Name
Abstract | ||
|---|---|---|
Traffic sign recognition has been a recurring application domain for visual objects detection. The public datasets have only recently reached large enough size and variety to enable proper empirical studies. We revisit the topic by showing how modern methods perform on two large detection and classification datasets (thousand of images, tens of categories) captured in Belgium and Germany. We show that, without any application specific modification, existing methods for pedestrian detection, and for digit and face classification; can reach performances in the range of 95% ~ 99% of the perfect solution. We show detailed experiments and discuss the trade-off of different options. Our top performing methods use modern variants of HOG features for detection, and sparse representations for classification. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1109/IJCNN.2013.6707049 | IJCNN |
Keywords | Field | DocType |
pedestrians,image representation,pedestrian detection,traffic engineering computing,belgium,hog features,classification datasets,digit classification,feature extraction,image classification,detection datasets,object detection,public datasets,road traffic,face classification,visual objects detection,germany,traffic sign recognition,sparse representations | Data mining,One-class classification,Feature detection (computer vision),Computer science,Artificial intelligence,Contextual image classification,Pedestrian detection,Object detection,Object-class detection,Pattern recognition,Feature extraction,Traffic sign recognition,Machine learning | Conference |
ISSN | ISBN | Citations |
2161-4393 | 978-1-4673-6128-6 | 67 |
PageRank | References | Authors |
2.35 | 8 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Markus Mathias | 1 | 443 | 16.78 |
| Radu Timofte | 2 | 1880 | 118.45 |
| Rodrigo Benenson | 3 | 1750 | 63.78 |
| Luc Van Gool | 4 | 27566 | 1819.51 |