Human Identity and Gender Recognition From Gait Sequences With Arbitrary Walking Directions
We investigate the problem of human identity and gender recognition from gait sequences with arbitrary walking directions. Most current approaches make the unrealistic assumption that persons walk along a fixed direction or a pre-defined path. Given a gait sequence collected from arbitrary walking d...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2016
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/81676 http://hdl.handle.net/10220/40923 |
| _version_ | 1826115271199293440 |
|---|---|
| author | Lu, Jiwen Wang, Gang Moulin, Pierre |
| author2 | School of Electrical and Electronic Engineering |
| author_facet | School of Electrical and Electronic Engineering Lu, Jiwen Wang, Gang Moulin, Pierre |
| author_sort | Lu, Jiwen |
| collection | NTU |
| description | We investigate the problem of human identity and gender recognition from gait sequences with arbitrary walking directions. Most current approaches make the unrealistic assumption that persons walk along a fixed direction or a pre-defined path. Given a gait sequence collected from arbitrary walking directions, we first obtain human silhouettes by background subtraction and cluster them into several clusters. For each cluster, we compute the cluster-based averaged gait image as features. Then, we propose a sparse reconstruction based metric learning method to learn a distance metric to minimize the intra-class sparse reconstruction errors and maximize the inter-class sparse reconstruction errors simultaneously, so that discriminative information can be exploited for recognition. The experimental results show the efficacy of our approach. |
| first_indexed | 2024-10-01T03:52:46Z |
| format | Journal Article |
| id | ntu-10356/81676 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:52:46Z |
| publishDate | 2016 |
| record_format | dspace |
| spelling | ntu-10356/816762020-03-07T13:56:08Z Human Identity and Gender Recognition From Gait Sequences With Arbitrary Walking Directions Lu, Jiwen Wang, Gang Moulin, Pierre School of Electrical and Electronic Engineering Human gait analysis Identity recognition We investigate the problem of human identity and gender recognition from gait sequences with arbitrary walking directions. Most current approaches make the unrealistic assumption that persons walk along a fixed direction or a pre-defined path. Given a gait sequence collected from arbitrary walking directions, we first obtain human silhouettes by background subtraction and cluster them into several clusters. For each cluster, we compute the cluster-based averaged gait image as features. Then, we propose a sparse reconstruction based metric learning method to learn a distance metric to minimize the intra-class sparse reconstruction errors and maximize the inter-class sparse reconstruction errors simultaneously, so that discriminative information can be exploited for recognition. The experimental results show the efficacy of our approach. ASTAR (Agency for Sci., Tech. and Research, S’pore) 2016-07-13T02:22:13Z 2019-12-06T14:35:54Z 2016-07-13T02:22:13Z 2019-12-06T14:35:54Z 2013 Journal Article Lu, J., Wang, G., & Moulin, P. (2014). Human Identity and Gender Recognition From Gait Sequences With Arbitrary Walking Directions. IEEE Transactions on Information Forensics and Security, 9(1), 51-61. 1556-6013 https://hdl.handle.net/10356/81676 http://hdl.handle.net/10220/40923 10.1109/TIFS.2013.2291969 en IEEE Transactions on Information Forensics and Security © 2013 IEEE. |
| spellingShingle | Human gait analysis Identity recognition Lu, Jiwen Wang, Gang Moulin, Pierre Human Identity and Gender Recognition From Gait Sequences With Arbitrary Walking Directions |
| title | Human Identity and Gender Recognition From Gait Sequences With Arbitrary Walking Directions |
| title_full | Human Identity and Gender Recognition From Gait Sequences With Arbitrary Walking Directions |
| title_fullStr | Human Identity and Gender Recognition From Gait Sequences With Arbitrary Walking Directions |
| title_full_unstemmed | Human Identity and Gender Recognition From Gait Sequences With Arbitrary Walking Directions |
| title_short | Human Identity and Gender Recognition From Gait Sequences With Arbitrary Walking Directions |
| title_sort | human identity and gender recognition from gait sequences with arbitrary walking directions |
| topic | Human gait analysis Identity recognition |
| url | https://hdl.handle.net/10356/81676 http://hdl.handle.net/10220/40923 |
| work_keys_str_mv | AT lujiwen humanidentityandgenderrecognitionfromgaitsequenceswitharbitrarywalkingdirections AT wanggang humanidentityandgenderrecognitionfromgaitsequenceswitharbitrarywalkingdirections AT moulinpierre humanidentityandgenderrecognitionfromgaitsequenceswitharbitrarywalkingdirections |