Human Skeleton Data Augmentation for Person Identification over Deep Neural Network
With the advancement in pose estimation techniques, skeleton-based person identification has recently received considerable attention in many applications. In this study, a skeleton-based person identification method using a deep neural network (DNN) is investigated. In this method, anthropometric f...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-07-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/14/4849 |
| _version_ | 1797562403814113280 |
|---|---|
| author | Beom Kwon Sanghoon Lee |
| author_facet | Beom Kwon Sanghoon Lee |
| author_sort | Beom Kwon |
| collection | DOAJ |
| description | With the advancement in pose estimation techniques, skeleton-based person identification has recently received considerable attention in many applications. In this study, a skeleton-based person identification method using a deep neural network (DNN) is investigated. In this method, anthropometric features extracted from the human skeleton sequence are used as the input to the DNN. However, training the DNN with insufficient training datasets makes the network unstable and may lead to overfitting during the training phase, causing significant performance degradation in the testing phase. To cope with a shortage in the dataset, we investigate novel data augmentation for skeleton-based person identification by utilizing the bilateral symmetry of the human body. To achieve this, augmented vectors are generated by sharing the anthropometric features extracted from one side of the human body with the other and vice versa. Thereby, the total number of anthropometric feature vectors is increased by 256 times, which enables the DNN to be trained while avoiding overfitting. The simulation results demonstrate that the average accuracy of person identification is remarkably improved up to 100% based on the augmentation on public datasets. |
| first_indexed | 2024-03-10T18:28:43Z |
| format | Article |
| id | doaj.art-7f27e72c2969491ea19c988a159897ff |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T18:28:43Z |
| publishDate | 2020-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-7f27e72c2969491ea19c988a159897ff2023-11-20T06:48:44ZengMDPI AGApplied Sciences2076-34172020-07-011014484910.3390/app10144849Human Skeleton Data Augmentation for Person Identification over Deep Neural NetworkBeom Kwon0Sanghoon Lee1Division of Network Business, Samsung Electronics Company, Ltd., Suwon 16677, KoreaDepartment of Electrical and Electronic Engineering, Yonsei University, Seoul 03722, KoreaWith the advancement in pose estimation techniques, skeleton-based person identification has recently received considerable attention in many applications. In this study, a skeleton-based person identification method using a deep neural network (DNN) is investigated. In this method, anthropometric features extracted from the human skeleton sequence are used as the input to the DNN. However, training the DNN with insufficient training datasets makes the network unstable and may lead to overfitting during the training phase, causing significant performance degradation in the testing phase. To cope with a shortage in the dataset, we investigate novel data augmentation for skeleton-based person identification by utilizing the bilateral symmetry of the human body. To achieve this, augmented vectors are generated by sharing the anthropometric features extracted from one side of the human body with the other and vice versa. Thereby, the total number of anthropometric feature vectors is increased by 256 times, which enables the DNN to be trained while avoiding overfitting. The simulation results demonstrate that the average accuracy of person identification is remarkably improved up to 100% based on the augmentation on public datasets.https://www.mdpi.com/2076-3417/10/14/4849anthropometric featuredata augmentationdeep learningdeep neural networkhuman skeletonperson identification |
| spellingShingle | Beom Kwon Sanghoon Lee Human Skeleton Data Augmentation for Person Identification over Deep Neural Network Applied Sciences anthropometric feature data augmentation deep learning deep neural network human skeleton person identification |
| title | Human Skeleton Data Augmentation for Person Identification over Deep Neural Network |
| title_full | Human Skeleton Data Augmentation for Person Identification over Deep Neural Network |
| title_fullStr | Human Skeleton Data Augmentation for Person Identification over Deep Neural Network |
| title_full_unstemmed | Human Skeleton Data Augmentation for Person Identification over Deep Neural Network |
| title_short | Human Skeleton Data Augmentation for Person Identification over Deep Neural Network |
| title_sort | human skeleton data augmentation for person identification over deep neural network |
| topic | anthropometric feature data augmentation deep learning deep neural network human skeleton person identification |
| url | https://www.mdpi.com/2076-3417/10/14/4849 |
| work_keys_str_mv | AT beomkwon humanskeletondataaugmentationforpersonidentificationoverdeepneuralnetwork AT sanghoonlee humanskeletondataaugmentationforpersonidentificationoverdeepneuralnetwork |