Gait Recognition by Combining the Long-Short-Term Attention Network and Personal Physiological Features
Although gait recognition has been greatly improved by efforts from many researchers in recent years, its performance is still unsatisfactory due to the lack of gait information under the real scenariowhere only one or two images may be used for recognition. In this paper, a new gait recognition fra...
| Main Authors: | , , , |
|---|---|
| 格式: | 文件 |
| 语言: | English |
| 出版: |
MDPI AG
2022-11-01
|
| 丛编: | Sensors |
| 主题: | |
| 在线阅读: | https://www.mdpi.com/1424-8220/22/22/8779 |
| _version_ | 1827643691022417920 |
|---|---|
| author | Chunsheng Hua Yingjie Pan Jia Li Zhibo Wang |
| author_facet | Chunsheng Hua Yingjie Pan Jia Li Zhibo Wang |
| author_sort | Chunsheng Hua |
| collection | DOAJ |
| description | Although gait recognition has been greatly improved by efforts from many researchers in recent years, its performance is still unsatisfactory due to the lack of gait information under the real scenariowhere only one or two images may be used for recognition. In this paper, a new gait recognition framework is brought about which can combine the long-short-term attention modules on silhouette images over the whole sequence and the real human physiological information calculated by a monocular image. The contributions of this work include the following: (1) Fusing the global long-term attention (GLTA) and local short-term attention (LSTA) over the whole query sequence to improve the gait recognition accuracy, where both the short-term gait feature (from two or three frames) and long-term feature (from the whole sequence) are extracted; (2) presenting a method to calculate the real personal static and dynamic physiological features through a single monocular image; (3) by efficiently applying the human physiological information, a new physiological feature extraction (PFE) network is proposed to concatenate the physiological information with silhouette for gait recognition. Through the experiments between the CASIA-B and Multi-state Gait datasets, the effectiveness and efficiency of the proposed method are proven. Under three different walking conditions of the CASIA-B dataset, the mean accuracy of rank-1 in our method is up to 89.6%, and in the Multi-state Gait dataset, wearing different clothes, the mean accuracy of rank-1 in our method is 2.4% higher than the other works. |
| first_indexed | 2024-03-09T18:00:45Z |
| format | Article |
| id | doaj.art-2180eec83f69453aab03b0808b12ae3f |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T18:00:45Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-2180eec83f69453aab03b0808b12ae3f2023-11-24T09:55:44ZengMDPI AGSensors1424-82202022-11-012222877910.3390/s22228779Gait Recognition by Combining the Long-Short-Term Attention Network and Personal Physiological FeaturesChunsheng Hua0Yingjie Pan1Jia Li2Zhibo Wang3Institute of Intelligent Robot and Pattern Recognition, College of Information, Liaoning University, No. 66 Chongshan Middle Road, Huanggu District, Shenyang 110036, ChinaCollege of Information, Liaoning University, Shenyang 110036, ChinaDepartment of Endocrinology and Metabolism, The Fourth Affiliated Hospital of China Medical University, Shenyang 110096, ChinaShenyang Contain Electronic Technology Co., Ltd., Shenyang 110167, ChinaAlthough gait recognition has been greatly improved by efforts from many researchers in recent years, its performance is still unsatisfactory due to the lack of gait information under the real scenariowhere only one or two images may be used for recognition. In this paper, a new gait recognition framework is brought about which can combine the long-short-term attention modules on silhouette images over the whole sequence and the real human physiological information calculated by a monocular image. The contributions of this work include the following: (1) Fusing the global long-term attention (GLTA) and local short-term attention (LSTA) over the whole query sequence to improve the gait recognition accuracy, where both the short-term gait feature (from two or three frames) and long-term feature (from the whole sequence) are extracted; (2) presenting a method to calculate the real personal static and dynamic physiological features through a single monocular image; (3) by efficiently applying the human physiological information, a new physiological feature extraction (PFE) network is proposed to concatenate the physiological information with silhouette for gait recognition. Through the experiments between the CASIA-B and Multi-state Gait datasets, the effectiveness and efficiency of the proposed method are proven. Under three different walking conditions of the CASIA-B dataset, the mean accuracy of rank-1 in our method is up to 89.6%, and in the Multi-state Gait dataset, wearing different clothes, the mean accuracy of rank-1 in our method is 2.4% higher than the other works.https://www.mdpi.com/1424-8220/22/22/8779gait recognitionbiometricsfeature extractionfeature fusionimage sequencedeep learning |
| spellingShingle | Chunsheng Hua Yingjie Pan Jia Li Zhibo Wang Gait Recognition by Combining the Long-Short-Term Attention Network and Personal Physiological Features Sensors gait recognition biometrics feature extraction feature fusion image sequence deep learning |
| title | Gait Recognition by Combining the Long-Short-Term Attention Network and Personal Physiological Features |
| title_full | Gait Recognition by Combining the Long-Short-Term Attention Network and Personal Physiological Features |
| title_fullStr | Gait Recognition by Combining the Long-Short-Term Attention Network and Personal Physiological Features |
| title_full_unstemmed | Gait Recognition by Combining the Long-Short-Term Attention Network and Personal Physiological Features |
| title_short | Gait Recognition by Combining the Long-Short-Term Attention Network and Personal Physiological Features |
| title_sort | gait recognition by combining the long short term attention network and personal physiological features |
| topic | gait recognition biometrics feature extraction feature fusion image sequence deep learning |
| url | https://www.mdpi.com/1424-8220/22/22/8779 |
| work_keys_str_mv | AT chunshenghua gaitrecognitionbycombiningthelongshorttermattentionnetworkandpersonalphysiologicalfeatures AT yingjiepan gaitrecognitionbycombiningthelongshorttermattentionnetworkandpersonalphysiologicalfeatures AT jiali gaitrecognitionbycombiningthelongshorttermattentionnetworkandpersonalphysiologicalfeatures AT zhibowang gaitrecognitionbycombiningthelongshorttermattentionnetworkandpersonalphysiologicalfeatures |