无人驾驶汽车中的车道线检测研究

Research on Lane Line Detection in Driverless Cars

随着人工智能的发展,无人驾驶将成为一种新的交通趋势。无人驾驶汽车是通过车载传感系统感知道路环境,自动规划行车路线并控制车辆到达预定目标的智能汽车。无人驾驶技术集自动控制、体系结构、人工智能、视觉计算等众多技术于一体,是计算机科学、模式识别和智能控制技术高度发展的产物。有效的获取车道线信息,对无人车的决策有至关重要的作用。本文对车道线图片进行预处理,包括中值平滑去噪、形态学变换、OSTU阈值分割,最后采用Sobel算法进行车道线轮廓提取,MATLAB仿真结果表明,该方法能快速准确的检测出车道线。

With the development of artificial intelligence, driverless driving will become a new traffic trend. A driverless car is a smart car that senses the road environment through an in-vehicle sensing system, automatically plans driving routes, and controls the vehicle to reach a predetermined target. The unmanned technology integrates many technologies such as automatic control , architecture , artificial intelligence, and visual computing. It is a product of computer science, pattern recognition and intelligent control technology. Effective access to lane line information is critical to the decision-making of unmanned vehicles. In this paper, the lane line image is preprocessed, including median smoothing denoising, morphological transformation, OSTU threshold segmentation. Finally, the sobel algorithm is used to extract the lane line contour. The MATLAB simulation results show that the method can de? tect the lane line quickly and accurately.