Fitness exercise recognition method based on wearable sensor

Abstract

The invention discloses a fitness exercise recognition method based on a wearable sensor. The fitness exercise recognition method specifically comprises the following steps of step 1, acquiring an inertial sensing signal in the fitness exercise process and preprocessing the same; step 2, performing window segmentation on the signal preprocessed in the step 1; step 3, performing feature extractionon the signal segmented in the step 2; step 4, performing normalization processing on the feature data extracted in the step 3; step 5, carrying out feature dimension reduction on the features processed in the step 4; and step 6, recognizing the features processed in the step 5. The exercise information is extracted by utilizing the acceleration and angular velocity signals acquired by the exercise sensor integrated in the wearable equipment in the process of the fitness exercise of the person, so that the recognition of the fitness exercise is realized.

Description

technical field [0001] The invention belongs to the field of computer technology and application technology, and relates to a body-building exercise recognition method based on a wearable sensor. Background technique [0002] There are two main types of traditional human behavior recognition technologies. One is to obtain video and image data of human behavior through video recording and photography, the other is to obtain data based on environmental sensors, and the third is to obtain data through wearable devices. The human behavior recognition method based on video equipment obtains the image information of human movement and analyzes its image sequence to realize human behavior recognition. However, in actual application, video acquisition equipment is required to obtain target video information, and such equipment is usually large in size, fixed in position, high in power consumption, heavy in calculation, and has poor anti-interference ability, which may cause unpredic...

AI Technical Summary

Problems solved by technology

[0009] Chinese patent (title: fitness exercise recognition method and system based on multi-source data fusion, application number: CN201710525603.7) discloses a fitness exercise recognition method and system based on multi-source data fusion, which requires Fusion of data based on environmental sensors (such as fitness equipment) can improve the accuracy of recognition to a certain extent, but the more movements require more equipment that can collect data, the cost is expensive, and the applicability is not good enough

[0010] Chinese patent (name: a user behavior recognition method based on a smart mobile device sensor, application number: CN201910347816.4) discloses a user behavior recognition method based on a smart mobile device sensor, the method obtains acceleration and angular velocity data , image it and process it according to the image processing method, but its recognition action is relatively simple, which is not enough to support the current practical needs

Images