Real-time synthetically generated video from still frames

• US 11,032,585 B2
• Filed: 06/28/2019
• Issued: 06/08/2021
• Est. Priority Date: 07/06/2018
• Status: Active Grant

• Current Assignee: Capital One Services LLC (Capital One Financial Corporation)
• Original Assignee: Capital One Services LLC (Capital One Financial Corporation)
• Inventors: Walters, Austin, Pham, Vincent, Key, Kate, Taylor, Kenneth, Truong, Anh, Abdi Taghi Abad, Fardin, Goodsitt, Jeremy
• Primary Examiner(s): Wills, Diane M
• Application Number:
  US16/457,670
• Publication Number:
  US 20190327501A1
• Time in Patent Office: 711 Days
• CPC Class Codes: G06F 11/3608 using formal methods, e.g. model checking, abstract interpretation theorem proving G06N5/013
• CPC Class Codes: G06F 11/3628 of optimised code optimisation G06F8/443
• CPC Class Codes: G06F 11/3636 by tracing the execution of the program
• CPC Class Codes: G06F 11/3684 for test design, e.g. generating new test cases
• CPC Class Codes: G06F 11/3688 for test execution, e.g. scheduling of test suites
• CPC Class Codes: G06F 16/215 Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
• CPC Class Codes: G06F 16/2237 Vectors, bitmaps or matrices
• CPC Class Codes: G06F 16/2264 Multidimensional index structures
• CPC Class Codes: G06F 16/2423 Interactive query statement specification based on a database schema
• CPC Class Codes: G06F 16/24568 Data stream processing; Continuous queries
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/254 Extract, transform and load [ETL] procedures, e.g. ETL data flows in data warehouses
• CPC Class Codes: G06F 16/258 Data format conversion from or to a database
• CPC Class Codes: G06F 16/283 Multi-dimensional databases or data warehouses, e.g. MOLAP or ROLAP
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06F 16/288 Entity relationship models
• CPC Class Codes: G06F 16/335 Filtering based on additional data, e.g. user or group profiles filtering in web context G06F16/9535, G06F16/9536
• CPC Class Codes: G06F 16/35 Clustering; Classification
• CPC Class Codes: G06F 16/90332 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 16/90335 Query processing
• CPC Class Codes: G06F 16/9038 : Presentation of query results
• CPC Class Codes: G06F 16/906 : Clustering; Classification
• CPC Class Codes: G06F 16/93 : Document management systems
• CPC Class Codes: G06F 17/15 : Correlation function computation including computation of convolution operations arithmetic circuits for sum of products per se, e.g. multiply-accumulators G06F7/5443; digital filters, e.g. FIR, IIR, adaptive filters H03H17/00
• CPC Class Codes: G06F 17/16 : Matrix or vector computation , e.g. matrix-matrix or matrix-vector multiplication, matrix factorization matrix transposition G06F7/78
• CPC Class Codes: G06F 17/18 : for evaluating statistical data , e.g. average values, frequency distributions, probability functions, regression analysis forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04
• CPC Class Codes: G06F 18/2115 : by evaluating different subsets according to an optimisation criterion, e.g. class separability, forward selection or backward elimination
• CPC Class Codes: G06F 18/214 : Generating training patterns; Bootstrap methods, e.g. bagging or boosting
• CPC Class Codes: G06F 18/2148 : characterised by the process organisation or structure, e.g. boosting cascade
• CPC Class Codes: G06F 18/217 : Validation; Performance evaluation; Active pattern learning techniques
• CPC Class Codes: G06F 18/2193 : based on specific statistical tests
• CPC Class Codes: G06F 18/22 : Matching criteria, e.g. proximity measures
• CPC Class Codes: G06F 18/23 : Clustering techniques
• CPC Class Codes: G06F 18/24 : Classification techniques
• CPC Class Codes: G06F 18/2411 : based on the proximity to a decision surface, e.g. support vector machines
• CPC Class Codes: G06F 18/2415 : based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
• CPC Class Codes: G06F 18/285 : Selection of pattern recognition techniques, e.g. of classifiers in a multi-classifier system
• CPC Class Codes: G06F 18/40 : Software arrangements specially adapted for pattern recognition, e.g. user interfaces or toolboxes therefor
• CPC Class Codes: G06F 21/552 : involving long-term monitoring or reporting
• CPC Class Codes: G06F 21/60 : Protecting data
• CPC Class Codes: G06F 21/6245 : Protecting personal data, e.g. for financial or medical purposes
• CPC Class Codes: G06F 21/6254 : by anonymising data, e.g. decorrelating personal data from the owner's identification
• CPC Class Codes: G06F 30/20 : Design optimisation, verification or simulation optimisation, verification or simulation of circuit designs G06F30/30
• CPC Class Codes: G06F 40/117 : Tagging; Marking up details of markup languages G06F40/143; Designating a block; Setting of attributes style sheets, e.g. eXtensible Stylesheet Language Transformation [XSLT], G06F40/154
• CPC Class Codes: G06F 40/166 : Editing, e.g. inserting or deleting
• CPC Class Codes: G06F 40/20 : Natural language analysis semantic analysis of natural language G06F40/30
• CPC Class Codes: G06F 8/71 : Version control security arrangements therefor G06F21/57; Configuration management
• CPC Class Codes: G06F 9/54 : Interprogram communication
• CPC Class Codes: G06F 9/541 : via adapters, e.g. between incompatible applications
• CPC Class Codes: G06F 9/547 : Remote procedure calls [RPC]; Web services
• CPC Class Codes: G06N 20/00 : Machine learning
• CPC Class Codes: G06N 20/10 : using kernel methods, e.g. support vector machines [SVM]
• CPC Class Codes: G06N 20/20 : Ensemble learning
• CPC Class Codes: G06N 3/04 : Architecture, e.g. interconnection topology
• CPC Class Codes: G06N 3/044 : Recurrent networks, e.g. Hopfield networks
• CPC Class Codes: G06N 3/045 : Combinations of networks
• CPC Class Codes: G06N 3/047 : Probabilistic or stochastic networks
• CPC Class Codes: G06N 3/06 : Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
• CPC Class Codes: G06N 3/08 : Learning methods
• CPC Class Codes: G06N 3/084 : Backpropagation, e.g. using gradient descent
• CPC Class Codes: G06N 3/088 : Non-supervised learning, e.g. competitive learning
• CPC Class Codes: G06N 5/00 : Computing arrangements using knowledge-based models
• CPC Class Codes: G06N 5/01 : Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
• CPC Class Codes: G06N 5/02 : Knowledge representation; Symbolic representation
• CPC Class Codes: G06N 5/022 : Knowledge engineering; Knowledge acquisition
• CPC Class Codes: G06N 5/04 : Inference or reasoning models
• CPC Class Codes: G06N 7/00 : Computing arrangements based on specific mathematical models
• CPC Class Codes: G06N 7/01 : Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06Q 10/04 : Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" market predictions or forecasting for commercial activities G06Q30/0202
• CPC Class Codes: G06T 11/001 : Texturing; Colouring; Generation of texture or colour inpainting G06T5/77
• CPC Class Codes: G06T 2207/10016 : Video; Image sequence
• CPC Class Codes: G06T 2207/10024 : Color image
• CPC Class Codes: G06T 2207/20081 : Training; Learning
• CPC Class Codes: G06T 2207/20084 : Artificial neural networks [ANN]
• CPC Class Codes: G06T 7/194 : involving foreground-background segmentation
• CPC Class Codes: G06T 7/246 : using feature-based methods, e.g. the tracking of corners or segments
• CPC Class Codes: G06T 7/248 : involving reference images or patches
• CPC Class Codes: G06T 7/254 : involving subtraction of images
• CPC Class Codes: G06V 10/768 : using context analysis, e.g. recognition aided by known co-occurring patterns
• CPC Class Codes: G06V 10/993 : Evaluation of the quality of the acquired pattern
• CPC Class Codes: G06V 30/194 : References adjustable by an adaptive method, e.g. learning
• CPC Class Codes: G06V 30/1985 : Syntactic analysis, e.g. using a grammatical approach syntactic image representation G06V30/18171
• CPC Class Codes: H04L 63/1416 : Event detection, e.g. attack signature detection
• CPC Class Codes: H04L 63/1491 : using deception as countermeasure, e.g. honeypots, honeynets, decoys or entrapment
• CPC Class Codes: H04L 67/306 : User profiles
• CPC Class Codes: H04L 67/34 : involving the movement of software or configuration parameters network booting or remote initial program loading [RIPL] G06F9/4416
• CPC Class Codes: H04N 21/23412 : for generating or manipulating the scene composition of objects, e.g. MPEG-4 objects
• CPC Class Codes: H04N 21/8153 : comprising still images, e.g. texture, background image

Abstract

Systems and methods for generating synthetic video are disclosed. For example, a system may include a memory unit and a processor configured to execute the instructions to perform operations. The operations may include receiving video data, normalizing image frames, generating difference images, and generating an image sequence generator model. The operations may include training an autoencoder model using difference images, the autoencoder comprising an encoder model and a decoder model. The operations may include identifying a seed image frame and generating a seed difference image from the seed image frame. The operations may include generating, by the image sequence generator model, synthetic difference images based on the seed difference image. In some aspects, the operations may include using the decoder model to synthetic normalized image frames from the synthetic difference images. The operations may include generating synthetic video by adding background to the synthetic normalized image frames.

Claims

1. A system for generating synthetic video, the system comprising:

one or more memory units for storing instructions; and

one or more processors configured to execute the instructions to perform operations comprising;

training, using a sequence of difference images, an image sequence generator model to generate synthetic difference images;

obtaining a seed difference image by one of;

receiving the seed difference image;

or

performing at least one of forward-step or backward-step encoding using an encoder model;

generating a sequence of synthetic difference images based on the seed difference image, wherein the sequence of synthetic difference images is generated by iteratively using the image sequence generator model to accept a previous synthetic difference image as an input and return a subsequent synthetic difference image as an output, starting from the seed difference image; and

generating a sequence of synthetic images based on the sequence of synthetic difference images, the generating comprising implementing a decoder model on the sequence of synthetic difference images to perform at least one of forward-step decoding or backward-step decoding.

2. The system of claim 1, the operations further comprising:

receiving the sequence of difference images.

3. The system of claim 1, the operations further comprising:

receiving a sequence of images; and

generating the sequence of difference images by performing a method of image subtraction on the sequence of images.

4. The system of claim 1, the operations further comprising:

receiving a sequence of images;

normalizing the sequence of images; and

generating the sequence of difference images by performing a method of image subtraction on the normalized sequence of images.

5. The system of claim 4, wherein normalizing the sequence of images comprises background subtraction.

6. The system of claim 5, wherein background subtraction comprises implementing a trained object recognition model.

7. The system of claim 6, wherein background subtraction comprises identifying a boundary using an image gradient method.

8. The system of claim 1, wherein:

the operations further comprise generating the image sequence generator model; and

training the image sequence generator model comprises training the generated image sequence generator model.

9. The system of claim 1, the operations further comprising:

training, using the sequence of difference images and a sequence of images corresponding to the sequence of difference images, the decoder model to generate a synthetic image based on a difference image.

10. The system of claim 1, the operations further comprising training an autoencoder model using the sequence of difference images and a sequence of images, the autoencoder model comprising an encoder model and the decoder model, wherein:

a difference image in the sequence of difference images corresponds to a preceding image in the sequence of images and a subsequent image in the sequence of images; and

training the autoencoder model comprises at least one of;

training the encoder model to generate to the difference image from the preceding image and training the decoder model to generate the subsequent image from the difference image;

or

training the encoder model to generate the difference image from the subsequent image and training the decoder model to generate the preceding image from the difference image.

11. The system of claim 10, wherein the sequence of images comprises normalized images.

12. The system of claim 1, wherein obtaining the seed difference image comprises receiving the seed difference image.

13. The system of claim 1, wherein:

obtaining the seed difference image comprises generating the seed difference image by performing the at least one of the forward-step or backward-step encoding using the encoder model; and

the encoder model corresponds to the decoder model.

14. The system of claim 1, the operations further comprising generating synthetic video by adding background to individual ones of the sequence of synthetic images.

15. The system of claim 14, wherein adding background comprises using a machine learning model to perform at least one of adjusting a color channel, adjusting a luminance channel, detecting edges, or detecting image features.

16. The system of claim 14, the operations further comprising generating a background image using a neural network model, and wherein adding background comprises combining the generated background image with the individual ones of the sequence of synthetic images.

17. The system of claim 1, wherein the image sequence generator model comprises at least one of a recurrent neural network (RNN) model, a generative adversarial network (GAN) model, an RNN-GAN model, a convolutional neural network model, or a long short-term memory model.

18. The system of claim 1, the operations further comprising retrieving the image sequence generator model from memory.

19. A method for generating synthetic video comprising:

training, using a sequence of difference images, an image sequence generator model to generate synthetic difference images;

obtaining a seed difference image by one of;

receiving the seed difference image;

or

performing at least one of a forward-step or backward-step encoding using an encoder model;

generating a sequence of synthetic difference images based on the seed difference image, wherein the sequence of synthetic difference images is generated by iteratively using the image sequence generator model to accept a previous synthetic difference image as an input and return a subsequent synthetic difference image as an output, starting from the seed difference image; and

generating a sequence of synthetic images based on the sequence of synthetic difference images, the generating comprising implementing a decoder model on the sequence of synthetic difference images to perform at least one of forward-step decoding or backward-step decoding.

20. A system for generating synthetic video, the system comprising:

one or more memory units for storing instructions; and

one or more processors configured to execute the instructions to perform operations comprising;

training, using a sequence of difference images, an image sequence generator model to generate synthetic difference images;

training an autoencoder model using the sequence of difference images and a sequence of images, the autoencoder model comprising an encoder model and a decoder model, wherein;

a difference image in the sequence of difference images corresponds to a preceding image in a sequence of images and a subsequent image in the sequence of images; and

training the autoencoder model comprises least one of;

training the encoder model to generate the difference image from the preceding image and training the decoder model to generate the subsequent image from the difference image;

or

training the encoder model to generate the difference image from the subsequent image and training the decoder model to generate the preceding image from the difference image;

obtaining a seed difference image by one of;

receiving the seed difference image;

or

performing at least one of forward-step or backward-step encoding using the encoder model;

generating a sequence of synthetic difference images based on the seed difference image, wherein the sequence of synthetic difference images is generated by iteratively using the image sequence generator model to accept a previous synthetic difference image as an input and return a subsequent synthetic difference image as an output, starting from the seed difference image; and

generating a sequence of synthetic images based on the sequence of synthetic difference images, the generating comprising implementing a decoder model on the sequence of synthetic difference images to perform at least one of forward-step decoding or backward-step decoding; and

generating synthetic video by adding background to individual ones of the sequence of synthetic images.