Human Motion Target Posture Detection Algorithm using Semi-supervised Learning in Internet of Things

Lei Chen, Shangbin Li
2021 IEEE Access  
In order to address the problem that the traditional human motion attitude detection process is easy to ignore the data calibration, which leads to the problems of long running time, low accuracy and poor detection effect, a human motion target attitude detection algorithm based on semi-supervised learning in the Internet of things environment is proposed. Firstly, human motion target images are collected using the IoT (Internet of things), human motion attitude features are extracted based on
more » ... he eight-star model, and multi-features are fused to form image blocks of 17-dimensional feature vectors. Then, random fern classifiers are optimized and semi-supervised learning is used to calculate a large number of uncalibrated data in time domain, spatial domain and data. The classifier is trained to complete image block classification. Finally, the classifier parameters are updated iteratively to complete the attitude detection of human motion target. The results show that the proposed algorithm has high accuracy in human motion attitude extraction and multi-feature fusion, and has a high correct classification rate for different feature poses, as high as 92.5%. The average F value of human motion attitude detection is 0.95, the overlap ratio is high and the time is short. The overall performance is good. INDEX TERMS Semi-supervised learning, human motion posture, extraction, multi-feature fusion, classifier, detection I. INTRODUCTION Human motion posture detection is mainly to describe the information about human motion, grasp the content expressed by human body and then further detect human behavior, which is highly practicable [1]. With the improvement of the people's quality of life, simple video monitoring can no longer meet the needs [2-3]. So it is of great significance to find an efficient way to detect the human motion posture for response to various emergencies, especially for public places. Human motion posture detection is also widely used in sports, medical and other fields, and is the focus of the current research on artificial intelligence [4-5]. The Internet of Things is a combination of radio frequency identification technology, sensor technology and artificial intelligence technology. The network environment created by this technology can well perceive the real world. In the Internet of Things environment, the human body motion target posture is detected, the human target motion process is monitored in real time through the information network, and the motion posture information is shared, which can effectively obtain human body motion information, thereby realizing intelligent motion posture detection. However, due to the variety of environment types, there is a huge amount of information in human motion [6] , and together with the interference from other external factors, it is difficult to precisely detect the human motion target posture in practice. Therefore, it is a point research issue to find an effective algorithm of human posture detection in the computer filed. This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/ This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication.
doi:10.1109/access.2021.3091430 fatcat:wkbkxrjhubd6ljejnwp5jfb5z4