Mark-free cervical vertebra motion detection method

A motion detection, label-free technology, applied in neural learning methods, image data processing, instruments, etc.

Inactive Publication Date: 2021-08-31
HARBIN UNIV OF SCI & TECH
View PDF8 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to solve the problem that the existing marker target recognition method has limitations, and propose a marker-free cervical vertebra motion detection 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
  • Mark-free cervical vertebra motion detection method
  • Mark-free cervical vertebra motion detection method
  • Mark-free cervical vertebra motion detection method

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0058] A marker-free cervical motion detection method in this embodiment, such as figure 1 As shown, the method goes through the following steps:

[0059] Step 1. Obtain continuous image frames containing the neck by collecting videos containing the neck;

[0060] Among them, the camera needs to be calibrated before the step of collecting the video containing the neck;

[0061] Step 2, the method of combining the L-K optical flow method and the maximum inter-class variance image segmentation method to detect the neck region target in the image, specifically:

[0062] First, obtain two consecutive frames of images, and perform grayscale processing on the images to obtain their grayscale images;

[0063] Second, calculate the Lucas-Kanade optical flow algorithm for two consecutive frames of images to obtain the optical flow field;

[0064] Third, image segmentation with maximum inter-class variance is performed in the optical flow field, and the area with continuous optical f...

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 an unmarked cervical vertebra motion detection method, and belongs to the field of image recognition. An existing target recognition method with a marker has limitation. The method comprises the following steps: acquiring continuous image frames containing necks; detecting a neck region target in the image by combining an L-K optical flow method and a maximum between-class variance image segmentation method; the neck edge is detected, and neck contour part information is extracted; taking the center of mass of the extracted neck edge image as a coordinate origin, establishing a coordinate system, connecting the centers of mass of the image in four quadrants with the origin, and calculating a tangent value of an included angle between each connecting line and a horizontal axis to obtain a feature vector; performing neck feature extraction; carrying out neck posture recognition by adopting a BP neural network; extracting sample feature data to calculate training parameters, and training a classifier according to the extracted feature parameters; and then detecting the neck image to be detected, and recognizing a detection result. The method has the advantages of short target recognition time and accurate recognition result.

Description

technical field [0001] The invention relates to a markerless cervical vertebra motion detection method. Background technique [0002] With the acceleration of the pace of society and the popularization of smart phones, long hours of desk work and more and more "head-down people" make cervical spondylosis more and more young and popular. Cervical spondylosis is a dysfunctional syndrome of the cervical spine caused by intervertebral disc herniation and bone hyperplasia. It was originally a common and frequently-occurring disease in the middle-aged and elderly people. However, surveys in recent years have found that more and more people have cervical spondylosis in mild or severe ways, especially office workers who work at desks for a long time and students with heavy academic burdens, the prevalence of cervical spondylosis is generally higher than other crowd. According to relevant occupational surveys, the prevalence of cervical spondylosis in clerical positions, teachers, ...

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): G06T7/215G06T7/246G06T7/66G06T7/80G06K9/62G06N3/08G06T5/00G06T7/11G06T7/13G06T7/136G06T7/155G06T7/194
CPCG06T7/215G06T7/251G06T7/66G06T7/80G06T7/11G06T7/13G06T7/136G06T7/155G06T7/194G06T5/002G06T5/007G06N3/08G06T2207/20081G06T2207/20084G06T2207/20036G06F18/24133
Inventor 刘卓夫陈胜修
Owner HARBIN UNIV OF SCI & 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