Title :
Video sequence modeling by dynamic Bayesian networks: a systematic approach from coarse-to-fine grains
Author :
Luo, Ying ; Hwang, Jenq-Neng
Author_Institution :
Dept. of Electr. Eng., Washington Univ., Seattle, WA, USA
Abstract :
A dynamic Bayesian network (DBN) based framework to model video sequences is proposed. The video sequences of interest include single-shot video sequences containing only one event and multishot video sequences containing various events. By taking advantage of the temporal continuity of video sequences and assuming Markovian property between successive image frames, we propose DBNs as the tool to map low-level features to high-level concepts. The feasibility of DBN modeling is tested on single-and multishot video sequences. Specifically, a coarse-grained video interpretation framework based on one kind of DBN, the hierarchical hidden Markov model (HHMM), is proposed for multishot video sequences. For single-shot video sequences, we present a fine-grained object based interpretation and classification system based on another version of DBNs. The preliminary simulations show great promise on the efficiency and flexibility of using DBNs for video sequence modeling.
Keywords :
belief networks; hidden Markov models; image classification; image sequences; video signal processing; coarse-grained video interpretation framework; coarse-to-fine grain; dynamic Bayesian network; fine-grained object based classification system; fine-grained object based interpretation; hierarchical HMM; hierarchical hidden Markov model; image frame; low-level feature mapping; multishot video sequence; single-shot video sequence modeling; Bandwidth; Bayesian methods; Content based retrieval; Data mining; Hidden Markov models; Information processing; Information retrieval; Layout; Testing; Video sequences;
Conference_Titel :
Image Processing, 2003. ICIP 2003. Proceedings. 2003 International Conference on
Print_ISBN :
0-7803-7750-8
DOI :
10.1109/ICIP.2003.1246755
