基于二维熵和轮廓特征的非结构化道路检测

Unstructured road detection based on two-dimensional entropy and contour features

针对非结构化道路场景复杂干扰因素较多、检测困难的问题,提出了一种基于轮廓特征和二维最大熵的道路检测算法。采用融合色彩特征不变量的二次二维最大熵分割算法对道路图像进行分割;利用边界跟踪算法提取分割图像的轮廓特征,根据道路区域的位置和几何特性选取最大轮廓;通过改进Mid-to-side算法进行边缘点搜索,用三阶道路模型重建道路边界,并对道路方向进行判断。实验结果表明,所提算法与传统算法相比,对三类不同场景下非结构化道路的检测准确率可提高25%左右,具有较强抗阴影干扰的能力,并能有效识别道路方向。

The scene of unstructured road is complex and easy to be influenced by many factors. In order to solve the detection difficulty, a road detection algorithm based on contour features and two-dimensional maximum entropy was proposed. Quadratic two-dimensional maximum entropy segmentation method combined with invariant color feature was used for road image segmentation. Afterwards, contour features were extracted from segmentation result by boundary tracking algorithm, and then the maximum contour was chosen. Finally, the improved mid-to-side algorithm was used to search road edge points, then road boundary was reconstructed through road model and road direction was judged. The experimental results show that the detection accuracy rate is improved about 25% in three kinds of unstructured scene compared with traditional algorithm. In addition, this method is robust against shadows and can recognize road direction efficiently.