Fitness action standard evaluating method and device

Abstract

The invention discloses a fitness action standard evaluating method and device. According to the invention, an action recognition time interval for each fitness action in a fitness template video is set, and the action recognition time interval of each fitness action is readjusted, so that the recognition end time of the previous action recognition time interval in two adjacent action recognitiontime intervals is not behind the recognition start time of the next action recognition time interval; the time score of the fitness action is calculated according to the action recognition time interval of each fitness action and the action end time of the fitness action; the time score can be used as the standard score alone to evaluate whether the fitness action is standard, and can be used as the standard score in combination with the strength score acquired through action recognition to evaluate whether the fitness action is standard; and therefore, the completion time of the fitness action can be accurately evaluated.

Description

technical field [0001] The invention relates to the technical field of sports applications, in particular to a method and device for evaluating the standard degree of fitness movements. Background technique [0002] Along with improving day by day of people's living standard, people also pay more and more attention to physical exercise. At the same time, people's lives are full of various fitness software to help people exercise. Current fitness software adopts the method of playing fitness template videos, and users learn and imitate while watching the videos to help users keep fit. However, the existing fitness software cannot monitor whether the user's fitness movements are standard, and cannot perform somatosensory detection. Although there are currently some somatosensory detection applications, such as somatosensory games, which can detect the user's actions, they can only detect whether the user has done a simple action (such as waving), and cannot detect the time s...

AI Technical Summary

Problems solved by technology

However, the existing fitness software cannot monitor whether the user's fitness movements are standard, and cannot perform somatosensory detection

Although there are currently some somatosensory detection applications, such as somatosensory games, which can detect the user's actions, they can only detect whether the user has done a simple action (such as waving), and cannot detect the time spent by the user's fitness actions. It is difficult to detect complex movements such as fitness, and cannot guide users to achieve a good training effect

Images