Emotion recognition using Kinect motion capture data of human gaits
Automatic emotion recognition is of great value in many applications, however, to fully display the application value of emotion recognition, more portable, non-intrusive, inexpensive technologies need to be developed. Human gaits could reflect the walker’s emotional state, and could be an informati...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2016-09-01
|
| Series: | PeerJ |
| Subjects: | |
| Online Access: | https://peerj.com/articles/2364.pdf |
| _version_ | 1827606534396313600 |
|---|---|
| author | Shun Li Liqing Cui Changye Zhu Baobin Li Nan Zhao Tingshao Zhu |
| author_facet | Shun Li Liqing Cui Changye Zhu Baobin Li Nan Zhao Tingshao Zhu |
| author_sort | Shun Li |
| collection | DOAJ |
| description | Automatic emotion recognition is of great value in many applications, however, to fully display the application value of emotion recognition, more portable, non-intrusive, inexpensive technologies need to be developed. Human gaits could reflect the walker’s emotional state, and could be an information source for emotion recognition. This paper proposed a novel method to recognize emotional state through human gaits by using Microsoft Kinect, a low-cost, portable, camera-based sensor. Fifty-nine participants’ gaits under neutral state, induced anger and induced happiness were recorded by two Kinect cameras, and the original data were processed through joint selection, coordinate system transformation, sliding window gauss filtering, differential operation, and data segmentation. Features of gait patterns were extracted from 3-dimentional coordinates of 14 main body joints by Fourier transformation and Principal Component Analysis (PCA). The classifiers NaiveBayes, RandomForests, LibSVM and SMO (Sequential Minimal Optimization) were trained and evaluated, and the accuracy of recognizing anger and happiness from neutral state achieved 80.5% and 75.4%. Although the results of distinguishing angry and happiness states were not ideal in current study, it showed the feasibility of automatically recognizing emotional states from gaits, with the characteristics meeting the application requirements. |
| first_indexed | 2024-03-09T06:38:38Z |
| format | Article |
| id | doaj.art-d1b7be43c4cd43cc9edfa9c3792f4bd3 |
| institution | Directory Open Access Journal |
| issn | 2167-8359 |
| language | English |
| last_indexed | 2024-03-09T06:38:38Z |
| publishDate | 2016-09-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ |
| spelling | doaj.art-d1b7be43c4cd43cc9edfa9c3792f4bd32023-12-03T10:54:56ZengPeerJ Inc.PeerJ2167-83592016-09-014e236410.7717/peerj.2364Emotion recognition using Kinect motion capture data of human gaitsShun Li0Liqing Cui1Changye Zhu2Baobin Li3Nan Zhao4Tingshao Zhu5Institute of Psychology, Chinese Academy of Sciences, Beijing, ChinaInstitute of Psychology, Chinese Academy of Sciences, Beijing, ChinaSchool of Computer and Control, University of Chinese Academy of Sciences, Beijing, ChinaSchool of Computer and Control, University of Chinese Academy of Sciences, Beijing, ChinaInstitute of Psychology, Chinese Academy of Sciences, Beijing, ChinaInstitute of Psychology, Chinese Academy of Sciences, Beijing, ChinaAutomatic emotion recognition is of great value in many applications, however, to fully display the application value of emotion recognition, more portable, non-intrusive, inexpensive technologies need to be developed. Human gaits could reflect the walker’s emotional state, and could be an information source for emotion recognition. This paper proposed a novel method to recognize emotional state through human gaits by using Microsoft Kinect, a low-cost, portable, camera-based sensor. Fifty-nine participants’ gaits under neutral state, induced anger and induced happiness were recorded by two Kinect cameras, and the original data were processed through joint selection, coordinate system transformation, sliding window gauss filtering, differential operation, and data segmentation. Features of gait patterns were extracted from 3-dimentional coordinates of 14 main body joints by Fourier transformation and Principal Component Analysis (PCA). The classifiers NaiveBayes, RandomForests, LibSVM and SMO (Sequential Minimal Optimization) were trained and evaluated, and the accuracy of recognizing anger and happiness from neutral state achieved 80.5% and 75.4%. Although the results of distinguishing angry and happiness states were not ideal in current study, it showed the feasibility of automatically recognizing emotional states from gaits, with the characteristics meeting the application requirements.https://peerj.com/articles/2364.pdfEmotion recognitionAffective computingGaitMachine learningKinect |
| spellingShingle | Shun Li Liqing Cui Changye Zhu Baobin Li Nan Zhao Tingshao Zhu Emotion recognition using Kinect motion capture data of human gaits PeerJ Emotion recognition Affective computing Gait Machine learning Kinect |
| title | Emotion recognition using Kinect motion capture data of human gaits |
| title_full | Emotion recognition using Kinect motion capture data of human gaits |
| title_fullStr | Emotion recognition using Kinect motion capture data of human gaits |
| title_full_unstemmed | Emotion recognition using Kinect motion capture data of human gaits |
| title_short | Emotion recognition using Kinect motion capture data of human gaits |
| title_sort | emotion recognition using kinect motion capture data of human gaits |
| topic | Emotion recognition Affective computing Gait Machine learning Kinect |
| url | https://peerj.com/articles/2364.pdf |
| work_keys_str_mv | AT shunli emotionrecognitionusingkinectmotioncapturedataofhumangaits AT liqingcui emotionrecognitionusingkinectmotioncapturedataofhumangaits AT changyezhu emotionrecognitionusingkinectmotioncapturedataofhumangaits AT baobinli emotionrecognitionusingkinectmotioncapturedataofhumangaits AT nanzhao emotionrecognitionusingkinectmotioncapturedataofhumangaits AT tingshaozhu emotionrecognitionusingkinectmotioncapturedataofhumangaits |