Unlock instant, AI-driven research and patent intelligence for your innovation.

Optical flow generating device and method

A generation device and optical flow technology, applied in the field of computer vision, can solve the problems of large amount of calculation and slow speed, and achieve the effect of improving the training speed

Active Publication Date: 2020-07-10
SHANGHAI YITU NETWORK SCI & TECH
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Direct calculation of optical flow requires a large amount of calculation and is slow

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Optical flow generating device and method
  • Optical flow generating device and method

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0054] The optical flow generation device of the first embodiment of the present invention:

[0055] Such as figure 1 As shown, it is a schematic structural diagram of the optical flow generation device of the first embodiment of the present invention, figure 1 It mainly shows the structural schematic diagram of the optical flow generation device in the first embodiment of the present invention when training the first generator 1; the optical flow generation device in the first embodiment of the present invention includes: generating an adversarial network.

[0056] The generation confrontation network includes a first generator 1 and a discriminator 2 .

[0057] The first generator 1 includes a first neural network, and the first generator 1 inputs two frames of images and outputs a corresponding first predicted optical flow.

[0058] The output terminal of the first generator 1 is connected to the input terminal of the discriminator 2 .

[0059] The discriminator 2 includ...

no. 2 example

[0071] The optical flow generation device of the second embodiment of the present invention:

[0072] Such as figure 2 Shown is a schematic structural diagram of the optical flow generation device according to the second embodiment of the present invention, figure 2 It mainly shows the structural schematic diagram of the optical flow generation device in the second embodiment of the present invention when training the second generator 4; the optical flow generation device in the second embodiment of the present invention includes: generating an adversarial network.

[0073] The generation confrontation network includes a first generator 1 and a discriminator 2 .

[0074] The first generator 1 includes a first neural network, and the first generator 1 inputs two frames of images and outputs a corresponding first predicted optical flow.

[0075] The output terminal of the first generator 1 is connected to the input terminal of the discriminator 2 .

[0076] The discriminato...

no. 2 example

[0105] The optical flow generation method of the second embodiment of the present invention:

[0106] The optical flow generation method of the second embodiment of the present invention uses a generative adversarial network to generate optical flow, that is, uses figure 2 The shown optical flow generating device according to the second embodiment of the present invention generates optical flow.

[0107] Such as figure 2 As shown, the generative adversarial network includes a first generator 1 and a discriminator 2 .

[0108] The first generator 1 includes a first neural network, and the first generator 1 inputs two frames of images and outputs a corresponding first predicted optical flow.

[0109] The output terminal of the first generator 1 is connected to the input terminal of the discriminator 2 .

[0110] The discriminator 2 includes a second neural network, and the discriminator 2 inputs two frames of images and an optical flow, and the optical flow input by the dis...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an optical flow generation device. The device comprises a generative adversarial network, wherein the generative adversarial network comprises a first generator and a discriminator; the first generator comprises a first neural network, inputs two frames of images and outputs a corresponding first prediction optical flow; the output end of the first generator is connected with the input end of a discriminator; the discriminator comprises a second neural network, the discriminator inputs two frames of images and an optical flow and judges the authenticity of the input optical flow, and the optical flow input by the discriminator comprises a sample optical flow or a first prediction optical flow corresponding to the training set; the weight parameter of the first neural network of the first generator is obtained through training, and when the discriminator cannot distinguish the first prediction optical flow from the sample optical flow, the training of the first generator is completed. The invention also discloses an optical flow generation method. The method has a better light index and a faster training speed.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to an optical flow generation device. The invention also relates to a method for generating an optical flow. Background technique [0002] In the process of shooting a moving object or shooting the external environment when the object itself is moving, a continuous frame image will be formed. For the moving object in the frame image, the actual position of the moving object will change with time. changes, while the frame images are arranged in chronological order, so the position of the moving object in the frame image will also change continuously. The optical flow refers to the change of the position of the image corresponding to the moving object in different frame images; it can also be expressed as : In computer vision, optical flow defines the movement of objects in an image, which can be caused by camera movement or object movement. Specifically, it refers to the am...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/269G06N3/04G06N3/08
CPCG06T7/269G06N3/08G06T2207/20081G06T2207/20084G06N3/045
Inventor 康燕斌张志齐
Owner SHANGHAI YITU NETWORK SCI & TECH