Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Video motion information acquisition method and system and electronic equipment

A motion information and acquisition method technology, applied in the field of video task processing, can solve the problems of high storage cost, optical flow calculation may not be accurate, etc., and achieve the effect of low calculation cost, fast speed and simple implementation

Pending Publication Date: 2020-04-10
SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

It takes a lot of storage cost, and the optical flow calculation may not be accurate

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
  • Video motion information acquisition method and system and electronic equipment
  • Video motion information acquisition method and system and electronic equipment
  • Video motion information acquisition method and system and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0058] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application, not to limit the present application.

[0059] In order to solve the deficiencies in the existing technology, this application builds a network model for video motion information by predicting the surrounding frames from the current frame. In practical applications, a single frame image is input to the network model, and the network model outputs the surrounding frame corresponding to the single frame image. Frame images, or recognize image object classification results, and obtain moving objects in the video. This application can be applied to various video and image processing tasks such as image conversion, video classificati...

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 relates to a video motion information acquisition method and system and electronic equipment. The method comprises the following steps: constructing a network model for video motion information through a method of predicting a surrounding frame by a current frame; inputting a single-frame image into the constructed network model, and outputting a surrounding frame image correspondingto the single-frame image by the network model according to a loss function, wherein each individual loss function is a root-mean-square error of each pixel of each image, and the total loss functionL is L = LT + alpha1 (LT + 1 + LT-1) + alpha2 (LT + 2 + LT-2) + alpha3 (LT + 3 + LT-3)... + alpha n (LT + n + LT-n). According to the invention, the motion information of a video is obtained by usingthe method for predicting the surrounding frame by using the current frame, the understanding of the moving object in the video is facilitated, the realization is simple, the original network structure does not need to be changed, the parameter amount is not increased, the calculation amount of a network is not increased, the additional storage amount is not increased, the speed is faster, and the calculation cost is low.

Description

technical field [0001] The present application belongs to the technical field of video task processing, and in particular relates to a video motion information acquisition method, system and electronic equipment. Background technique [0002] In video tasks, the network model needs more reliable motion features to reflect the dynamic changes in the video and help the model to predict more accurately. The motion information in the video includes the motion of the camera and the motion of the objects in the video, as well as the influence of illumination changes. The actual environment between consecutive frames is complex and changeable, so obtaining video motion information is often a difficult point in processing video tasks. Existing treatments include: [0003] 1. Three-dimensional convolution [0004] Convolutional neural networks have been widely used in computer vision in recent years. For problems based on video analysis, two-dimensional convolution cannot capture i...

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): G06K9/00G06N3/04G06N3/08
CPCG06N3/08G06V20/42G06N3/045
Inventor 邬晶晶张涌文森特·周
Owner SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com