| 基于相位信息与空间关系的路面裂缝检测 |
| |
| 引用本文： | 陈松,靳华中,郭鹏. 基于相位信息与空间关系的路面裂缝检测[J]. 湖北工业大学学报, 2014, 0(4): 106-111 |
| |
| 作者姓名： | 陈松 靳华中 郭鹏 |
| |
| 作者单位： | 湖北工业大学计算机学院,湖北 武汉430068 |
| |
| 基金项目： | 国家级大学生创新创业训练计划（201210500021）;湖北省省优秀青年基金（Q20121410）;湖北工业大学博士启动基金（BSQD12033） |
| |
| 摘 要： | 针对传统边缘检测算法的不足,分析路面裂缝低信噪比特点,提出了一种基于相位信息与区域空间关系的路面裂缝检测方法。首先,利用相位信息计算成对像素的相似性,并引入空间关系,使得位于边缘同侧的相似性增强,异侧的相似性减弱,然后应用谱方法进行聚类,完成裂缝边缘提取。实验结果表明方法有效。
|
| 关 键 词： | 裂缝检测 相位信息 空间关系 聚类 方向能量模型 |
Pavement Crack Detection based on Phase Information and Spatial Relations |
| |
| CHEN Song,JIN Huazhong,GUO Peng. Pavement Crack Detection based on Phase Information and Spatial Relations[J]. Journal of Hubei University of Technology, 2014, 0(4): 106-111 |
| |
| Authors: | CHEN Song JIN Huazhong GUO Peng |
| |
| Affiliation: | (School of Computer Science, Hubei Univ. of Tech. , Wuhan 430068, China) |
| |
| Abstract: | Aiming at the traditional arithmetic insufficiency,this paper purposes a pavement crack detection based on phase information and spatial relations.Firstly,the similarity between pairs of pixels was calcu-lated through the phase information.Then,spatial relationship was introduced to find regions where simi-larity between pixels in a given region is high and similarity between pixels in different regions is low.Af-ter that,the crack edge detection was completed with the spectral clustering method.The experimental re-sults prove the effectiveness of the crack detection method. |
| |
| Keywords: | crack detection phase information spatial relations spectral clustering oriented energy model |
| 本文献已被 维普 等数据库收录！ |
|
