基于泊松噪声-双边滤波算法的桥梁裂缝修补痕迹图像分割
DOI:
作者:
作者单位:

河南大学土木建筑学院

作者简介:

通讯作者:

中图分类号:

U446

基金项目:

甘肃省科技重大专项计划项目(19ZD2GA002);校企合作项目(2019-003);河南省科技发展计划项目(182300410150,162102210173);河南省交通厅项目(2016Y2)


Image segmentation of bridge crack repair traces based on Poisson-noise and bilateral-filtering algorithm
Author:
Affiliation:

School of Civil Engineering and Architecture of Henan University

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    裂缝作为混凝土桥梁的主要病害大量存在,部分裂缝修补后会二次开裂,且裂缝修补痕迹在病害智能识别中易与混凝土剥落等缺陷混淆,因此裂缝修补痕迹的准确识别不仅是二次裂缝准确识别的基础,也是混凝土桥梁整体病害识别的重要环节。为了获取边缘清晰连续的裂缝修补痕迹,本文先对裂缝修补痕迹的图像添加泊松噪声,再利用双边滤波对添加的噪声及原有噪声进行平滑,然后用Otsu算法对裂缝修补痕迹进行图像分割,并使用峰值信噪比(PSNR)和结构相似性(SSIM)评价滤波效果,使用运行时间和最大连续可用内存块(LCFB)使用情况评价分割效果,最后以河南省某高速公路桥梁历年定检中的裂缝修补痕迹图像作为实例,对本文方法进行实际验证。结果显示,裂缝修补痕迹图像经过泊松噪声-双边滤波算法处理后,PSNR值最高约35.0901dB,SSIM值可达约0.8801,说明添加泊松噪声可改善图像质量并优化双边滤波效果;经过Otsu算法进行图像分割的运行时间比其他方法缩短约25%~50%,LCFB比其他方法提高约0.25%;经过处理的裂缝修补痕迹图像达到理想预期效果,验证了本文提出的方法的有效性和可行性。

    Abstract:

    As a main kind of disease, large number of crack exist in the concrete bridge, and some cracks will be secondary dehisced after maintenance, and the crack repair traces are easily confused with concrete spalling and other defects when identifying disease intelligently, so identifying the crack repair traces accurately is not only the basis of identification of secondary cracks but also important to the identification of the overall disease of concrete bridges. To obtain crack repair traces with continuous edges clearly, this paper proposes a method to add Poisson-noise to the image of crack repair traces firstly, then uses bilateral-filtering to smooth the added noise and the original noise, then uses the Otsu algorithm to segment the image of crack repair traces. The filtering effect is evaluated using the peak signal-to-noise ratio (PSNR) and structural similarity (SSIM), and the segmentation effect is evaluated using the running time and maximum continuous memory block (LCFB) usage. The results show that the highest PSNR value of the crack repair trace images processed by the Poisson-noise and bilateral-filtering algorithm is about 35.0901 dB, and the SSIM value reach about 0.8801, which shows that adding Poisson-noise improves image quality and optimizes the bilateral filtering effect. The running time of image segmentation by the Otsu algorithm is about 25%-50% shorter than other methods, and the LCFB is about 0.25% higher than other methods. The processed crack repair trace images achieve the desired expected effect, which verifies the effectiveness and feasibility of the method proposed in this paper.

    参考文献
    相似文献
    引证文献
引用本文
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2022-08-12
  • 最后修改日期:2022-12-29
  • 录用日期:2023-01-11
  • 在线发布日期:
  • 出版日期: