• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Journal of information and computational science >A Pavement Cracks Detection Algorithm Based on NSCT Domain
【24h】

A Pavement Cracks Detection Algorithm Based on NSCT Domain

机译：基于NSCT域的路面裂缝检测算法

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

The complex nature of road images and weak signal make the detection pavement cracks particularly difficult. In order to solve this problem, an algorithm for pavement cracks detection based on Non Subsampled Contourlet Transform (NSCT) is proposed. Firstly, the high frequency sub-band coefficients and low frequency sub-band coefficients at different scales and in different directions are obtained by image decomposition using the NSCT. Then, the adjacent sub-band coefficients subtraction to deal with the noise in high frequency sub-bandthe modulus maximum method is used to get the edge inspection of high frequency sub-band image. The Canny operator is used to proceed the edge detection of low frequency sub-band image. Finally, the low frequency image is adopted to compensate the high frequency image for obtaining the final edge image. The experimental result shows that this method has the advantages of correct edge position, complete detection and few false edge points.
机译：道路图像的复杂性质和微弱的信号使得检测路面裂缝特别困难。为了解决这一问题，提出了一种基于非二次采样轮廓波变换（NSCT）的路面裂缝检测算法。首先，利用NSCT对图像进行分解，得到不同尺度，不同方向的高频子带系数和低频子带系数。然后，对相邻子带系数进行减法处理，以处理高频子带中的噪声。采用模最大法对高频子带图像进行边缘检测。 Canny运算符用于进行低频子带图像的边缘检测。最后，采用低频图像对高频图像进行补偿，以获得最终的边缘图像。实验结果表明，该方法具有正确的边缘位置，完整的检测和较少的虚假边缘点的优点。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号