File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/ICMSAO.2017.7934895
- Scopus: eid_2-s2.0-85021424133
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: Visual human action classification for control of a passive walker
Title | Visual human action classification for control of a passive walker |
---|---|
Authors | |
Keywords | PCA Walker robot Fall detection Visual classification |
Issue Date | 2017 |
Citation | 2017 7th International Conference on Modeling, Simulation, and Applied Optimization, ICMSAO 2017, 2017, article no. 7934895 How to Cite? |
Abstract | Human action/behavior classification plays an important role for controlling systems having interaction with human users. Safety and dependability of such systems are crucial especially for walking assist systems. In this paper, upper body joint model of a user of a walking assist system is extracted using a depth sensor and a probabilistic model is proposed to detect possible non-walking states that might happen to the user. The 3D model of upper body skeleton, is reduced in dimension by applying Principal Component Analysis (PCA). The principal components are tested to have a normal distribution allowing a multivariate normal distribution fitting for walking data. The model is shown to be capable of recognizing four different falling scenarios and sitting. In these non-walking states, the motion of a passive-type walker called 'RT Walker', is controlled by generating brake force to assure fall prevention and sitting/standing up support. The experimental data is gathered from an experienced physical therapist capable of imitating different walking problems. |
Persistent Identifier | http://hdl.handle.net/10722/302974 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Taghvaei, Sajjad | - |
dc.contributor.author | Hirata, Yasuhisa | - |
dc.contributor.author | Kosuge, Kazuhiro | - |
dc.date.accessioned | 2021-09-07T08:42:57Z | - |
dc.date.available | 2021-09-07T08:42:57Z | - |
dc.date.issued | 2017 | - |
dc.identifier.citation | 2017 7th International Conference on Modeling, Simulation, and Applied Optimization, ICMSAO 2017, 2017, article no. 7934895 | - |
dc.identifier.uri | http://hdl.handle.net/10722/302974 | - |
dc.description.abstract | Human action/behavior classification plays an important role for controlling systems having interaction with human users. Safety and dependability of such systems are crucial especially for walking assist systems. In this paper, upper body joint model of a user of a walking assist system is extracted using a depth sensor and a probabilistic model is proposed to detect possible non-walking states that might happen to the user. The 3D model of upper body skeleton, is reduced in dimension by applying Principal Component Analysis (PCA). The principal components are tested to have a normal distribution allowing a multivariate normal distribution fitting for walking data. The model is shown to be capable of recognizing four different falling scenarios and sitting. In these non-walking states, the motion of a passive-type walker called 'RT Walker', is controlled by generating brake force to assure fall prevention and sitting/standing up support. The experimental data is gathered from an experienced physical therapist capable of imitating different walking problems. | - |
dc.language | eng | - |
dc.relation.ispartof | 2017 7th International Conference on Modeling, Simulation, and Applied Optimization, ICMSAO 2017 | - |
dc.subject | PCA | - |
dc.subject | Walker robot | - |
dc.subject | Fall detection | - |
dc.subject | Visual classification | - |
dc.title | Visual human action classification for control of a passive walker | - |
dc.type | Conference_Paper | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/ICMSAO.2017.7934895 | - |
dc.identifier.scopus | eid_2-s2.0-85021424133 | - |
dc.identifier.spage | article no. 7934895 | - |
dc.identifier.epage | article no. 7934895 | - |