Abstract | ||
---|---|---|
A problem of interest in digital video edition is the elimination of moving objects from one video and the introduction of pieces of other videos in their places. A fundamental problem to build computational tools for this purpose is the segmentation of moving objects. This paper approaches this problem by a new technique, based on Beucher's paradigm, with markers detected by morphological operators designed by computational learning (or, equivalently, statistical optimization.) The objects in the first frames of the video are marked manually and used to train the markers detector. Then, the operator designed is used to mark the objects in the other frames and Beucher's paradigm is applied to all frames marked by the detector. Some synthetical and real world examples illustrate the application of the technique proposed. Complex situations as occlusion are examined. |
Year | DOI | Venue |
---|---|---|
1999 | 10.1109/SIBGRA.1999.805736 | SIBGRAPI |
Keywords | Field | DocType |
mathematical morphology,motion estimation,computer vision,image segmentation | Digital video,Computer vision,Computer graphics (images),Computer science,Mathematical morphology,Segmentation,Image segmentation,Operator (computer programming),Artificial intelligence,Motion estimation,Detector | Conference |
ISBN | Citations | PageRank |
0-7695-0481-7 | 4 | 0.65 |
References | Authors | |
0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Roberto Hirata Jr. | 1 | 13 | 7.80 |
Junior Barrera | 2 | 237 | 43.96 |
Franklin César Flores | 3 | 45 | 8.15 |
Roberto de Alencar Lotufo | 4 | 572 | 53.61 |