Abstract | ||
---|---|---|
We present promising results for real-time vehicle visual detection, obtained with adaBoost using new original "keypoints presence features". These weak-classifiers produce a boolean response based on presence or absence in the tested image of a "keypoint" (~ a SURF interest point) with a descriptor sufficiently similar (i.e. within a given distance) to a reference descriptor characterizing the feature. A first experiment was conducted on a public image dataset containing lateral-viewed cars, yielding 95% recall with 95% precision on test set. Moreover, analysis of the positions of adaBoost-selected keypoints show that they correspond to a specific part of the object category (such as "wheel" or "side skirt") and thus have a "semantic" meaning. |
Year | Venue | Keywords |
---|---|---|
2009 | Clinical Orthopaedics and Related Research | image categorization,interest points,boosting,vehicle visual detection,image analysis,boolean functions,data collection,real time information |
Field | DocType | Volume |
Boolean function,Data collection,Computer vision,AdaBoost,Real-time data,Pattern recognition,Artificial intelligence,Recall,Mathematics,Test set | Journal | abs/0910.1 |
ISSN | Citations | PageRank |
16th World Congress on Intelligent Transport Systems (ITSwc'2009),
Su\`ede (2009) | 1 | 0.37 |
References | Authors | |
7 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Taoufik Bdiri | 1 | 77 | 5.26 |
Fabien Moutarde | 2 | 54 | 15.26 |
Nicolas Bourdis | 3 | 1 | 0.37 |
Bruno Steux | 4 | 39 | 5.28 |