Name
Abstract | ||
|---|---|---|
The video segmentation problem can be regarded as a prob- lem of detecting the fundamental video units (shots). Due to different ways of linking two consecutive shots this task turns out to be difficult. In this work, we propose a method to detect both cuts and gradual transitions by image seg- mentation tools instead of using dissimilarity measures or mathematical models. Firstly, the video is transformed into a 2D image, called visual rhythm by sub-sampling. After- wards, we apply image processing tools to detect all ver- tical aligned transitions in this image. The main operator applied here is the morphological multi-scale gradient. We also present some experimental results. |
Year | DOI | Venue |
|---|---|---|
2003 | 10.1109/ICIP.2003.1246858 | ICIP (2) |
Keywords | Field | DocType |
histograms,rhythm,image segmentation,image processing,mathematical model,mathematical morphology,image retrieval,morphology | Computer vision,Histogram,Sub-sampling,Pattern recognition,Computer science,Segmentation,Mathematical morphology,Image processing,Image retrieval,Image segmentation,Artificial intelligence,Mathematical model | Conference |
Citations | PageRank | References |
3 | 0.41 | 4 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Silvio Jamil Ferzoli Guimarães | 1 | 145 | 25.38 |
| Michel Couprie | 2 | 51 | 4.54 |
| Arnaldo De Albuquerque Araújo | 3 | 3 | 0.41 |
| Neucimar Jerônimo Leite | 4 | 418 | 29.45 |