Name
Abstract | ||
|---|---|---|
Motion estimation is a key problem in the analysis of image sequences. From a sequence of images we can only estimate an approximation of the image motion field called optical flow. We propose to improve optical flow estimation by including information from images of textural features. We compute the optical flow from intensity and textural images from first-order derivatives, then combine estimates using the spatial gradient as confidence measure. Experimental results with images for which the ground-truth optical flow is known show clearly that the estimate improves by including estimates from textural images. Experiments with several underwater images also show a qualitative improvement. |
Year | DOI | Venue |
|---|---|---|
2004 | 10.1016/j.patrec.2003.11.007 | Pattern Recognition Letters |
Keywords | Field | DocType |
image motion field,image sequence,texture,motion estimation,optical flow,underwater image,brightness constancy,differential approach,optical flow estimation,textural image,assumption,textural feature,confidence measure,underwater images,ground-truth optical flow,ground truth,first order | Computer vision,Pattern recognition,Image motion,Optical flow estimation,Artificial intelligence,Motion estimation,Optical flow,Mathematics,Underwater | Journal |
Volume | Issue | ISSN |
25 | 4 | Pattern Recognition Letters |
Citations | PageRank | References |
7 | 0.55 | 15 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| M. A. Arredondo | 1 | 7 | 0.55 |
| K. Lebart | 2 | 49 | 4.11 |
| D. Lane | 3 | 7 | 0.55 |