Abstract
The paper proposes a technique for the recognition of the posture of articulated forms within David Marr's computer vision framework. The technique is based on the identification and propagation of kinesiologic constraints at each joint of a model through a multilevel system of filters which determine the acceptability of the derived description of an articulated form locally, regionally and globally.
Original language | English |
---|---|
Title of host publication | Conference A |
Subtitle of host publication | Computer Vision and Applications |
Publisher | Institute of Electrical and Electronics Engineers (IEEE) |
Pages | 542-545 |
Number of pages | 4 |
Volume | 1 |
ISBN (Print) | 081862910X |
DOIs | |
Publication status | Published - 1 Jan 1992 |
Event | 11th IAPR International Conference on Pattern Recognition, IAPR 1992 - The Hague, Netherlands Duration: 30 Aug 1992 → 3 Sep 1992 |
Conference
Conference | 11th IAPR International Conference on Pattern Recognition, IAPR 1992 |
---|---|
Country/Territory | Netherlands |
City | The Hague |
Period | 30/08/92 → 3/09/92 |