Supercharge Your Innovation With Domain-Expert AI Agents!

Human behavior prediction method and device

A prediction method and behavior technology, applied in the field of computer vision, can solve problems such as poor real-time performance, heavy recognition workload, and low efficiency

Inactive Publication Date: 2019-07-26
成都睿沿科技有限公司
View PDF8 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Among them, the manual recognition method mainly collects the video data of the surveillance area first, and then manually judges whether there are people with abnormal behavior in the surveillance video. The matching method mainly uses the Gaussian mixture model to obtain the human body contour and recognize human behavior according to the human body contour. It can only detect abnormalities and alarm when the behavior occurs or after the behavior occurs.
The existing human behavior prediction methods can only detect abnormalities after abnormal behaviors occur, and the real-time performance is poor.

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
  • Human behavior prediction method and device
  • Human behavior prediction method and device
  • Human behavior prediction method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0066] see figure 1 , figure 1 It is a schematic flowchart of a human behavior prediction method provided by an embodiment of the present invention. Among them, such as figure 1 As shown, the human behavior prediction method may include the following steps:

[0067] S101. Acquire an original video to be identified, and perform preprocessing on the original video to obtain a preprocessed video.

[0068] In the embodiment of the present application, the human behavior prediction method can be applied to public places such as kindergartens, schools, and nursing homes. The public place to be monitored is equipped with a camera device, and the original video to be identified can be obtained through the camera device.

[0069] In the embodiment of this application, before the original video to be identified is identified, the original video needs to be preprocessed, and the preprocessing method can be:

[0070] First, the original video is processed in grayscale transformation....

Embodiment 2

[0087] see figure 2 , figure 2 It is a schematic flowchart of a human behavior prediction method provided by an embodiment of the present invention. Among them, such as figure 2 As shown, the human behavior prediction method may include the following steps:

[0088] S201. Construct an original recognition model for predicting human behavior in a video, where the original recognition model includes an original feature extraction network and an original classification network.

[0089] S202. Obtain a training video used to train the original recognition model and a training action identifier corresponding to the training video.

[0090] S203. Perform segmentation processing on the training video to obtain a human movement video including human movement content in the training video.

[0091] In this embodiment of the present application, an inter-frame difference algorithm, a background difference algorithm, etc. may be used to segment the training video, which is not lim...

Embodiment approach

[0133] As an optional implementation, the human behavior prediction method may also include the following steps:

[0134] S212. Determine whether the predicted value corresponding to the behavior identifier is greater than the abnormal behavior threshold, and if so, perform step S213; if not, end the process.

[0135] S213. Output abnormal behavior alarm information.

[0136] In the embodiment of the present application, each behavior flag corresponds to a behavior abnormality threshold. After obtaining the human behavior prediction result, it can be judged whether there is an abnormality according to the behavior abnormality threshold corresponding to the behavior flag and the predicted value corresponding to the behavior flag. If it is judged that If the predicted value is greater than the abnormal behavior threshold, it indicates that the human behavior prediction corresponding to the behavior flag in the original video is abnormal, and the alarm information can be output i...

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 a human behavior prediction method and device, and the method comprises the steps: obtaining a to-be-identified original video, carrying out the preprocessing of the original video, removing the noise interference in the original video, and obtaining a preprocessed video; extracting human body behavior characteristics of the preprocessed video through a characteristic extraction network included in a pre-constructed artificial intelligence recognition model; and finally, processing the human body behavior characteristics through a behavior classification network included in the artificial intelligence recognition model to obtain a human body behavior prediction result including behavior identification, so that the human body behavior can be predicted, abnormity canbe predicted in time when an abnormal behavior just occurs, and the real-time performance is good.

Description

technical field [0001] The present application relates to the field of computer vision, in particular, to a method and device for predicting human behavior. Background technique [0002] At present, the safety of public places such as kindergartens, schools, and nursing homes has attracted people's attention. People need to monitor in real time whether there are people with abnormal behavior in the monitoring area (such as kindergartens, schools, nursing homes and other public places), so as to find and eliminate the safety hazards in the monitoring area in time. Existing human behavior recognition methods include artificial recognition and machine recognition. Among them, the manual recognition method mainly collects the video data of the surveillance area first, and then manually judges whether there are people with abnormal behavior in the surveillance video. The matching method mainly uses the Gaussian mixture model to obtain the human body contour and recognizes human...

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): G06K9/62G06K9/00
CPCG06V40/20G06F18/214G06F18/24
Inventor 曹亚滕雨橦吉翔
Owner 成都睿沿科技有限公司
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