Target posture recognition method and device, and camera

A recognition method and technology for a target object, which are applied in the field of gesture recognition method, device and camera of the target object, and can solve the problems of missed detection of the target posture, low recognition accuracy, and inability to obtain the pixel points of the target object with moving motion.

Pending Publication Date: 2020-05-05
HANGZHOU HIKVISION DIGITAL TECH
View PDF6 Cites 28 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the above method uses frame difference image analysis to extract target pixel points. When the target movement changes little, the pixel difference between adjacent frames is very small. At this time, the target pixel points with moving motion may not be obtained from the frame difference image. , which can easily lead to missed detection of the target posture, resulting in low recognition accuracy

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
  • Target posture recognition method and device, and camera
  • Target posture recognition method and device, and camera
  • Target posture recognition method and device, and camera

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0118] Embodiment 1: The following will take the recognition of the sitting posture of the human body as an embodiment.

[0119] see Figure 4 , Figure 4 It is a schematic flow chart of a method for standing up gesture recognition based on a target human body.

[0120] Step 401, start from collecting a frame of image, record the frame number f of the current frame;

[0121] Step 402, preprocessing the images: scaling the collected images according to the fixed size w×h to obtain image frames of the same size, one is to avoid the difference in image size due to the difference of the camera devices, and the other is to have the same size. It is beneficial to improve the accuracy of image analysis in subsequent steps.

[0122] Step 403, according to the human body key points preset by the human body parts related to the posture to be recognized, perform human body key point detection, and acquire and save each preset human body key point information J in the frame image. n，f...

Embodiment 2

[0152] Embodiment 2: The following will take the recognition of students' sitting postures as an example based on classroom video resources of distance education and taking the recording of classroom videos as an application scenario.

[0153] In the field of education and teaching, the emergence of distance education, smart classrooms, and classroom video surveillance has made modern education more convenient and efficient. At present, there are two ways to obtain course video resources in distance education. One is to use manual filming to record, and the other is to use a method based on traditional image processing to control the recording equipment to record automatically. However, the former method is reliable but expensive; the latter method is less expensive but unreliable. In the following embodiment, based on the recognition result of the sitting-up posture, the switching and adjustment of the long-distance and short-view shooting of the recording device are control...

Embodiment 3

[0194] Embodiment 3: Based on the classroom video resources of distance education, and taking the recording of the classroom video as the application scenario, the recognition of the gesture of writing on the blackboard when there is only one presenter is an embodiment.

[0195] When recording a course video, it is usually necessary to adjust the stretching ratio of the camera according to whether the presenter has blackboard writing behavior, so that the blackboard writing content of the presenter can be captured.

[0196] A known method for automatically recognizing writing behavior on a blackboard, comprising: analyzing a frame difference image between a current video frame and a previous video frame, obtaining human body pixels with moving motions according to the frame difference images, The formed figure is used as an outline, and it is judged whether there is blackboard writing according to the change of the outline.

[0197] However, the above methods use frame differe...

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 target object posture recognition method, and the method comprises the steps: obtaining a current video frame; detecting a preset key point of the target object in the current video frame, and obtaining preset key point information of the target object in the current frame; according to the preset key point information, judging whether the position change of the preset key points of the current target object in the current frame and the previous f frames meets a first preset attitude condition, and/or judging whether the position relationship between the preset key points of the current target object in the current frame meets a second preset attitude condition; if the preset posture condition is met, the current target object posture is recognized as a preset posture, f is a preset natural number, and the preset posture condition is set according to the position characteristics between the key points of the to-be-recognized posture of the target object. According to the method of the invention, the method can accurately recognize the small change of the posture, is wide in application range, is low in requirements for an image in a video frame, is high inposture recognition accuracy, and is small in false detection and missing detection of posture recognition.

Description

technical field [0001] The invention relates to the field of image analysis, in particular to a gesture recognition method, device and camera of a target object. Background technique [0002] With the development of image acquisition and analysis technology, analysis based on video or image data has been more and more widely used, for example, gesture detection or recognition of objects. [0003] The existing methods for realizing the gesture detection or recognition of the target object through video or image analysis are mainly: analyzing the frame difference image between the current frame and the previous frame, obtaining the target object pixel points with moving action according to the frame difference image, The figure composed of the moving target pixel points is used as the outline, and it is judged whether there is a specific posture according to the change of the outline. [0004] However, the above methods use frame difference image analysis to extract target pi...

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): G06K9/00G06K9/62
CPCG06V40/103G06V20/46G06F18/24G06F18/214
Inventor 吕瑞
Owner HANGZHOU HIKVISION DIGITAL TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap