Name
Abstract | ||
|---|---|---|
Automatic road signs recognition (RSR) aims to increase the safety for all traffic participants such as drivers and pedestrians. Despite all the significant advances in road sign detection brought by computer vision for driving assistance, it is still a challenging problem. One reason is the extremely varying lighting conditions, namely daytime and nighttime. An automatic system equipped with a camera on the dashboard of the vehicle, must detect and alarms the driver when a road sign is present in poor lighting conditions. Most of existing RSR systems divided the problem into three modules: object detection, shape recognition and content classification. This paper's main objective is to develop an adequate and robust system for road signs detection independent of lighting. The road sign detection is based on the RGB-color space segmentation with an empirically determined threshold. It extracts the relevant red and blue regions in the image with limit values of Bounding Boxes. The extraction algorithm proposed and its performances are tested and discussed in a dataset of real driving scenarios, captured under various weather conditions. |
Year | DOI | Venue |
|---|---|---|
2016 | 10.1109/IDT.2016.7843064 | 2016 11th International Design & Test Symposium (IDT) |
Keywords | Field | DocType |
Road sign detection,RGB-color space,color segmentation,Bounding Boxes,various weather conditions | Object detection,Computer vision,Computer science,Extraction algorithm,Segmentation,RGB color space,Vision based,Real-time computing,Sign detection,Artificial intelligence,Dashboard (business),Bounding overwatch | Conference |
ISSN | ISBN | Citations |
2162-061X | 978-1-5090-4901-1 | 0 |
PageRank | References | Authors |
0.34 | 9 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Sabrine Hamdi | 1 | 0 | 0.34 |
| Hassene Faiedh | 2 | 21 | 3.25 |
| Chokn Souani | 3 | 0 | 0.34 |
| Kamel Besbes | 4 | 44 | 15.41 |