Abstract | ||
---|---|---|
Motion detection algorithms usually detect moving regions in a rough way; in some application contexts it could be mandatory
to obtain the exact shape of such objects by removing cast shadows as well as ghosts and reflections due to variations in
light conditions. To address this problem we propose an approach based on edge matching. The basic idea is that edges extracted
in shadow (or ghost) regions in current image exactly match with edges extracted in the correspondent regions in the background
image. On the contrary, edges extracted on foreground objects have not correspondent edges in the background image. In order
to remove all shadow regions instead of only shadow points, we firstly segment the foreground image into subregions, according
to uniformity of photometric gain between adjacent points. The algorithm has been tested in many different real contexts,
both in indoor and outdoor environments.
|
Year | DOI | Venue |
---|---|---|
2009 | 10.1007/978-3-642-10520-3_41 | International Symposium on Visual Computing |
Keywords | Field | DocType |
correspondent region,shadows removal,shadow point,foreground image,background image,shadow region,cast shadow,edges matching,correspondent edge,foreground object,adjacent point,current image | Computer vision,Shadow,Motion detection,Pattern recognition,Computer science,Edge matching,Artificial intelligence | Conference |
Volume | ISSN | Citations |
5876 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 22 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Paolo Spagnolo | 1 | 168 | 22.37 |
Pier Luigi Mazzeo | 2 | 72 | 13.84 |
Marco Leo | 3 | 81 | 12.03 |
Tiziana D'Orazio | 4 | 204 | 31.62 |