Name
Title | ||
|---|---|---|
Real-time compressed-domain spatiotemporal segmentation and ontologies for video indexing and retrieval |
Abstract | ||
|---|---|---|
In this paper, a novel algorithm is presented for the real-time, compressed-domain, unsupervised segmentation of image sequences and is applied to video indexing and retrieval. The segmentation algorithm uses motion and color information directly extracted from the MPEG-2 compressed stream. An iterative rejection scheme based on the bilinear motion model is used to effect foreground/background segmentation. Following that, meaningful foreground spatiotemporal objects are formed by initially examining the temporal consistency of the output of iterative rejection, clustering the resulting foreground macroblocks to connected regions and finally performing region tracking. Background segmentation to spatiotemporal objects is additionally performed. MPEG-7 compliant low-level descriptors describing the color, shape, position, and motion of the resulting spatiotemporal objects are extracted and are automatically mapped to appropriate intermediate-level descriptors forming a simple vocabulary termed object ontology. This, combined with a relevance feedback mechanism, allows the qualitative definition of the high-level concepts the user queries for (semantic objects, each represented by a keyword) and the retrieval of relevant video segments. Desired spatial and temporal relationships between the objects in multiple-keyword queries can also be expressed, using the shot ontology. Experimental results of the application of the segmentation algorithm to known sequences demonstrate the efficiency of the proposed segmentation approach. Sample queries reveal the potential of employing this segmentation algorithm as part of an object-based video indexing and retrieval scheme. |
Year | DOI | Venue |
|---|---|---|
2004 | 10.1109/TCSVT.2004.826768 | IEEE Trans. Circuits Syst. Video Techn. |
Keywords | Field | DocType |
relevant video segment,segmentation algorithm,object-based video indexing,unsupervised segmentation,proposed segmentation approach,effect foreground,real-time compressed-domain spatiotemporal segmentation,bilinear motion model,meaningful foreground spatiotemporal object,novel algorithm,background segmentation,indexing terms,iterative methods,foreground background,real time systems,image segmentation,support vector machines,real time,data compression,support vector machine,image retrieval,ontologies,data mining,indexing,video compression | Object detection,Computer vision,Relevance feedback,Scale-space segmentation,Pattern recognition,Segmentation,Computer science,Image retrieval,Segmentation-based object categorization,Search engine indexing,Image segmentation,Artificial intelligence | Journal |
Volume | Issue | ISSN |
14 | 5 | 1051-8215 |
Citations | PageRank | References |
76 | 3.91 | 39 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| V. Mezaris | 1 | 293 | 16.26 |
| I. Kompatsiaris | 2 | 282 | 15.61 |
| nikolaos v boulgouris | 3 | 416 | 23.69 |
| michael g strintzis | 4 | 1095 | 79.71 |