Gait Analysis for Classification
This thesis describes a representation of gait appearance for the purpose of person identification and classification. This gait representation is based on simple localized image features such as moments extracted from orthogonal view video silhouettes of human walking motion. A suite of time-integr...
| Main Author: | |
|---|---|
| Language: | en_US |
| Published: |
2004
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/7109 |
| _version_ | 1811094455097229312 |
|---|---|
| author | Lee, Lily |
| author_facet | Lee, Lily |
| author_sort | Lee, Lily |
| collection | MIT |
| description | This thesis describes a representation of gait appearance for the purpose of person identification and classification. This gait representation is based on simple localized image features such as moments extracted from orthogonal view video silhouettes of human walking motion. A suite of time-integration methods, spanning a range of coarseness of time aggregation and modeling of feature distributions, are applied to these image features to create a suite of gait sequence representations. Despite their simplicity, the resulting feature vectors contain enough information to perform well on human identification and gender classification tasks. We demonstrate the accuracy of recognition on gait video sequences collected over different days and times and under varying lighting environments. Each of the integration methods are investigated for their advantages and disadvantages. An improved gait representation is built based on our experiences with the initial set of gait representations. In addition, we show gender classification results using our gait appearance features, the effect of our heuristic feature selection method, and the significance of individual features. |
| first_indexed | 2024-09-23T16:00:20Z |
| id | mit-1721.1/7109 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T16:00:20Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | mit-1721.1/71092019-04-12T08:33:58Z Gait Analysis for Classification Lee, Lily AI gait recognition gender classification This thesis describes a representation of gait appearance for the purpose of person identification and classification. This gait representation is based on simple localized image features such as moments extracted from orthogonal view video silhouettes of human walking motion. A suite of time-integration methods, spanning a range of coarseness of time aggregation and modeling of feature distributions, are applied to these image features to create a suite of gait sequence representations. Despite their simplicity, the resulting feature vectors contain enough information to perform well on human identification and gender classification tasks. We demonstrate the accuracy of recognition on gait video sequences collected over different days and times and under varying lighting environments. Each of the integration methods are investigated for their advantages and disadvantages. An improved gait representation is built based on our experiences with the initial set of gait representations. In addition, we show gender classification results using our gait appearance features, the effect of our heuristic feature selection method, and the significance of individual features. 2004-10-20T20:32:06Z 2004-10-20T20:32:06Z 2003-06-26 AITR-2003-014 http://hdl.handle.net/1721.1/7109 en_US AITR-2003-014 110 p. 4040471 bytes 994319 bytes application/postscript application/pdf application/postscript application/pdf |
| spellingShingle | AI gait recognition gender classification Lee, Lily Gait Analysis for Classification |
| title | Gait Analysis for Classification |
| title_full | Gait Analysis for Classification |
| title_fullStr | Gait Analysis for Classification |
| title_full_unstemmed | Gait Analysis for Classification |
| title_short | Gait Analysis for Classification |
| title_sort | gait analysis for classification |
| topic | AI gait recognition gender classification |
| url | http://hdl.handle.net/1721.1/7109 |
| work_keys_str_mv | AT leelily gaitanalysisforclassification |