Sitting posture detection method based on sitting posture depth image

Abstract

A sitting posture detection method based on a sitting posture depth image includes the steps of (1) obtaining a sitting posture depth image of a human body through a depth sensor and a depth distance value of all pixel pints in the sitting posture depth image; (2) segmenting the sitting posture depth image, and removing interference of an external background and the human body, so as to obtain a sitting posture segmented image; (3)determining key points through the sitting posture segmented image which include a head vertex, a head central point, a left shoulder point, a right shoulder point, a shoulder central point and a body central point; and (4) judging a sitting posture according to the key points. The sitting posture detection method based on the sitting posture depth image is high in sitting posture detection accuracy, sitting posture detection can be performed through sitting posture detection software only by connection of a mobile phone with the depth sensor, and the method is convenient to use and wide in range of application, and has very good portability and flexibility.

Description

technical field [0001] The invention relates to a sitting posture detection method, in particular to a sitting posture detection method based on a sitting posture depth image. Background technique [0002] Nowadays, due to the needs of study and work, people spend more and more time sitting and standing every day. According to statistics, people now spend more than 8 hours sitting and standing on average every day. In the case of sitting and standing for a long time, because it is difficult for people to maintain a good sitting and standing posture all the time, it is easy to have bad sitting postures such as being too close to the desk, leaning the body, and tilting the head. Over time, it is easy to suffer from myopia, strabismus, lumbar spine diseases, cervical spine diseases, etc., which seriously affect people's health. Therefore, in order to encourage people to correct bad sitting posture, develop good sitting posture habits, and reduce the probability of suffering fr...

AI Technical Summary

Problems solved by technology

However, there are still some defects in these methods at present, such as color images are easily affected by light and complex backgrounds; the method of sitting posture detection through binocular cameras, the accuracy of depth images is not high, which will cause errors in sitting posture detection; When the fixed camera in the desk is used for image acquisition, the equipment is inconvenient to move, the scope of use is too limited, and the requirements for the equipment are high

[0004] In general, the existing sitting posture detection methods or systems have the disadvantages of complicated installation, inconvenient portability, troublesome use and low accuracy of sitting posture detection

Images