Abstract
A new road detection algorithm based on image inhomogeneous features and geometry model is introduced to improve its robustness for illumination variations, shadows, noise, or the discontinuity of road boundary, etc. The local deviation and discontinuity of road image are fused to make in-homogeneous image whose is binarized to road edge based on scale-histogram. After estimating the optimum control points using M-estimator road edge above can be fitted with Catmull-Rom spline. The simulation results confirm the fine robustness and adaptiveness of the newly proposed algorithm.
| Original language | English |
|---|---|
| Pages | 5275-5278 |
| Number of pages | 4 |
| State | Published - 2004 |
| Event | WCICA 2004 - Fifth World Congress on Intelligent Control and Automation, Conference Proceedings - Hangzhou, China Duration: 15 Jun 2004 → 19 Jun 2004 |
Conference
| Conference | WCICA 2004 - Fifth World Congress on Intelligent Control and Automation, Conference Proceedings |
|---|---|
| Country/Territory | China |
| City | Hangzhou |
| Period | 15/06/04 → 19/06/04 |
Keywords
- Catmull-Rom spline
- Inhomogeneous features
- M-estimtor
- Road detection