Abstract
Efforts to understand human motion have been increasing in number and complexity, and will most likely prove to be a key component in human-computer interfaces. One key feature of motion in general, and human motion in particular, is its dynamic nature. The present work seeks to model human motions in a manner amenable to leaning and recognition. Toward this end, hidden Markov models (HMMs) are employed to model semantically meaningful human movements. The data used for modeling the human motions is an approximate pose derived from a sequence of camera images. An HMM is learned for each motion class and employed as a maximum likelihood recognizer. Experiments show promising results for a set of six sport actions.
| Original language | English |
|---|---|
| Title of host publication | Robot and Human Communication - Proceedings of the IEEE International Workshop |
| Pages | 129-134 |
| Number of pages | 6 |
| Publication status | Published - 1995 |
| Externally published | Yes |
| Event | Proceedings of the 1995 4th IEEE International Workshop on Robot and Human Communication, RO-MAN - Tokyo, Jpn Duration: 1995 Jul 5 → 1995 Jul 7 |
Other
| Other | Proceedings of the 1995 4th IEEE International Workshop on Robot and Human Communication, RO-MAN |
|---|---|
| City | Tokyo, Jpn |
| Period | 95/7/5 → 95/7/7 |
Fingerprint
ASJC Scopus subject areas
- Hardware and Architecture
- Software
Cite this
Applications of HMM modeling to recognizing human gestures in image sequences for a man-machine interface. / Stoll, Perry A.; Ohya, Jun.
Robot and Human Communication - Proceedings of the IEEE International Workshop. 1995. p. 129-134.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Applications of HMM modeling to recognizing human gestures in image sequences for a man-machine interface
AU - Stoll, Perry A.
AU - Ohya, Jun
PY - 1995
Y1 - 1995
N2 - Efforts to understand human motion have been increasing in number and complexity, and will most likely prove to be a key component in human-computer interfaces. One key feature of motion in general, and human motion in particular, is its dynamic nature. The present work seeks to model human motions in a manner amenable to leaning and recognition. Toward this end, hidden Markov models (HMMs) are employed to model semantically meaningful human movements. The data used for modeling the human motions is an approximate pose derived from a sequence of camera images. An HMM is learned for each motion class and employed as a maximum likelihood recognizer. Experiments show promising results for a set of six sport actions.
AB - Efforts to understand human motion have been increasing in number and complexity, and will most likely prove to be a key component in human-computer interfaces. One key feature of motion in general, and human motion in particular, is its dynamic nature. The present work seeks to model human motions in a manner amenable to leaning and recognition. Toward this end, hidden Markov models (HMMs) are employed to model semantically meaningful human movements. The data used for modeling the human motions is an approximate pose derived from a sequence of camera images. An HMM is learned for each motion class and employed as a maximum likelihood recognizer. Experiments show promising results for a set of six sport actions.
UR - http://www.scopus.com/inward/record.url?scp=0029524495&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0029524495&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:0029524495
SP - 129
EP - 134
BT - Robot and Human Communication - Proceedings of the IEEE International Workshop
ER -