Human body sitting posture recognition method based on depth camera Kinect

Abstract

The invention belongs to the related technical field of depth camera recognition, and particularly relates to a human body sitting posture recognition method based on a depth camera Kinect. The methodcomprises the following steps: S1, capturing an image of a to-be-identified object by adopting a Kinect camera, and identifying three-dimensional position coordinates and quaternion position coordinates of a plurality of skeleton joint feature points of the object; S2, calculating the distance between the eyes of the to-be-identified object and the read object, the height difference of the shoulders and the spine angle; then calculating a three-way rotation angle of each section of bone; and S3, comparing the calculation results with respective corresponding preset acceptable ranges, and if the calculation results are all within the preset acceptable ranges, determining that the sitting posture of the to-be-identified object is qualified, otherwise, determining that the sitting posture ofthe to-be-identified object is unqualified. According to the invention, the problem of human body sitting posture recognition is efficiently solved, the accuracy and comfort are high, and the cost islow.

Description

technical field [0001] The invention belongs to the technical field related to depth camera recognition, and more specifically relates to a human body sitting posture recognition method based on a depth camera Kinect. Background technique [0002] With the increasing pressure of academic competition in modern society, the health risks of adolescents and children's growth and development have become more and more obvious. When entering the state of work and study, every part of our spine also enters into a tense load posture simultaneously. In order to carefully observe books and screens, the cervical spine must be in a stiff state for a long time. If you are reading and writing, you will also be in a stiff bowed posture, which is one of the worst postures for the cervical spine. Reading and writing at a desk for a long time and irregular sitting posture are the direct factors that lead to symptoms such as myopia, hunchback, and lateral tilt of the spine in adolescents and c...

AI Technical Summary

Problems solved by technology

The existing mechanical posture detection system has the advantages of high accuracy and high real-time performance, but has the defects of low comfort and high cost; the existing optical posture detection system has the advantages of high comfort and low cost, but has high hardware requirements , the defect of many restrictions on use; the existing RGB image-based sitting posture detection system has the advantage of high efficiency, but there is a defect of lack of depth information

Images