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

Behavior recognition method and device and computer equipment

A recognition method and behavioral technology, applied in the field of image recognition, can solve problems such as poor recognition accuracy, lack of recognition solutions, and low recognition efficiency, and achieve the effect of improving recognition accuracy and reducing background interference

Active Publication Date: 2021-07-02
TELLHOW SOFTWARE
View PDF13 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, in the field of behavior recognition, the existing technologies mostly focus on behavior recognition that does not distinguish between objects, but there is a lack of recognition schemes for specific behaviors of specific groups of people, and most of them are for behaviors with significant body movements such as skipping rope, waving, running, etc.
In particular, for the recognition of non-obvious physical behaviors such as smoking or playing with mobile phones, the current technical solutions have poor recognition accuracy and low recognition efficiency

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
  • Behavior recognition method and device and computer equipment
  • Behavior recognition method and device and computer equipment
  • Behavior recognition method and device and computer equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0052] figure 1 It is a schematic flowchart of a behavior recognition method provided by an embodiment of the present disclosure. Such as figure 1 As shown, the behavior recognition method mainly includes the following steps:

[0053] S101, extracting key points of bones of each object to be tested in the current frame image, wherein the key points of bones include at least key points of the wrist, key points of the elbow and key points of the shoulder;

[0054] This solution mainly judges whether there is smoking behavior or mobile phone behavior by performing behavior recognition on each object to be tested in the image. For example, video collection and image video are carried out on-site in the business hall to analyze whether there are abnormal behaviors such as staff or customers smoking or playing with mobile phones in the business hall, so that automatic monitoring of personnel behavior in specific scenes can be realized.

[0055] Such as figure 2 As shown, specif...

Embodiment approach

[0117] According to a specific implementation manner of the present disclosure, the step of acquiring the hand region image of the target object includes:

[0118] Taking the wrist key point of the target object as the center, intercept a square area with a preset side length as the hand area image.

[0119] In general, when the target object has the behavior of playing mobile phone or smoking, the corresponding mobile phone or cigarette will appear in the image of the area near the key point of the wrist, so the image of the square area centered on the key point of the wrist is intercepted as the image of the hand area. Input into the behavior recognition model for recognition.

[0120] In a specific implementation manner, the resolution of the monitored image is 1366×768, and the side length of the hand region image is set to 150. Of course, during specific implementation, different preset side lengths may be set according to specific conditions, which is not limited here.

...

Embodiment 2

[0123] see Figure 6 , is a block diagram of a behavior recognition device provided by an embodiment of the present disclosure. Such as Figure 6 As shown, the behavior recognition device 600 includes:

[0124] An extraction module 601, configured to extract key points of bones of each object to be measured in the current frame image, wherein the key points of bones include at least key points of the wrist, key points of the elbow and key points of the shoulder;

[0125] The search module 602 is used to search for the target object whose arm angle is smaller than the angle threshold from all the objects to be tested according to the key points of the skeleton, wherein the arm angle is the vector formed by the elbow key point and the shoulder key point and the elbow The angle between the key point and the vector formed by the wrist key point;

[0126] The first acquiring module 603 is configured to acquire a hand region image of the target object, wherein the hand region ima...

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 embodiment of the invention discloses a behavior recognition method. The method comprises the following steps: extracting skeleton key points of each to-be-detected object in a current frame image; according to the skeleton key points, searching target objects with arm included angles smaller than an included angle threshold value from all the to-be-detected objects; acquiring a hand region image of the target object; and identifying whether the hand region image of each target object contains the target object or not by using a pre-trained behavior identification model, and outputting a behavior identification result corresponding to each target object in the current frame image. Through combination of skeleton key point analysis and hand region image target identification, real-time identification of smoking and mobile phone playing behaviors of people in a monitoring image can be realized. Cigarette mobile phone recognition is carried out on the hand area image, background interference can be greatly reduced, and the recognition accuracy is improved.

Description

technical field [0001] The invention relates to the field of image recognition, in particular to a behavior recognition method, device and computer equipment. Background technique [0002] In order to improve the service quality of the staff in the business hall and maintain the good image of the company, it is necessary to strengthen the supervision of the working status and behavioral norms of the staff in the business hall. Employees smoking or playing with mobile phones during work will greatly affect their work efficiency and cause dissatisfaction among visiting customers. In addition, smoking in public places not only damages one's own health, but also seriously pollutes indoor air and affects the health of others. With the development of AI (Artificial Intelligence, AI for short) technology, image recognition is widely used in all aspects of life and production. Applying advanced image recognition technology to control the smoking and mobile phone behavior of the st...

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): G06K9/00G06N3/08
CPCG06N3/08G06V40/20Y02P90/30
Inventor 蔡逸超游华斌黄睿晏斐张远来
Owner TELLHOW SOFTWARE
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