Crack Detection Using Fast Spectral Clustering Considering Graph Connectivity
Crack Detection Using Fast Spectral Clustering Considering Graph Connectivity
复制标题
DOI：
10.1109/compcomm.2018.8780974
复制
发表时间：
2018-12
期刊：
影响因子：
--
通讯作者：
Daiki Shiotsuka;Kousuke Matsushima;Osamu Takahashi
中科院分区：
文献类型：
--
作者：
Daiki Shiotsuka;Kousuke Matsushima;Osamu Takahashi
路面裂缝会引起各种交通问题。因此，我们应该适当地修复它们。目前，计算机视觉中的裂纹检测方法已经提出了很多种。谱聚类就是其中之一，也是一种有效的方法，但由于计算量大，处理时间长。其中，拉普拉斯矩阵和特征值的计算对处理时间的影响尤为显著。为此，本文提出了两种提高算法效率的方法.一种是对拉普拉斯矩阵进行考虑图连通性的稀疏化处理，另一种是考虑路面图像裂缝像素数。
Cracks on pavement roads cause various traffic problems. Therefore we should repair them properly. Nowadays a variety of crack detection methods in computer vision have been proposed. Spectral clustering is one of them and an effective method, but suffers from processing time due to the large amount of calculation. Among them, calculating of Laplacian-matrix and eigenvalues especially affect processing time. Therefore we propose two methods to improve the efficiency of algorithm. One applies sparse process considering graph connectivity for Laplacian-matrix, and the other considers amount of pixel of crack of pavement road images.