Name
Abstract | ||
|---|---|---|
We address the problem of segmenting a video in two classes of different semantic value, namely background and people, with the goal of guaranteeing that no people (or body parts) are classified as background. Body parts classified as background are given a higher classification error cost (segmentation with bias on background), as opposed to traditional approaches focused on people detection. To generate the people-background segmentation mask, the proposed approach first combines detection confidence maps of body parts and then extends them in order to derive a background mask, which is finally post-processed using morphological operators. Experiments validate the performance of our algorithm in different complex indoor and outdoor scenes with both static and moving cameras. |
Year | DOI | Venue |
|---|---|---|
2012 | 10.1109/ICIP.2012.6466819 | Image Processing |
Keywords | Field | DocType |
cameras,image classification,image segmentation,video signal processing,background class,background mask,classification error cost,detection confidence map,morphological operator,moving camera,people class,people detection,people-background segmentation mask,semantic value,static camera,unequal error cost,video segmentation,People detection,background confidence map,detection confidence map,people-background segmentation | Background subtraction,Computer vision,Scale-space segmentation,Market segmentation,Pattern recognition,Segmentation,Computer science,Segmentation-based object categorization,Image segmentation,Operator (computer programming),Artificial intelligence,Contextual image classification | Conference |
ISSN | ISBN | Citations |
1522-4880 E-ISBN : 978-1-4673-2532-5 | 978-1-4673-2532-5 | 3 |
PageRank | References | Authors |
0.37 | 13 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Memarmoghadam Alireza | 1 | 177 | 7.02 |
| A. Cavallaro | 2 | 1938 | 140.21 |
| Jose Martinez | 3 | 224 | 23.89 |
| Garcia-Martin, A. | 4 | 3 | 0.37 |