基于二维熵与轮廓特征非结构化道路检测.docVIP

基于二维熵与轮廓特征非结构化道路检测 　　文章编号:10019081(2013)07200504 doi:10.11772/j.issn.10019081.2013.07.2005 摘 要： 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。 关键词：二维最大熵；色彩特征不变量；轮廓特征；非结构化道路；道路模型 中图分类号：TP391.413 文献标志码:A 英文标题 Unstructured road detection based on twodimensional entropy and contour features  英文作者名 GUO Qiumei*, HUANG Yuqing 英文地址( School of Information Engineering, Southwest University of Science and Technology, Mianyang Sichuan 621010, China英文摘要) Abstract： 作者改过中文摘要，在现在英文翻译的基础上进行修改。 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. 英文关键词Key words： twodimensional maximum entropy; invariant color feature; contour feature; unstructured road; road model  0 引言 随着人们对智能导航系统需求的增加，无人驾驶自主导航系统研究得到了飞速发展，道路检测是其中的一项关键技术。能否准确检测出前方道路是智能车辆安全行驶的前提条件［1］。 道路一般分为结构化道路和非结构化道路两类，结构化道路有明显的车道标志线，检测方法相对成熟；非结构化道路所处环境复杂干扰因素较多，如光照变化、阴影