Abstract | ||
---|---|---|
We present an active vision system for segmenta- tion of visual scenes based on integration of several cues. The system serves as a visual front end for generation of object hypotheses for new, previously unseen objects in natural scenes. The system combines a set of foveal and peripheral cameras where, through a stereo based fixation process, object hypothe- ses are generated. In addition to considering the segmentation process in 3D, the main contribution of the paper is integration of different cues in a temporal framework and improvement of initial hypotheses over time. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1109/ROBOT.2010.5509973 | ICRA |
Keywords | Field | DocType |
shape,robustness,active vision,layout,image segmentation,machine vision,mathematical model,front end,computer science,visualization | Object detection,Computer vision,Scale-space segmentation,Machine vision,Segmentation,Visualization,Computer science,Image segmentation,Robustness (computer science),Artificial intelligence,Foveal | Conference |
Volume | Issue | ISSN |
2010 | 1 | 1050-4729 |
Citations | PageRank | References |
37 | 1.50 | 9 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Mårten Björkman | 1 | 202 | 13.90 |
Danica Kragic | 2 | 2070 | 142.17 |