Human body action function detection system, detection method and detector

Abstract

The invention belongs to the technical field of human body data identification, and discloses a human body action function detection system, a detection method and a detector. A data acquisition module adopts depth camera equipment to acquire a human body motion video; a skeleton node position acquisition module is used for establishing a simple human skeleton model for analysis and acquiring spatial coordinate data of human skeletons; a data calculation module is used for obtaining spatial data among the articulation points according to the depth positions of the coordinate points in the skeleton data; a posture library matching module is used for matching the spatial data with a posture library template obtained by performing machine learning on a large number of data samples; and a limbmovement recognition module is used for limb recognition. According to the invention, synchronous detection of motion data of multiple parts in functional action detection such as deep squatting by lifting hands, three-dimensional forward bending and lateral bending of a standing person is creatively realized, and quantification of functional action detection data is realized.

Description

technical field [0001] The invention belongs to the technical field of human body data identification, and in particular relates to a human body action function detection system, detection method and detection instrument. Background technique [0002] At present, the existing technologies commonly used in the industry are as follows: the research of the existing technologies has confirmed that there is a certain correlation between the decline and abnormality of motor function and the occurrence and development of sports injuries: [0003] The tension of pectoralis major and pectoralis minor in patients with acromion impingement syndrome and rotator cuff injury is higher than that of healthy people. patients with non-specific low back pain, lumbar disc herniation and other lumbar injuries show the characteristics of multifidus muscle, transverse abdominus muscle, oblique muscle weakness and volume reduction, while cruciate ligament injury of knee joint and anterior knee pain...

AI Technical Summary

Problems solved by technology

It is conceivable that the cost of a motion capture system using multiple cameras at the same time is still very high, and its dependence on special environments is still very strong

Moreover, the above detection methods can only test one part at a time, which takes a long time and has high economic costs, and does not realize the simultaneous test of multi-part motion data, which cannot meet the requirements of body posture and movement pattern detection in large-scale screening physical examinations. Simple and fast demand

[0006] To sum up, the problems existing in the existing technology are: (1) The existing marker-type human behavior detection technology can only be used in a special environment, and the human body needs to wear special equipment, which is cumbersome and expensive

[0007] (2) The cost of the existing non-marking point human behavior detection technology is also very high, and the dependence on the special environment is still very strong; and the above detection methods can only test one part at a time, which takes a long time and has high economic costs, and Synchronous testing of multi-part motion data has not been realized, which cannot meet the simple and fast requirements for body posture and movement pattern detection in large-scale screening physical examinations

[0008] (3) However, there is currently no means and method for quantitative and rapid detection of functional movement examination to quickly screen subjects for abnormal motor function

[0010] Many companies in the field of static detection in the industry have already achieved corresponding detection products, but there are no products for dynamic detection.

Images