Abstract | ||
---|---|---|
We propose a 3D object recognition method based on first extracting a compact description of image sequences, and then matching these descriptions with a two-steps strategy. The compactness of the description, made of a set of time-invariant local features, allows us to use a simple nearest neighbour matching to obtain an initial set of recognition hypothesis; spatio-temporal constraints help us to con- firm or to reject these hypotheses. We carried out an extensive experimental analysis to assess our method against changes in illumination, abrupt scale changes, occlusions, clutter, view-point variations. Since our approach is based on the use of image sequences we also tested it with different camera motions. Our description strategy may be also applied to relatively simple poor-textured objects, since few stable features are enough for recognition. |
Year | DOI | Venue |
---|---|---|
2007 | 10.1109/WIAMIS.2007.77 | WIAMIS |
Keywords | Field | DocType |
simple nearest neighbour,spatio-temporal constraint,two-steps strategy,image sequence,recognition hypothesis,view-based description,initial set,simple poor-textured object,object recognition method,compact description,description strategy,abrupt scale change,lighting,object recognition,feature extraction,coherence,experimental analysis,testing,data mining | Computer vision,Nearest neighbour,Pattern recognition,Clutter,Computer science,Image matching,View based,Compact space,Feature extraction,Artificial intelligence,Cognitive neuroscience of visual object recognition | Conference |
ISBN | Citations | PageRank |
0-7695-2818-X | 2 | 0.37 |
References | Authors | |
8 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Elisabetta Delponte | 1 | 50 | 4.72 |
N. Noceti | 2 | 30 | 1.91 |
F. Odone | 3 | 98 | 10.27 |
Alessandro Verri | 4 | 1754 | 190.73 |