彩色图像区域生长算法的道路分割识别  

Region growing algorithm for color image segmentation to identify road

作　　者：王建华[1] 骆岩红[1] 文茜[1] 

机构地区：[1]西北民族大学电气工程学院,甘肃兰州730000

出　　处：《自动化与仪器仪表》2014年第5期158-159,166,共3页Automation & Instrumentation

摘　　要：将彩色图像区域生长算法应用到智能交通的道路分割中。针对彩色图像,提出了一种简单的颜色特征提取方法。该方法利用中值点法来改进其中种子点的选取方法,并结合RGB彩色空间中像素点的性质确定区域生长准则和终止准则。实验结果表明:该方法在保证区域连通性的同时,也能够有效的分割出道路区域,同时对各种路况有良好的适应性。In this paper, the color image region growing algorithm is applied to lane segmentation of the in-telligent traffic. This paper presents a simple method for color images feature extraction. The method selects the region growing algorithm for color image processing,uses the median point method to improve the selec-tion of the seed point,and combines with the nature of the pixels in the RGB color space to determine the re-gion growing and termination criteria. The results of experiment show that this method not only ensures the connectivity of the region,but also segment the lane boundary effectively, adapt to a variety of lane conditions.

关 键 词：彩色图像特征提取 区域生长 道路分割 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]