Abstract
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 Internet of things (IoT), human motion attitude features are extracted based on the 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.
Highlights
Human motion posture detection is mainly to describe the information about human motion, grasp the content expressed by human body and further detect human behavior, which is highly practicable [1]
The main contributions of this paper are as follows: (1)This paper fuses and processes the multiple features and forms image maps, providing an effective foundation for the following algorithm calculation; (2)The training classifier based on semi-supervised learning gives full play of data processing and solves the problems of heavy computation burden and long time consuming of unlabeled data; (3)This paper innovatively considers the three restrictions of time domain, space domain and data in the algorithm design, which plays crucial role in the training effect of classifier; (4)Based on a large number of data, various types of human motion postures, this paper designs multiple verification indexes and tests the algorithm with them one by one, improving the credibility of the experimental results
On the basis of the existing research, this algorithm optimizes the design of the classifier, and uses the semi supervised learning method to train the classifier under the three-layer constraints to complete the pose detection of human moving objects, which has high accuracy of feature extraction and feature fusion, and the correct classification rate of feature pose is high, It can provide data support for human motion behavior research and further promote the development of computer vision
Summary
Human motion posture detection is mainly to describe the information about human motion, grasp the content expressed by human body and further detect human behavior, which is highly practicable [1]. Aiming at the problems of the above-mentioned research, this paper designs the human body moving target pose detection algorithm in the Internet of Things environment, introduces semi-supervised learning, calculates a large amount of unlabeled data, and adds the three-layer restriction conditions of time domain, space domain and data, and efficient training The classifier improves the accuracy of algorithm detection.The results show that the proposed algorithm has high accuracy in feature extraction and multi-feature fusion, the correct classification rate is as high as 92.5%, the F value of human motion posture detection is high, the overlap ratio between the algorithm output and the calibration range is as high as 95%, and the average running time is as low as 1.1s, compared with other literature algorithms, the proposed algorithm has the advantage of being more efficient and accurate
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
