Name
Abstract | ||
|---|---|---|
This paper presents a general, trainable system for object detection in unconstrained, cluttered scenes. The system derives much of its power from a representation that describes an object class in terms of an overcomplete dictionary of local, oriented, multiscale intensity differences between adjacent regions, efficiently computable as a Haar wavelet transform. This example-based learning approach implicitly derives a model of an object class by training a support vector machine classifier using a large set of positive and negative examples. We present results on face, people, and car detection tasks using the same architecture. In addition, we quantify how the representation affects detection performance by considering several alternate representations including pixels and principal components. We also describe a real-time application of our person detection system as part of a driver assistance system. |
Year | DOI | Venue |
|---|---|---|
2000 | 10.1023/A:1008162616689 | International Journal of Computer Vision |
Keywords | Field | DocType |
computer vision,machine learning,pattern recognition,people detection,face detection,ear detection | Viola–Jones object detection framework,Computer science,Artificial intelligence,Face detection,Object detection,Computer vision,Object-class detection,Pattern recognition,Object Class,Pixel,Haar wavelet,Machine learning,Principal component analysis | Journal |
Volume | Issue | ISSN |
38 | 1 | 1573-1405 |
Citations | PageRank | References |
571 | 82.07 | 20 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Constantine Papageorgiou | 1 | 1897 | 403.34 |
| Tomaso Poggio | 2 | 13488 | 3380.01 |