Abstract | ||
---|---|---|
Extraction of visual descriptors is a crucial problem for state-of-the-art visual information analysis. In this paper, we present a knowledge-based approach for detection of visual objects in video sequences, extraction of visual descriptors and matching with pre-defined objects. The proposed approach models objects through their visual descriptors defined in MPEG7. It first extracts moving regions using an efficient active contours technique. It then computes visual descriptions of the moving regions including color, motion and shape features that are invariant to affine transformations. The extracted features axe matched to a-priori knowledge about the objects' descriptions, using appropriately defined matching functions. Results are presented which illustrate the theoretical developments. |
Year | DOI | Venue |
---|---|---|
2003 | 10.1007/978-3-540-25981-7_9 | ADAPTIVE MULTIMEDIA RETRIEVAL |
Keywords | Field | DocType |
a priori knowledge,information analysis,knowledge base,affine transformation,active contour | Affine transformation,Visual Objects,Object detection,Computer vision,Human visual system model,Computer science,Visual descriptors,Invariant (mathematics),Artificial intelligence,Knowledge base,Image sequence | Conference |
Volume | ISSN | Citations |
3094 | 0302-9743 | 3 |
PageRank | References | Authors |
0.43 | 6 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Paraskevi K. Tzouveli | 1 | 34 | 5.15 |
Georgios Andreou | 2 | 3 | 0.43 |
Gabriel Tsechpenakis | 3 | 160 | 14.47 |
Yannis S. Avrithis | 4 | 1240 | 76.86 |
Stefanos Kollias | 5 | 2268 | 229.16 |