摘要
就几何特征而言,直线和直线条带是描述道路的最理想符号。道路影像中的直线和直线条带多数具有较长的长度,同时由于干扰和噪声的存在,直线中往往包含有缝隙,直线条带则会包含孔洞以及附着有不规则块,已有的方法在提取这类不甚理想的基元时都有一些缺陷。本文提出了一种针对此情况的直线提取新思路,首先提取并细化边缘,然后依据结构特点得出直线基本段,最后反复地利用已获取部分预测并检测出后续点,同样的思路也可用于提取构成道路影像的直线条带。实验结果证明,算法具有优良的性能。
Straight line and linear band are the best symbols for representing roads in regard to geometric characteristics. Most of the straight lines and linear bands in a road image are quite long. Because disturbance and noise exist, a straight line may contain some fissures and a linear band may contain some holes and be attached to some irregular blocks. Existing approaches all have a few drawbacks while they are used to extract such features. In order to overcome these disadvantages, a new method for line extracting is given. Firstly, it extracts the line and thins the edges, and then finds a base line segment according to the structural characteristics; finally predicts and detects the following points iteratively by making use of the obtained part. The same principle can also be used to extract the linear bands of which a road consists. Experimental results show that this method has excellent performance.
出处
《仪器仪表学报》
EI
CAS
CSCD
北大核心
2007年第3期519-523,共5页
Chinese Journal of Scientific Instrument
关键词
直线提取
直线条带提取
道路提取
图像分析
line extraction
linear band extraction
road extraction
image analysis
