Name
Title | ||
|---|---|---|
Analysis and performance evaluation of optical flow features for dynamic texture recognition |
Abstract | ||
|---|---|---|
We address the problem of dynamic texture (DT) classification using optical flow features. Optical flow based approaches dominate among the currently available DT classification methods. The features used by these approaches often describe local image distortions in terms of such quantities as curl or divergence. Both normal and complete flows have been considered, with normal flow (NF) being used more frequently. However, precise meaning and applicability of normal and complete flow features have never been analysed properly. We provide a principled analysis of local image distortions and their relation to optical flow. Then we present the results of a comprehensive DT classification study that compares the performances of different flow features for a NF algorithm and four different complete flow algorithms. The efficiencies of two flow confidence measures are also studied. |
Year | DOI | Venue |
|---|---|---|
2007 | 10.1016/j.image.2007.05.013 | Sig. Proc.: Image Comm. |
Keywords | Field | DocType |
available dt classification method,different flow feature,dynamic texture recognition,optical flow,flow confidence measure,normal flow,local image distortion,complete flow feature,dynamic texture,complete flow,optical flow feature,image distortions,classification,performance evaluation,different complete flow algorithm | Signal processing,Computer vision,Divergence,Computer science,Flow (psychology),Image quality,Texture recognition,Artificial intelligence,Motion estimation,Curl (mathematics),Optical flow | Journal |
Volume | Issue | ISSN |
22 | 7-8 | Signal Processing: Image Communication |
Citations | PageRank | References |
16 | 0.74 | 20 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Sándor Fazekas | 1 | 242 | 9.74 |
| Chetverikov, D. | 2 | 956 | 99.89 |