Standing long jump test method based on optimized OpenPose model

Abstract

The invention relates to a standing long jump test method based on an optimized OpenPose model, and the method comprises the steps: obtaining an image through a camera with limited parameters, and then carrying out the preprocessing of the image; and inputting the preprocessed image into a pre-trained model for prediction, and if a serious error occurs in human body posture recognition, interrupting the detection process. Detection of the standing long jump process is divided into four stages, one standing long jump is completed only when the detection of each stage reaches a certain threshold value, and measurement is not performed when the detection does not reach the standard. And when a landing stage is reached, the measurement module calculates the final effective standing long jump score of the tested student to the score of the tested student. The camera is limited, so that the effect of the invention is guaranteed. According to the method, the thought of local evaluation is applied, and processing information is reduced under the condition that the recognition accuracy is not reduced. The number of convolutional layers is reduced, and the prediction time is shortened. And various substandard postures can be identified.

Description

technical field [0001] The invention relates to the field of image processing technology, in particular to a standing long jump test method based on an optimized OpenPose model. Background technique [0002] As an important reference standard and project for measuring physical fitness, standing long jump has been designated as the national men's body side project. At present, there are three main types of standing long jump test methods, namely measurement board measurement, ultrasonic-based standing long jump test and machine vision-based standing long jump test. The first two use sensors to count, with simple structure, easy to be interfered by the outside world, high misjudgment rate, and not very practical. In the analysis depth image counting device, Kincet is mainly used to obtain depth images, which requires the use of proprietary equipment, the algorithm is complex, the price is high, and the computer performance requirements are high, so it is difficult to meet the...

AI Technical Summary

Problems solved by technology

The first two use sensors to count, the structure is simple, easy to be disturbed 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 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