TY  - JOUR
AB  - In this paper we propose an architecture of an image understanding system for a situated
arti cial communicator realizing human-machine interaction. Starting with sensor input the
processing is initially carried out in separate pathways using di erent schemes of image seg-
mentation. Subsequently, a hybrid technique for 2D-object recognition is employed. The nal
model based 3D-reconstruction yields a 3D-scene representation. Intermediate results are linked
over time in memory moduls to enhance e ciency of processing on image sequences. Results
of the individual moduls will be presented and discussed.
DA  - 1999
LA  - eng
IS  - 4
M2  - 542
PY  - 1999
SN  - 1054-6618
SP  - 542-548
T2  - Pattern Recognition and Image Analysis
TI  - Towards an Image Understanding Architecture for a Situated Artificial Communicator
UR  - https://nbn-resolving.org/urn:nbn:de:0070-pub-27149139
Y2  - 2024-11-22T05:04:58
ER  -