Supercharge Your Innovation With Domain-Expert AI Agents!

Sampling method, model generation method, video behavior recognition method and device

A video and behavioral technology, applied in the field of video analysis, can solve the problems of lack of video sampling method and low precision, and achieve the effect of improving learning accuracy, improving effect and reducing influence

Active Publication Date: 2020-11-13
YUSUR TECH CO LTD
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the 3D convolutional neural network (C3D) based on deep learning is faster, its accuracy is lower than that of the dual-stream neural network.
[0007] Therefore, the intelligent behavior recognition algorithm based on deep learning lacks a more effective video sampling method

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
  • Sampling method, model generation method, video behavior recognition method and device
  • Sampling method, model generation method, video behavior recognition method and device
  • Sampling method, model generation method, video behavior recognition method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention more clear, the embodiments of the present invention will be further described in detail below in conjunction with the accompanying drawings. Here, the exemplary embodiments and descriptions of the present invention are used to explain the present invention, but not to limit the present invention.

[0029] The inventors found that the reason why the current video behavior recognition algorithm based on deep learning needs a more effective video sampling method to obtain data that is more suitable as the input of the neural network has the following three specific problems.

[0030] First, there is a large amount of time and space redundant data in video data: in a video scene, the images of two adjacent frames do not change much; in a single frame, there is a continuous area with similar or consistent colors. These redundant information occupy the input of the ne...

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 present invention provides a method for sampling video behavior data, a method for generating a video behavior recognition model, a method for video behavior recognition, electronic equipment, and a computer-readable storage medium, wherein the sampling method includes: extracting the video from encoded data of the video The encoding information of the first intermediate frame; the encoding information includes a motion vector; according to the difference between the encoding information of different coding units of the first intermediate frame, determine the feature area of ​​the first intermediate frame; in the determined When the motion vector in the coding information of the coding unit corresponding to the feature area of ​​the first intermediate frame is greater than or equal to the set motion threshold, determine the first sampling unit according to the feature area of ​​the first intermediate frame; according to the A first sampling unit determines data for sampling the video. Through the above solution, the present invention can effectively sample videos, thereby improving the effect of video behavior recognition.

Description

technical field [0001] The invention relates to the technical field of video analysis, in particular to a sampling method, a model generation method, a video behavior recognition method and a device. Background technique [0002] Behavior recognition is an important part of video analysis. It has many applications in security, behavior analysis and other fields. In recent years, video-oriented behavior recognition algorithms have received great attention. [0003] Video behavior recognition can be divided into traditional algorithms based on optical flow and intelligent algorithms based on deep learning. The behavior recognition algorithm based on optical flow uses pixels as the calculation unit to process certain frames in the video, which requires a large amount of calculation but good stability. Represented by the improved dense trajectory algorithm (IDT, Improved Dense Trajectories), it includes densely sampled feature points, feature point trajectory tracking, and traj...

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 Patents(China)
IPC IPC(8): G06K9/00G06N3/04G06N3/08
CPCG06N3/08G06N3/04G06V20/40
Inventor 鄢贵海赵巍岳
Owner YUSUR TECH CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com