欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
针对汽车在高速公路上行驶的道路区域分割问题，以路面颜色特征为研究对象，提出了一种将聚类分析应用于区域生长准则的算法，实现道路分割。为了提高算法的精确度，对图像进行预处理，消除车道线对道路分割的干扰。根据图像预处理之后道路信息分布的特点，将图像分为3块子区域分别用不同的算法进行检测。对于道路信息丰富，非道路信息也较多的中部区域，在传统区域生长的基础上结合聚类分析，提出了一种自适应生长准则的区域生长算法。该算法既能适应高速公路各种行驶环境，且实时性好、可靠性高、鲁棒性强。
英文摘要：
Aiming at road detection of vehicle driving on the highway, this thesis focused on the color and gray of image, an improved method based on cluster analysis and region growing for road detection was presented. In order to enhance the algorithm＇ s accuracy, image pre-process which could eliminate lane＇ s interferences was taken. After the image pre-process, according to the distribution of the characteristics of the image, it was divided into three parts which were processed in different algorithms. For the central region which had much road information and mixed non-road information, an adaptive region growing rules algorithm which based on the traditional region growing algorithm and cluster analysis was used for segmenting the road region effectively. The algorithm could adaptive many situations on the highway, and it is an algorithm with high accuracy, real-times and robustness.
同期刊论文项目
同项目期刊论文
A spatial orthogonal allocation and heterogeneous cultural hybrid algorithm for multi-robot explorat
Vision-based long-distance lane perception and front vehicle location for full autonomous vehicles o
A regularity model-based multiobjective estimation of distribution algorithm with reducing redundant
期刊信息
位置：