|本期目录/Table of Contents|

[1]洪汉玉,章秀华,叶佳伦,等.桥梁裂痕检测与识别方法[J].武汉工程大学学报,2014,(02):63-67.[doi:103969/jissn16742869201402012]
 HONG Han yu,ZHANG Xiu hua,YE Jia lun,et al.Detection and recognition method for bridge fissure[J].Journal of Wuhan Institute of Technology,2014,(02):63-67.[doi:103969/jissn16742869201402012]
点击复制

桥梁裂痕检测与识别方法(/HTML)
分享到:

《武汉工程大学学报》[ISSN:1674-2869/CN:42-1779/TQ]

卷:
期数:
2014年02期
页码:
63-67
栏目:
机电与信息工程
出版日期:
2014-02-28

文章信息/Info

Title:
Detection and recognition method for bridge fissure
文章编号:
16742869(2014)02006305
作者:
洪汉玉1章秀华1叶佳伦1荆根强2
1.武汉工程大学图像处理与智能控制研究所,湖北 武汉 430205;2.交通运输部公路科学研究所, 北京 100088
Author(s):
HONG Hanyu1ZHANG Xiuhua1YE Jialun1JING Genqiang2
1.Laboratory for Image Processing and Intelligent Control,Wuhan Institute of Technology,Wuhan 430205,China;2. Research Institute of Highway,Ministry of Transport,Beijing 100088,China
关键词:
桥梁病害 模糊裂痕 图像特征自动识别
Keywords:
bridge distressblurry crackimage featureautomatic recognition
分类号:
TP391
DOI:
103969/jissn16742869201402012
文献标志码:
A
摘要:
桥梁裂痕图像检测过程中,采集的桥梁裂痕图像容易出现模糊,且桥梁裂痕本身具有裂痕特征不明显、杂质干扰大等特点,为了达到对桥梁裂痕准确、快速检测的目的,提出了一种桥梁混凝土结构裂痕病害的自动检测识别方法.首先对采集到的桥梁裂痕图像进行去模糊处理,在此基础上利用非负特征提取桥梁裂痕目标信息,然后利用方差特征去除特征结果图中的伪特征,并使用特征图像中目标特征象素的圆投影特征来增强目标裂痕信息,同时进一步去除虚假特征.分别对不同的桥梁裂痕图像进行了多种不同类型的处理实验,包括裂痕图像去模糊前后的目标裂缝检测结果对比实验,特征图像的方差特征去噪实验,以及圆投影进行特征目标特征增强同时进一步去噪的实验.结果表明,该方法对桥梁裂痕的提取与检测有效,有一定的实际意义.
Abstract:
The acquired image of bridge fissure is easy to be blurred,and the bridge fissure has the characters of nonremarkable fissure feature and excessive noise,during detecting bridge fissure.To detect the bridge fissure quickly and exactly,an automatic detection and recognition method for beton concrete girder bridge was proposed.First,the blur of the acquired bridge fissure image was removed,and the bridge fissure object information was extracted from the deblurred image by using the nonnegative feature.Then false features were eliminated from the feature intensity image with the variance feature method.The circle projection method was used to enhance the object fissure information and to further eliminate the false feature.Different types of experiments are implemented on bridge fissure images,which include the fissure detection result comparison experiment before and after deblurring,the feature image denoising experiment using variance feature,the object information enhancement experiment using circle projection.The results demonstrate that the method proposed in this paper is effective for the bridge fissure extraction and detection.

参考文献/References:

[1]洪汉玉.现代图像图形处理与分析[M].武汉:中国地质大学出版社,2011.HONG Hanyu.Advanced processing and analysis for image and graphics[M].Wuhan:China University of Geosciences Press,2011.(in Chinese)[2]许薛军,张肖宁.基于数字图像的混凝土桥梁裂缝检测技术[J].湖南大学学报:自然科学版,2013,40(7):3440.XU Xuejun,ZHANG Xiaoning.Crack detection of concrete bridges based digital image[J].Journal of Hunan University:Natural Sciences,2013,40(7):3440.(in Chinese)[3]魏武,王俊杰,蔡钊雄.基于小波和Radon变换的桥梁缝检测[J].计算机工程与设计.2013,34(9):31513157.WEI Wu,WANG Junjie,CAI Zhaoxiong.Bridge crack detection based on wavelet and Radon transform[J].Computer Engineering and Design.2013,34(9):31513157.(in Chinese)[4]于泳波,李万恒,张劲泉,等.基于图像连通域的桥梁缝痕提取方法[J].公路交通科技,2011,28(7):9093.YU Yongbo,LI Wanheng,ZHANG Jinquan,et al.Bridge cracks extraction method based on image connected domain[J].Journal of Highway and Transportation Research and Development,2011,28(7):9093.(in Chinese)[5]HONG Hanyu,ZHANG Tianxu.Fast restoration approach for rotational motion blurred image based on deconvolution along the blurring paths[J].Optical Engineering,2003,42(12):34713486. [6]HONG Hanyu,LI Liangcheng,PARK In Kyu,et al.Universal deblurring method for real images using transition region[J].Optical Engineering,2012,51(4):04700604700610.[7]XU Bugao,HUANG Yaxiong. Development of an automatic pavement surface distress inspection system[R].Austin:Center for Transportation Research,the University of Texas at Austin,2003.

相似文献/References:

[1]洪汉玉,章秀华,叶佳伦,等.桥梁裂痕检测与识别方法[J].武汉工程大学学报,2014,(02):88.
 Hong Han-yu,Zhang Xiu-hua,Ye Jia-lun,et al.Hong Han-yu1,Zhang Xiu-hua1,Ye Jia-lun1,Jing Gen-qiang2[J].Journal of Wuhan Institute of Technology,2014,(02):88.

备注/Memo

备注/Memo:
收稿日期:20140224基金项目:国家自然科学基金面上项目(61175013,61305039);湖北省自然科学基金创新群体项目(2012FFA046)作者简介:洪汉玉(1964),男,湖北阳新人,教授,博士,博士研究生导师.研究方向:图像识别与智能控制.
更新日期/Last Update: 2014-03-20