data to the storage module.
  • the depth auto-encoder further includes: a decoding end; the hybrid codec module is further configured to decode the video compressed data to obtain the first decompressed data and the encoded decoding end parameter; The neural network codec module is further configured to decode the encoded decoding end parameter to obtain a decoding end parameter; the decoding end is configured to decode the first decompressed data to obtain original video data.
  • the storage module is further configured to store the first decompressed data, the encoded decoding end parameter, and the original video data.
  • the hybrid codec module is further configured to read the video compressed data from the storage module to decode the video compressed data.
  • the neural network codec module is further configured to read the encoded decoding end parameter from the storage module to decode the encoded decoding end parameter.
  • the depth autoencoder module is further configured to read the first decompressed data from the storage module, and read parameters of the decoding end from the neural network codec module, so that The decoding end decodes the first decompressed data.
  • the decoding end is an N-layer artificial neural network structure that is symmetric with the encoding end structure.
  • the nth layer of the decoding end is the (N-n+1)th layer of the encoding end
  • the weight matrix between the nth layer and the n+1th layer of the decoding end Is a transposition of a weight matrix between the (Nn)th layer and the (N-n+1)th layer of the encoding end, where 1 ⁇ n ⁇ N.
  • the depth autoencoder module is further configured to initialize the depth auto-encoder and train the depth auto-encoder by using training video to obtain depth automatic for video coding. Encoder.
  • the depth autoencoder module is further configured to perform training on the depth autocoder by using training video, including: using two adjacent layers of the depth autoencoder encoding end as a limitation a Boltzmann machine; initializing the limited Boltzmann machine; training the limited Boltzmann machine with the training video data; fine-tuning the depth autoencoder encoding end with a backpropagation algorithm A weight matrix to minimize the reconstruction error to the original input.
  • a controller is further included, interconnected with the depth autoencoder module, the neural network codec module, and the hybrid codec module for controlling the above modules.
  • the present disclosure also provides a video encoding method based on a depth auto-encoder, which uses the video encoding and decoding apparatus of any of the above to perform video encoding, including: compressing the original video for the first time, and obtaining the first compressed data; Encoding compression, obtaining encoded decoding end parameters; performing hybrid encoding on the first compressed data and the encoded decoding end parameters to obtain video compressed data.
  • the original video is first compressed using a first N-layer artificial neural network structure.
  • the first layer of the first N-layer artificial neural network structure is an input layer
  • the second to N layers are hidden layers
  • the inter-layer units are fully connected
  • the intra-layer elements are not connected.
  • the number of hidden cells of the N-layer hidden layer is smaller than the number of input cells of the input layer.
  • the hybrid encoding comprises entropy encoding.
  • the entropy encoding comprises Huffman encoding.
  • the method further includes: storing the first compressed data, the decoding end parameter, and the video compressed data.
  • the decoding end parameters are read to encode and compress the decoding end parameters.
  • the first compressed data and the encoded decoded end parameters are read to perform the hybrid encoding, and the video compressed data is stored.
  • the method further includes: decoding the video compressed data to obtain first decompressed data and the encoded decoding end parameter; and decoding the encoded decoding end parameter to obtain a decoding end parameter; Decoding the first decompressed data to obtain original video data.
  • the method further includes: storing the first decompressed data, the encoded decoding end parameters, and the original video data.
  • the video compression data is read to decode the video compression data.
  • the encoded decoder parameters are read to decode the encoded decoder parameters.
  • the first decompressed data and parameters of the decoding end are read to decode the first decompressed data.
  • the first decompressed data is decoded using a second N-layer artificial neural network structure that is symmetric with the first N-layer artificial neural network structure.
  • the nth layer of the second N-layer artificial neural network structure is the (N-n+1)th layer of the first N-layer artificial neural network structure
  • the second N The weight matrix between the nth layer and the n+1th layer of the layer artificial neural network structure is the weight between the (Nn)th layer and the (N-n+1)th layer of the first N layer artificial neural network structure The transposition of the matrix, where 1 ⁇ n ⁇ N.
  • the method before the first compression of the original video, the method further includes: initializing a depth auto-encoder; and training the deep auto-encoder with the training video data.
  • the training the depth autoencoder with the training video data comprises: using two adjacent layers of the depth autoencoder encoding end as a limited Boltzmann machine; initializing the limiting glass Using the training video data to train the restricted Boltzmann machine; using a backpropagation method to adjust the weight matrix of the depth autoencoder encoding end, minimizing the reconstruction of the original input error.
  • the method further includes: controlling the foregoing steps by using a controller.
  • a forward operation is sequentially performed on each layer in the N-layer artificial neural network structure; in an inverse order of the forward operation, in the N-layer artificial neural network structure
  • Each layer sequentially performs a reverse operation; performs weight update on each layer in the N-layer artificial neural network structure; and repeatedly performs the above steps multiple times to complete the training of the N-layer artificial neural network structure.
  • the performing the inverse operations sequentially on the layers in the N-layer artificial neural network structure includes: a first computing portion: obtained by the output neuron gradient and the input neurons Weight gradient; second operation portion: calculating the input neuron gradient using the output neuron gradient and weight.
  • performing weight update on each layer in the N-layer artificial neural network structure includes: updating the weight by using the weight gradient to obtain an updated weight .
  • the encoding result of video data by deep automatic encoder includes the characteristics of video data, which facilitates the classification and search of video data, and introduces machine learning into the field of video coding, which has broad development space and application prospects;
  • FIG. 1 is a schematic structural diagram of a video codec apparatus according to an embodiment of the present disclosure
  • FIG. 2 is a schematic diagram of a depth autoencoder of an embodiment of the present disclosure
  • FIG. 3 is a coding flowchart of a video encoding and decoding method according to an embodiment of the present disclosure
  • FIG. 4 is a flowchart of a deep autoencoder training of a video encoding and decoding method according to an embodiment of the present disclosure
  • FIG. 5 is a flowchart of decoding of a video encoding and decoding method according to an embodiment of the present disclosure.
  • FIG. 1 is a schematic structural diagram of the video encoding and decoding device, including a controller 10, a depth auto-encoder module 20, and a neural network codec module. 30, a hybrid codec module 40, a storage module 50; wherein
  • Controller 10 is interconnected with depth autoencoder module 20, neural network codec module 30, and hybrid codec module 40. Controller 10 includes a local command queue. The controller 10 is configured to store the control instructions compiled by the user program in the instruction queue, and decode them into control signals to control each module to complete its respective functions, and implement video encoding and decoding.
  • the storage module 50 is also interconnected with the depth autoencoder module 20, the neural network codec module 30, and the hybrid codec module 40 for storing various data and parameters in the video codec process.
  • the depth autoencoder module 20 includes a depth autoencoder including a structurally symmetric encoding end and a decoding end, the encoding end being an N-layer artificial neural network structure, wherein the first layer is an input layer, and the second to N The layer is a hidden layer, the inter-layer unit is fully connected, and the intra-layer unit has no connection.
  • the number of hidden units in the hidden layer of the N-th layer is smaller than the number of input units in the input layer, so that the effect of video compression can be achieved, wherein N is greater than or equal to 2.
  • the decoding end is an N-layer artificial neural network structure symmetric with the coding end structure.
  • the first layer (ie, the input layer) of the decoding end is the Nth layer hidden layer of the coding end
  • the second layer ie, the first layer is hidden
  • the layer containing) is the N-1 layer hidden layer of the encoding end
  • the weight matrix between the first layer and the second layer of the decoding end is the transposition of the weight matrix between the N-1th layer and the Nth layer of the encoding end.
  • the third layer of the decoding end (ie, the second layer hidden layer) is the N-2 layer hidden layer of the encoding end, and the weight matrix between the second layer and the third layer of the decoding end is the N-2 layer and the encoding end of the encoding end. Transpose of the weight matrix between the N-1 layers.
  • the Nth layer of the decoding end (ie, the Nth layer hidden layer) is the first layer of the encoding end (ie, the input layer), and the weight matrix between the N-1th layer and the Nth layer of the decoding end is the first of the encoding end.
  • the nth layer of the decoding end is the N-n+1 layer of the encoding end
  • the weight matrix between the two adjacent layers (the nth layer and the n+1th layer) of the decoding end is the adjacent two layers of the coding end (the first layer) Transposition of the weight matrix between the Nn layer and the N-n+1th layer).
  • the artificial neural network structure can be trained.
  • the training step is to perform a forward operation on each layer in a (multi-layer) artificial neural network, and then perform reverse operations in the order of the opposite layers, and finally calculate The gradient of the weights is used to update the weights; this is the sequential iteration of the training of the neural network, and the entire training process needs to be repeated several times.
  • the method for implementing artificial neural network training using an artificial neural network structure includes the following contents:
  • Forward operation steps First, a forward operation is sequentially performed on each layer in the multi-layer artificial neural network to obtain output neurons of each layer.
  • Reverse operation steps Then, in the reverse order of the forward operation, the layers in the multi-layer artificial neural network are sequentially subjected to an inverse operation to obtain a weight gradient of each layer and an input neuron gradient.
  • This step includes a first arithmetic part and a second arithmetic part.
  • the first arithmetic part is used to calculate the weight gradient.
  • the gradient of the weight of the layer is obtained by matrix multiplication or convolution of the output neuron gradient of the layer and the input neurons.
  • the second computational portion is used to calculate the input neuron gradient.
  • the input neuron gradient and weight can be used to calculate the input neuron gradient.
  • Weight update step Next, weight updates are performed on each layer in the multi-layer artificial neural network to obtain an updated weight. In this step, for each layer of the artificial neural network, the weight is updated with a weight gradient to obtain an updated weight.
  • the forward operation step, the reverse operation step, and the weight update step are repeatedly performed multiple times to complete the training of the multi-layer artificial neural network.
  • the entire training method requires repeated execution of the above process until the parameters of the artificial neural network meet the requirements, and the training process is completed.
  • a schematic diagram of a depth auto-encoder is exemplarily given.
  • the encoding end and the decoding end are five-layer artificial neural network structures, wherein the first layer hidden layer of the deep auto-encoder has 2000 units, the second layer has 1000 cells in the hidden layer, the hidden layer in the third layer has 500 cells, the hidden layer in the fourth layer has 30 cells, and the weight between the input layer and the hidden layer in the first layer
  • the matrix is W1
  • the weight matrix between the first layer hidden layer and the second layer hidden layer is W2
  • the weight matrix between the second layer hidden layer and the third layer hidden layer is W3
  • the weight matrix between the containing layer and the layer 4 hidden layer is W4.
  • the input layer of the decoding end has 30 units, the first layer has 500 cells, the second layer has 1000 cells, and the third layer has 2000 cells, the input layer and the first layer.
  • the weight matrix between the layer hidden layers is W T 4
  • the weight matrix between the first layer hidden layer and the second layer hidden layer is W T 3
  • the second layer hidden layer and the third layer hidden layer The weight matrix between them is W T 2
  • the weight matrix between the layer 3 hidden layer and the layer 4 hidden layer is W T 1 .
  • the depth autoencoder module 20 uses the encoding end of the depth autoencoder to compress the original video for the first time.
  • the original video data is input to the input layer of the encoding end, and is compressed by each layer of the encoding end and output by the hidden layer of the Nth layer to obtain the first compressed data.
  • the parameters of the decoding end are stored in the storage module 50, the parameters include the number of layers N of the decoding end, the number of units of each layer, and the weight matrix between the layers.
  • the neural network codec module 30 reads the parameters of the decoding end from the storage module 50, and encodes and compresses the parameters to generate the encoded decoding end parameters. Among them, the parameters can be encoded by a common coding method.
  • the hybrid codec module 40 performs secondary compression on the first compressed data. Specifically, it reads the first compressed data from the storage module 50, and reads the encoded decoding end parameters from the neural network codec module 30, and for the first time. The compressed data and the encoded decoding end parameters are mixed and encoded to obtain video compressed data, and stored in the storage module 50 to complete video compression.
  • the hybrid coding can adopt the Huffman coding isentropic coding mode.
  • the video codec device of the present disclosure uses the artificial neural network degree video to compress and compress the video twice, thereby improving the compression ratio of the video data, and because the artificial neural network has nonlinear characteristics, the parameters of the artificial neural network are taken as secrets.
  • the key realizes the integration of compression and encryption of video data.
  • the encoding result of video data by deep automatic encoder includes the characteristics of video data, which facilitates the classification and search of video data, and introduces machine learning into the field of video coding, which has broad development space and application prospects.
  • the video codec device of this embodiment may decode the video compressed data to reconstruct the original video data.
  • the hybrid codec module 40 decompresses the video compressed data for the first time. Specifically, it reads the video compressed data from the storage module 50, and decodes the video compressed data to obtain the first decompressed data and the encoded decoding end parameters, and stores the data in the decoded data. Storage module 50.
  • the decoding adopts a decoding manner corresponding to the hybrid encoding, and the first decompressed data is the first compressed data in the encoding process.
  • the neural network codec module 30 reads the encoded decoding end parameters from the storage module 50, and decodes the encoded decoding end parameters to obtain parameters of the decoding end.
  • the decoding adopts a decoding manner corresponding to the encoding mode of the decoding end parameter in the encoding process.
  • the depth autoencoder module 20 uses the decoding end to perform secondary decompression on the first decompressed data. Specifically, the deep autoencoder module 20 reads the first decompressed data from the storage module 50, and reads the parameters of the decoding end from the neural network codec module 30. The input layer of the data input decoding end is decompressed for the first time, and is decompressed by each layer of the decoding end and output by the hidden layer of the Nth layer to obtain original video data, and is stored in the storage module 50.
  • the video codec device of the present disclosure does not need to manually design a complicated codec process, and automatically extracts data features by using a deep automatic encoder, thereby greatly reducing manual intervention, realizing automation of the encoding process, and realizing simplicity and Good scalability, not only for video data compression, but also for other data compression.
  • the depth auto-encoder is generated by training.
  • the depth autoencoder module 20 first initializes a depth autoencoder, and then trains the encoding end of the depth autoencoder with the training video to obtain a depth autoencoder encoding end for video encoding.
  • the adjacent two layers of the deep autoencoder encoding end are used as a limited Boltzmann machine, the upper layer of the adjacent two layers is used as the visible layer, and the next layer is used as the hidden layer to limit the Boltzmann machine. Train.
  • v i is the i-th visible unit
  • h j is the j-th hidden unit
  • a i is the offset of the i-th visible unit v i
  • b j is the offset of the j-th hidden unit h j
  • w j is the weight connecting the jth hidden unit and the ith visible unit
  • n v and n h are the number of visible and hidden units, respectively.
  • the offset a i of the i-th visible cell v i is the i-th term of the offset vector a
  • the offset b j of the j-th hidden cell h j is the j-th term of the offset vector b
  • w j,i Is the element of the i-th column of the jth row in the weight matrix W
  • n s is the number of cells of the training sample set.
  • Boltzmann machine is trained. include:
  • ⁇ W, ⁇ a and ⁇ b are obtained using the CD-K algorithm
  • the above two steps are cycled J times to obtain a trained limited Boltzmann machine as a depth auto-encoder.
  • the steps of obtaining ⁇ W, ⁇ a and ⁇ b using the CD-K algorithm are as follows:
  • the back propagation algorithm is used to fine tune the weight matrix of the depth autoencoder's encoding end to minimize the reconstruction error to the original input. For example, when the weight matrix of the encoding end of the depth autoencoder is finely adjusted, the input/output unit and the hidden unit of the encoding end are no longer regarded as the unit of the Boltzmann machine, but the real output value of each unit is directly used. Since the encoder has been trained, a backpropagation algorithm can be used to adjust the weight matrix to minimize the reconstruction error of the encoder output.
  • Another embodiment of the present disclosure provides a video encoding and decoding method based on a depth auto-encoder. Referring to FIG. 3, the method includes:
  • step S101 the controller 10 sends an encoding instruction to the depth autoencoder module 20, and the encoding end of the deep autoencoder first compresses the original video.
  • step S102 the controller 10 sends an IO command to the depth autoencoder module 20, and the parameters of the first compressed data and the decoding end are stored in the storage module 50.
  • step S103 the controller 10 sends an IO command to the neural network codec module 30, and the neural network codec module 30 reads the parameters of the decoding end from the storage module 50.
  • step S104 the controller 10 sends an encoding instruction to the neural network codec module 30, and the neural network codec module 30 encodes and compresses the parameters.
  • step S105 the controller 10 sends an IO command to the hybrid codec module 40, and the hybrid codec module 40 reads the first compressed data from the storage module 50, and reads the encoded decoded terminal parameters from the neural network codec module 30.
  • step S106 the controller 10 sends an encoding instruction to the hybrid codec module 40, and the hybrid codec module 40 performs hybrid encoding on the first compressed data and the encoded decoding end parameters to obtain video compressed data.
  • step S107 the controller 10 sends an IO command to the hybrid codec module 40, and the hybrid codec module 40 stores the video compressed data in the storage module 50.
  • the method may further include:
  • Reading training video data from the storage module 50
  • the depth autoencoder is trained using training video data.
  • the video encoding and decoding method further includes:
  • step S201 the controller 10 sends an IO command to the hybrid codec module 40, and the hybrid codec module 40 reads the video compressed data from the storage module 50.
  • step S202 the controller 10 sends a decoding instruction to the hybrid codec module 40, and the hybrid codec module 40 decodes the video compressed data to obtain the first decompressed data and the encoded decoding end parameters.
  • step S203 the controller 10 sends an IO command to the hybrid codec module 40, and the hybrid codec module 40 stores the first decompressed data and the encoded decoder parameters in the storage module 50.
  • step S204 the controller 10 sends an IO command to the neural network codec module 30, and the neural network codec module 30 reads the encoded decoder parameters from the storage module 50.
  • step S205 the controller 10 sends a decoding instruction to the neural network codec module 30, and the neural network codec module 30 decodes the encoded decoding end parameters to obtain parameters of the decoding end.
  • step S206 the controller 10 sends an IO command to the depth autoencoder module 20, and the deep autoencoder module 20 reads the first decompressed data from the storage module 50, and reads the parameters of the decoding end from the neural network codec module 30.
  • step S207 the controller 10 sends a decoding instruction to the depth autoencoder module 20, and the depth autoencoder module 20 performs second decompression on the first decompressed data to obtain original video data.
  • step S208 the controller 10 sends an IO command to the depth autoencoder module 20, and the depth autoencoder module 20 stores the original video data in the storage module 50.
  • the present disclosure discloses a chip that includes the video codec described above.
  • the present disclosure discloses a chip package structure that includes the chip described above.
  • the present disclosure discloses a board that includes the chip package structure described above.
  • the present disclosure discloses an electronic device that includes the above-described card.
  • Electronic devices include data processing devices, robots, computers, printers, scanners, tablets, smart terminals, mobile phones, driving recorders, navigators, sensors, cameras, cloud servers, cameras, cameras, projectors, watches, headphones, mobile Storage, wearable device vehicles, household appliances, and/or medical devices.
  • the vehicle includes an airplane, a ship, and/or a vehicle;
  • the household appliance includes a television, an air conditioner, a microwave oven, a refrigerator, a rice cooker, a humidifier, a washing machine, an electric lamp, a gas stove, a range hood;
  • the medical device includes a nuclear magnetic resonance instrument, B-ultrasound and / or electrocardiograph.
  • each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of a software program module.
  • the integrated unit if implemented in the form of a software program module and sold or used as a standalone product, may be stored in a computer readable memory.
  • the technical solution of the present disclosure may be embodied in the form of a software product in the form of a software product in essence or in the form of a contribution to the prior art, and the computer software product is stored in a memory.
  • a number of instructions are included to cause a computer device (which may be a personal computer, server or network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present disclosure.
  • the foregoing memory includes: a U disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk, and the like, which can store program codes.
  • Each functional unit/module may be hardware, such as the hardware may be a circuit, including digital circuits, analog circuits, and the like.
  • Physical implementations of hardware structures include, but are not limited to, physical devices including, but not limited to, transistors, memristors, and the like.
  • the computing modules in the computing device can be any suitable hardware processor, such as a CPU, GPU, FPGA, DSP, ASIC, and the like.
  • the storage unit may be any suitable magnetic storage medium or magneto-optical storage medium such as RRAM, DRAM, SRAM, EDRAM, HBM, HMC, and the like.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Compression Or Coding Systems Of Tv Signals (AREA)

Abstract

La présente invention concerne un dispositif et un procédé de codage et de décodage vidéo basés sur un codeur automatique de profondeur. Le dispositif comprend : un module de codeur automatique de profondeur, un module de codec de réseau neuronal et un module de codec mixte. Le module codeur automatique de profondeur comprend un codeur automatique de profondeur. Le codeur automatique de profondeur comprend une extrémité de codage. L'extrémité de codage est utilisée pour réaliser une première compression sur une vidéo d'origine pour obtenir des données compressées une première fois. Le module de codec de réseau neuronal est utilisé pour réaliser un codage et une compression sur un paramètre de fin de décodage, de façon à générer un paramètre de fin de décodage qui a été codé. Le module de codec mixte est utilisé pour réaliser un codage mixte sur les données compressées une première fois et le paramètre de fin de décodage qui a été codé, de façon à obtenir les données de compression vidéo. Dans la présente invention, le taux de compression de données vidéo est amélioré en construisant un fin de codage et une fin de décodage qui sont symétriques dans la structure et en réalisant une compression et une décompression secondaires sur les données vidéo. En raison d'une caractéristique non linéaire d'un réseau neuronal artificiel, l'intégration d'une compression et d'un chiffrement de données vidéo est mise en œuvre, en utilisant un paramètre du réseau neuronal artificiel en tant que clef. Le résultat de codage des données vidéo contient une caractéristique des données vidéo, ce qui facilite la classification et la recherche des données vidéo et fournit un grand espace de développement et une grande perspective d'application. Sans le processus compliqué de codage et de décodage dans la conception manuelle, l'extraction automatique d'une caractéristique de données par le codeur automatique de profondeur réduit considérablement l'intervention manuelle, de telle sorte que l'automatisation du processus de codage est mise en œuvre, la mise en œuvre est simple, et l'extensibilité est satisfaisante, et par conséquent, la présente invention peut être utilisée pour compresser des données vidéo et peut également compresser d'autres données.
PCT/CN2018/074719 2016-12-30 2018-01-31 Dispositif et procédé de codage et de décodage vidéo basés sur un codeur automatique de profondeur Ceased WO2018121798A1 (fr)

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
CN201611269993 2016-12-30
CN201611269993.8 2016-12-30
CN201710068270.XA CN107046646B (zh) 2016-12-30 2017-02-07 基于深度自动编码器的视频编解码装置及方法
CN201710068270.X 2017-02-07

Publications (1)

Publication Number Publication Date
WO2018121798A1 true WO2018121798A1 (fr) 2018-07-05

Family

ID=59544165

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/074719 Ceased WO2018121798A1 (fr) 2016-12-30 2018-01-31 Dispositif et procédé de codage et de décodage vidéo basés sur un codeur automatique de profondeur

Country Status (2)

Country Link
CN (1) CN107046646B (fr)
WO (1) WO2018121798A1 (fr)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114697655A (zh) * 2020-12-30 2022-07-01 中国科学院计算技术研究所 均衡流间压缩速度的神经网络量化压缩方法及系统
CN117706360A (zh) * 2024-02-02 2024-03-15 深圳市昱森机电有限公司 电机运行状态的监测方法、装置、设备及存储介质

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107046646B (zh) * 2016-12-30 2020-05-22 上海寒武纪信息科技有限公司 基于深度自动编码器的视频编解码装置及方法
CN109308471B (zh) * 2018-09-29 2022-07-15 河海大学常州校区 一种肌电信号特征提取方法
CN109640095B (zh) * 2018-12-28 2020-12-25 中国科学技术大学 一种结合量子密钥分发的视频加密系统
CN110677681A (zh) * 2019-11-01 2020-01-10 合肥图鸭信息科技有限公司 一种视频编解码方法、装置及终端设备
CN110996108A (zh) * 2019-11-29 2020-04-10 合肥图鸭信息科技有限公司 一种视频帧重构方法、装置及终端设备
CN113347415B (zh) * 2020-03-02 2024-11-19 阿里巴巴集团控股有限公司 编码模式确定方法和装置

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103428495A (zh) * 2013-08-02 2013-12-04 中国联合网络通信集团有限公司 图像加密方法、图像解密方法和装置
CN104298973A (zh) * 2014-10-09 2015-01-21 北京工业大学 基于自编码器的人脸图像旋转方法
US20160093048A1 (en) * 2014-09-25 2016-03-31 Siemens Healthcare Gmbh Deep similarity learning for multimodal medical images
CN106203625A (zh) * 2016-06-29 2016-12-07 中国电子科技集团公司第二十八研究所 一种基于多重预训练的深层神经网络训练方法
CN107046646A (zh) * 2016-12-30 2017-08-15 上海寒武纪信息科技有限公司 基于深度自动编码器的视频编解码装置及方法

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100529311B1 (ko) * 2003-01-21 2005-11-17 삼성전자주식회사 신경 회로망을 이용하여 가변 길이 부호화 비트 스트림의길이를 선택하는 장치 및 방법
HUP0301368A3 (en) * 2003-05-20 2005-09-28 Amt Advanced Multimedia Techno Method and equipment for compressing motion picture data
WO2006099743A1 (fr) * 2005-03-25 2006-09-28 Algolith Inc. Dispositif et procede d'evaluation objective de la qualite d'une video codee en format dct avec ou sans sequence video d'origine
CN103369349B (zh) * 2012-03-28 2016-04-27 中国移动通信集团公司 一种数字视频质量控制方法及其装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103428495A (zh) * 2013-08-02 2013-12-04 中国联合网络通信集团有限公司 图像加密方法、图像解密方法和装置
US20160093048A1 (en) * 2014-09-25 2016-03-31 Siemens Healthcare Gmbh Deep similarity learning for multimodal medical images
CN104298973A (zh) * 2014-10-09 2015-01-21 北京工业大学 基于自编码器的人脸图像旋转方法
CN106203625A (zh) * 2016-06-29 2016-12-07 中国电子科技集团公司第二十八研究所 一种基于多重预训练的深层神经网络训练方法
CN107046646A (zh) * 2016-12-30 2017-08-15 上海寒武纪信息科技有限公司 基于深度自动编码器的视频编解码装置及方法

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114697655A (zh) * 2020-12-30 2022-07-01 中国科学院计算技术研究所 均衡流间压缩速度的神经网络量化压缩方法及系统
CN114697655B (zh) * 2020-12-30 2023-04-11 中国科学院计算技术研究所 均衡流间压缩速度的神经网络量化压缩方法及系统
CN117706360A (zh) * 2024-02-02 2024-03-15 深圳市昱森机电有限公司 电机运行状态的监测方法、装置、设备及存储介质

Also Published As

Publication number Publication date
CN107046646B (zh) 2020-05-22
CN107046646A (zh) 2017-08-15

Similar Documents

Publication Publication Date Title
WO2018121798A1 (fr) Dispositif et procédé de codage et de décodage vidéo basés sur un codeur automatique de profondeur
CN108271026B (zh) 压缩/解压缩的装置和系统、芯片、电子装置、方法
KR102771938B1 (ko) 신경망 모델 압축
CN114501031B (zh) 一种压缩编码、解压缩方法以及装置
US12120331B2 (en) System and method for compressing image based on flash in-memory computing array
CN110796251A (zh) 基于卷积神经网络的图像压缩优化方法
CN115022637B (zh) 一种图像编码方法、图像解压方法以及装置
CN116095183B (zh) 一种数据压缩方法以及相关设备
CN104504015A (zh) 一种基于动态增量式字典更新的学习算法
CN110909870A (zh) 训练装置及方法
JP2022551184A (ja) ブロック分割を伴うニューラルネットワークを復号する方法、装置及びプログラム
CN115941966A (zh) 一种视频压缩方法及电子设备
CN114501034B (zh) 基于离散高斯混合超先验和Mask的图像压缩方法及介质
Li et al. Multiple description coding based on convolutional auto-encoder
US20240221230A1 (en) Feature map encoding and decoding method and apparatus
CN114693811B (zh) 一种图像处理方法以及相关设备
CN110751274B (zh) 一种基于随机投影哈希的神经网络压缩方法及系统
CN115761446A (zh) 一种基于Swin-Transformer和自回归的图像压缩方法和系统
CN119232171B (zh) 一种面向孪生系统的数据智能压缩方法
CN111479286B (zh) 一种边缘计算系统减少通信流量的数据处理方法
Kandaswamy et al. Real-time hyper-dimensional reconfiguration at the edge using hardware accelerators
CN113096019A (zh) 图像重建方法、装置、图像处理设备及存储介质
CN117915107A (zh) 图像压缩系统、图像压缩方法、存储介质与芯片
CN118762090A (zh) 视觉处理的方法、装置、设备和存储介质
CN116260969A (zh) 一种自适应的通道渐进式编解码方法、装置、终端及介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18734040

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18734040

Country of ref document: EP

Kind code of ref document: A1