Abstract
This paper proposes a computer vision based method that recognizes interactions between human body and object. In two successive frames in a video sequence, our function based contour analysis method checks whether the silhouettes of the human body and object overlap. If they do not overlap, our method judges that the human body and object does not interact. If the two silhouettes overlap, our method checks whether the motion vectors obtained from the areas for the human body and object coincide. If they coincide, our method judges that the human body and object are interacting. Some experimental results show the effectiveness of the proposed method.
| Original language | English |
|---|---|
| Title of host publication | IFIP Advances in Information and Communication Technology |
| Publisher | Springer New York LLC |
| Pages | 173-180 |
| Number of pages | 8 |
| Volume | 112 |
| ISBN (Print) | 9781475751536 |
| DOIs | |
| Publication status | Published - 2003 |
| Event | IFIP 1st International Workshop on Entertainment Computing, IWEC 2002 - Makuhari Duration: 2002 May 14 → 2002 May 17 |
Publication series
| Name | IFIP Advances in Information and Communication Technology |
|---|---|
| Volume | 112 |
| ISSN (Print) | 18684238 |
Other
| Other | IFIP 1st International Workshop on Entertainment Computing, IWEC 2002 |
|---|---|
| City | Makuhari |
| Period | 02/5/14 → 02/5/17 |
Fingerprint
Keywords
- Computer vision
- Motion vector
- Recognition of interactions
- Silhouette analysis
ASJC Scopus subject areas
- Information Systems and Management
Cite this
Computer vision based recognition of interactions between human body and object. / Kobana, Masumi; Ohya, Jun.
IFIP Advances in Information and Communication Technology. Vol. 112 Springer New York LLC, 2003. p. 173-180 (IFIP Advances in Information and Communication Technology; Vol. 112).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Computer vision based recognition of interactions between human body and object
AU - Kobana, Masumi
AU - Ohya, Jun
PY - 2003
Y1 - 2003
N2 - This paper proposes a computer vision based method that recognizes interactions between human body and object. In two successive frames in a video sequence, our function based contour analysis method checks whether the silhouettes of the human body and object overlap. If they do not overlap, our method judges that the human body and object does not interact. If the two silhouettes overlap, our method checks whether the motion vectors obtained from the areas for the human body and object coincide. If they coincide, our method judges that the human body and object are interacting. Some experimental results show the effectiveness of the proposed method.
AB - This paper proposes a computer vision based method that recognizes interactions between human body and object. In two successive frames in a video sequence, our function based contour analysis method checks whether the silhouettes of the human body and object overlap. If they do not overlap, our method judges that the human body and object does not interact. If the two silhouettes overlap, our method checks whether the motion vectors obtained from the areas for the human body and object coincide. If they coincide, our method judges that the human body and object are interacting. Some experimental results show the effectiveness of the proposed method.
KW - Computer vision
KW - Motion vector
KW - Recognition of interactions
KW - Silhouette analysis
UR - http://www.scopus.com/inward/record.url?scp=84904307552&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84904307552&partnerID=8YFLogxK
U2 - 10.1007/978-0-387-35660-0
DO - 10.1007/978-0-387-35660-0
M3 - Conference contribution
SN - 9781475751536
VL - 112
T3 - IFIP Advances in Information and Communication Technology
SP - 173
EP - 180
BT - IFIP Advances in Information and Communication Technology
PB - Springer New York LLC
ER -