Human abnormal posture detection system and method based on three-dimensional vision

A three-dimensional vision and detection method technology, applied in the field of computer vision, can solve problems such as increasing the range of fall detection

Active Publication Date: 2019-02-12
QILU UNIV OF TECH
View PDF2 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The technical task of the present invention is to provide a human body abnormal posture detection system and method based on three-dimensional vision to solve the problem of how to increase the detection range of falls, effectively avoid blocking objects in the detection process, and how to accurately detect falls. question

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 abnormal posture detection system and method based on three-dimensional vision
  • Human abnormal posture detection system and method based on three-dimensional vision
  • Human abnormal posture detection system and method based on three-dimensional vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0082]The method for detecting abnormal posture of a human body based on three-dimensional vision of the present invention is that the Kinect somatosensory sensor is mounted on a mobile platform, and the mobile platform adopts a Mecanum wheel as a moving wheel, so that the mobile platform equipped with the Kinect somatosensory sensor can move following the movement of the human body , and use the Kinect somatosensory sensor to obtain the distance from the mobile platform to the human bone point, convert the acquired distance change into an electrical signal and send it to the mobile platform, so that the mobile platform can move along with the moving direction of the human body, and the mobile platform can be controlled according to the distance change The moving speed of the Mecanum wheel ensures that the mobile platform maintains a set distance from the human body; at the same time, according to the pictures captured by the camera on the Kinect somatosensory sensor, the inform...

Embodiment example

[0145] (1) Calculate the distance from the joint point to the plane: according to the extracted five feature key points and the two established planes L 1 and L 2 To calculate the distance from point to surface to determine the occurrence of falls.

[0146] The coordinates of the known point M (x M ,y M ,z M ) and the plane equation L: Ax+By+Cz+D=0, the distance formula from point M to plane L: First calculate the distance formula of the five bone feature points to the plane L1 respectively: Then calculate the distance formula of the five bone feature points to the plane L2 respectively:

[0147] For the Kinect somatosensory sensor, using the acquired five characteristic skeleton points, each frame of data will obtain five characteristic skeleton points to the plane L 1 and plane L 2 If the ten distance data are directly summed or averaged on the ten data, the obtained data is not very convincing and representative, and the error of the obtained data will be relativ...

Embodiment 3

[0171] This embodiment is a human body abnormal posture detection system based on three-dimensional vision, which is used to realize the human body abnormal posture detection method based on three-dimensional vision in Embodiment 1, including a mobile platform, four mobile wheels are installed on the lower side of the mobile platform, and the mobile wheels adopt Mecanum wheel; the upper side of the mobile platform is equipped with a Kinect somatosensory sensor, and the Kinect somatosensory sensor is equipped with a Depth sensor. The Depth sensor uses the time reflected back by the infrared pulse projected by TOF (Time of Flight) technology to obtain the Depth data (and sensor) distance information). The Kinect somatosensory sensor is wirelessly connected to an upper PC, and the upper PC communicates with the mobile platform in a wireless communication manner through the serial port Bluetooth; the mobile platform is also equipped with a DC motor, a main controller, a lithium bat...

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 abnormal posture detection system and method based on three-dimensional vision, and belongs to the technical field of computer vision. The technical problems to be solved by the invention is how to enlarge the fall detection range, effectively avoiding the blocking of the blocking object in the detection process, at that same time, how to detect the fall accurately.The adopted technical scheme is characterized in that a Kinect somatosensor is mounted on a mobile platform using a Mecanum wheel, so that the mobile platform equipped with the Kinect somatosensor can move with the human body; the kinect somatosensor is used to obtain the distance between the mobile platform and the human skeleton point, and the obtained distance change is converted into an electric signal to be sent to the mobile platform, so that the mobile platform can move with the moving direction and the moving speed of the human body, and the set distance between the mobile platform and the human body is ensured; at the same time, according to the image captured by the camera on the Kinect somatosensor, the human skeleton point information is obtained to establish the fall model and detect the fall of the human body.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a three-dimensional vision-based detection system and method for an abnormal posture of a human body. Background technique [0002] Falls have gradually become the fourth cause of high mortality and disability in the elderly after chronic diseases, traffic accidents, and cancer. If the elderly can be found in time when they fall, the elderly can be rescued and treated in time, and the injuries and pain caused by the fall can be reduced. [0003] The method of using the Kinect somatosensory sensor to do fall detection can be roughly divided into two categories: one is to use the RGB image and depth image obtained by Kinect to process, and use the Kinect depth image technology to obtain the foreground image of the human body depth image and establish the foreground Figure three Three-dimensional bounding box, through the real-time calculation of the length, width and heigh...

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): G06K9/00G06F17/18A61B5/11
CPCA61B5/1117G06F17/18G06V20/653G06V40/20
Inventor 王庆祥郭金鑫任晓强
Owner QILU UNIV OF 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