针对有阴影情况下的道路及导航线提取问题, 提出一种基于光照不变图像分割和投票函数的阴影道路图像道路及视觉导航线提取算法, 该算法利用正交分解法获取彩色光照不变图像, 并对其进行分割, 通过构造的投票函数及道路判别准则提取道路区域, 扫描道路定位点后对其进行最小二乘拟合提取导航线。该方法不需要大量样本进行学习。实验结果表明, 所提算法与现有两种算法相比, 在检测精度和速度上均具有明显优势, 并且算法复杂度较低。算法能够有效地解决阴影环境下道路及导航线的提取问题。

For extracting the road and navigation line under the shadow environment, a road and visual navigation line extraction algorithm is proposed based on illumination invariant image segmentation and vote functions. The color illumination invariant image is acquired with orthogonal decomposition method. After the image segmentation, the road region is extracted through the structure of the vote function and road criterion. The navigation line is detected by scanning path location and the least squares fitting. The proposed method does not require a large number of samples to learn. Experimental results show that, compared with two existing algorithms, the proposed algorithm has obvious advantages in detection accuracy, speed and complexity, it can effectively solve the road and navigation line extraction under the shadow environment.