Machine learning for human behavior analysis
Nowadays, many fitness bloggers have popped up to upload teaching yoga videos for rookies to exercise. Generally, yoga poses are designed to stretch different parts of human bodies, and if wrong videos are followed, it would be a waste of time and effort. However, the present solution to select the...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis-Master by Coursework |
| Language: | English |
| Published: |
Nanyang Technological University
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/158900 |
| _version_ | 1811681009228316672 |
|---|---|
| author | Chen, Zien |
| author2 | Tan Yap Peng |
| author_facet | Tan Yap Peng Chen, Zien |
| author_sort | Chen, Zien |
| collection | NTU |
| description | Nowadays, many fitness bloggers have popped up to upload teaching yoga videos for rookies to exercise. Generally, yoga poses are designed to stretch different parts of human bodies, and if wrong videos are followed, it would be a waste of time and effort. However, the present solution to select the right videos is by manual recognition, which is time-consuming and requires domain expertise. In addition, new yoga gestures are created constantly, which cannot be simply recognized by pose recognition or detection.
This dissertation aims to design a system to classify yoga exercising videos. It adopts VGG16, short for Visual Geometry Group Network, as its classification model. In this dissertation, one-shot learning is used to find gestures of interest in video testing samples. After that, these gestures are compared with small datasets using an m-way k-shots few-shot learning method. Eventually, it would label each yoga video, classifying its exercising part of body for yoga learners.
In addition, this dissertation provides a supervision function for learners. It allows users to input videos recording their gestures and judge if they do it right. The output score is an evaluation indicator similar to mAP. This part relies on supervised learning method, and this dissertation adopts Faster RCNN as its object detection model, whose accuracy is 90.90%, based on our experiments.
Keywords: yoga, VGG16, classification, one-shot learning, few-shot learning, supervised learning, mAP, accuracy. |
| first_indexed | 2024-10-01T03:34:08Z |
| format | Thesis-Master by Coursework |
| id | ntu-10356/158900 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:34:08Z |
| publishDate | 2022 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1589002023-07-04T17:49:18Z Machine learning for human behavior analysis Chen, Zien Tan Yap Peng School of Electrical and Electronic Engineering EYPTan@ntu.edu.sg Engineering::Electrical and electronic engineering Nowadays, many fitness bloggers have popped up to upload teaching yoga videos for rookies to exercise. Generally, yoga poses are designed to stretch different parts of human bodies, and if wrong videos are followed, it would be a waste of time and effort. However, the present solution to select the right videos is by manual recognition, which is time-consuming and requires domain expertise. In addition, new yoga gestures are created constantly, which cannot be simply recognized by pose recognition or detection. This dissertation aims to design a system to classify yoga exercising videos. It adopts VGG16, short for Visual Geometry Group Network, as its classification model. In this dissertation, one-shot learning is used to find gestures of interest in video testing samples. After that, these gestures are compared with small datasets using an m-way k-shots few-shot learning method. Eventually, it would label each yoga video, classifying its exercising part of body for yoga learners. In addition, this dissertation provides a supervision function for learners. It allows users to input videos recording their gestures and judge if they do it right. The output score is an evaluation indicator similar to mAP. This part relies on supervised learning method, and this dissertation adopts Faster RCNN as its object detection model, whose accuracy is 90.90%, based on our experiments. Keywords: yoga, VGG16, classification, one-shot learning, few-shot learning, supervised learning, mAP, accuracy. Master of Science (Computer Control and Automation) 2022-05-31T08:01:08Z 2022-05-31T08:01:08Z 2022 Thesis-Master by Coursework Chen, Z. (2022). Machine learning for human behavior analysis. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/158900 https://hdl.handle.net/10356/158900 en application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Electrical and electronic engineering Chen, Zien Machine learning for human behavior analysis |
| title | Machine learning for human behavior analysis |
| title_full | Machine learning for human behavior analysis |
| title_fullStr | Machine learning for human behavior analysis |
| title_full_unstemmed | Machine learning for human behavior analysis |
| title_short | Machine learning for human behavior analysis |
| title_sort | machine learning for human behavior analysis |
| topic | Engineering::Electrical and electronic engineering |
| url | https://hdl.handle.net/10356/158900 |
| work_keys_str_mv | AT chenzien machinelearningforhumanbehavioranalysis |