基于TopHat分割和曲线模型的三车道检测方法

Three-lane Detection Method Based on TopHat Segmentation and Curve Models

为了解决传统三车道检测过程中算法易受干扰、车道线拟合不准确、两侧车道误判等问题,提出了一种基于顶帽算法(Top Hat)分割和曲线模型的三车道检测方法.利用车道线的形状和颜色特征,在图像预处理阶段提出了一种变内核Top Hat的车道线分割算法.在车道线识别阶段,首先,提出了一种基于加权最小二乘法(weighted least squares,WLS)的消失点拟合方法以约束霍夫变换;其次,在极坐标中以DBSCAN(density-based spatial clustering of applications with noise)聚类法对直线聚类并匹配三车道模板;再次,以该模板为基础建立车道线感兴趣区,在每个感兴趣区内搜索并以三次曲线模型拟合车道线;最后,对于不确定的边侧车道,提出了一种基于随机投种法的边侧车道可行驶性判定方法.算法检测率以及漏检率结果显著优于传统三车道识别算法.实验结果表明:该算法具有良好的准确性及稳定性,更适用于三车道环境.

In order to solve problems in the process of traditional three-lane detection, such as low anti-interference capacity, inaccuracy in lane fitting, and error identification of side lane, a three-lanedetection method was proposed in this paper based on TopHat segmentation and curve models. A lanesegmentation algorithm using variable-kernel TopHat was proposed as image pre-processing, by usingshape features and color features of lane markings. For lane detection, firstly, a vanish-point fittingmethod based on WLS (weighted least squares) was proposed as a constraint of Hough transform.Secondly, straight lines were clustered in polar coordinates by using DBSCAN (density-based spatialclustering of applications with noise), matching to a template. Then lane ROI (region of interest) wasmade according to the straight-line template, and the lane was searched and fitted by using cubic curve.Finally, for uncertain side-lanes, a side-lane driving judgement method was proposed by using randomseed.The algorithm has better performance in both detection rate and lane miss rate than traditionalthree-lane detection algorithms. Experiment verifies that the method has high accuracy and stability, andis useful for three-lane detection.