摘要
A road recognition algorithm based on image inhomogeneous features and geometry model is introduced to improve its robustness against illumination variations, shadows, noise, or the discontinuity of road boundary, etc.. The local deviation and discontinuity of the road image are fused to obtain the inhomogeneous features of the image which are adaptively transformed into binary based on the threshold obtained from the scale-histogram. After estimating the optimal control points using M-estimator, the road edge can be fitted with 3 points Catmull-Rom spline. The simulation results demonstrate that the proposed algorithm has better robustness and adaptability. The field-testing results show that the recognition rate is higher than 95% under the conditions that images have partial shadow and discontinuous road boundary.
| 源语言 | 英语 |
|---|---|
| 页(从-至) | 384-387 |
| 页数 | 4 |
| 期刊 | Hsi-An Chiao Tung Ta Hsueh/Journal of Xi'an Jiaotong University |
| 卷 | 38 |
| 期 | 4 |
| 出版状态 | 已出版 - 4月 2004 |
学术指纹
探究 'Road recognition algorithm based on inhomogeneous features and spline model' 的科研主题。它们共同构成独一无二的学术指纹。引用此
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver