完全非结构化道路检测是智能车辆自主行驶所面临的关键技术难题,解决该问题可以增强智能车辆的环境适应能力。以实时道路图像的真彩色信息为研究对象,提出一种三次样条曲线模型和分块子区生长模型相结合的完全非结构化道路检测算法。该算法运用三次样条曲线插值实现了真彩色空间到伪彩色空间的映射,采用主次伪色调和纹理信息相结合的子区生长方法,实现了完全非结构化道路检测。实地图像测试和对比试验表明,该算法对道路区域检测准确性高,对受到阴影、水迹等影响的道路区域具有较强抗干扰能力,实时性好。

Detecting completely unstructured road may improve the adaptability for different environments,which is crucial for intelligent autenomous vehicle driving. In this paper, a road detection algorithm combined with cubic spline curve model and block sub-region growing model (CSCM_BSG) is proposed for true-color information of real-time road images.The algorithm applies the cubic spline interpolation to achieve the pseudo-color mapping at first, and accomplishes road region detection using the sub-region growing method combining the primary and secondary pseudo-hues with textures.The tests and comparative experiments on field images show that the algorithm is not only more accurate and applicable in real-time for road regions, but also has stronger counter-interference capability for shadows, water stains.