Pull-up test counting method and system based on Quick-OpenPose model

Abstract

The invention discloses a pull-up test counting method and system based on a Quick-OpenPose model. The method comprises the following steps: entering a student number authentication module; a pull-upcamera on the tester continuously shoots a test image of a tester to obtain an image, a human body posture recognition module is used for recognizing the posture, and when it is found for the first time that the distance between a wrist detection point and a horizontal bar in a certain frame of image is within a threshold range, the frame is set as a starting frame; when it is recognized that themoving posture meets the threshold value requirement, cumulative counting is conducted; if the human body posture is recognized to have a serious error, the error prevention module interrupts the detection process, returns to wait for restarting and performs voice broadcast; if it is recognized that the moving posture does not reach the standard, voice broadcast is conducted as well, recognition is not interrupted, and the action is not counted; when detecting that the wrist leaves the horizontal bar, ending the test; and the counting module calculates the final effective pull-up test countingscore of the tested person and carries out voice broadcast. The method is high in detection speed and high in efficiency, the parameter sharing rate is increased, and the model redundancy is reduced.

Description

technical field [0001] The invention belongs to the technical field of machine vision and image processing, in particular to a pull-up test counting method and system based on the Quick-OpenPose model. Background technique [0002] As an important reference standard and item to measure physical fitness, pull-up has been designated as a national high school entrance examination sports test item. At present, existing pull-up counting methods include: manual counting, infrared probe sensor counting, ultrasonic sensor counting, and analysis depth image counting. In the process of manual counting, it is time-consuming and labor-intensive, and it is easy to make mistakes. Using the sensor to count, the structure is simple, it is easy to be interfered by the outside world, the misjudgment rate is high, and the practicability is not very strong. In the analysis depth image counting device, Kincet is mainly used to obtain the depth image, which requires the use of proprietary equip...

AI Technical Summary

Problems solved by technology

In the process of manual counting, time-consuming and labor-intensive, error-prone

Using sensors to count, the structure is simple, easy to be disturbed by the outside world, the false positive rate is high, and the practicability is not very strong

In the analysis depth image counting device, Kincet is mainly used to obtain the depth image, which requires the use of proprietary equipment, the algorithm is relatively complex, the price is high, and the computer performance requirements are high, and it is difficult to meet the real-time requirements

Images