Abstract | ||
---|---|---|
This paper shows how to improve the real-time object detection in complex
robotics applications, by exploring new visual features as AdaBoost weak
classifiers. These new features are symmetric Haar filters (enforcing global
horizontal and vertical symmetry) and N-connexity control points. Experimental
evaluation on a car database show that the latter appear to provide the best
results for the vehicle-detection problem. |
Year | Venue | Keywords |
---|---|---|
2009 | Clinical Orthopaedics and Related Research | real time,pattern recognition |
Field | DocType | Volume |
Viola–Jones object detection framework,Haar,Computer science,Haar-like features,Artificial intelligence,Robotics,Object detection,Computer vision,Horizontal and vertical,AdaBoost,Pattern recognition,Object-class detection,Machine learning | Journal | abs/0910.1 |
ISSN | Citations | PageRank |
COGIS'07 conference on COGnitive systems with Interactive Sensors,
Stanford, Palo Alto : United States (2007) | 8 | 0.59 |
References | Authors | |
3 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Bogdan Stanciulescu | 1 | 83 | 4.38 |
Amaury Breheret | 2 | 29 | 2.42 |
Fabien Moutarde | 3 | 54 | 15.26 |