第18卷第8期 2010年8月
文章编号
1004-924X(2010)08-1869-08
光学精密工程
Optics and Precision Engineering
路面病害检测系统中的图像增强技术
张大奇，曲任茹，何力
（西北工业大学自动化学院，陕西西安710072）
Vol.18No.8
Aug.2010
摘要：为了提高路面病害检测系统的精度和自适应能力，研究了自动路面裂缝图像增强技术。针对图像每个像素建立由邻域一致性模糊摘测度、邻域模糊方差以及全局模糊隶属度组成的模糊特征模式对所有像索进行分类，实现对像素灰度渡越点位置的准确估计；在模糊隶属度函数设计上，利用修改控制点和权因子可局部地修改曲线形状的功能，通过非均匀有理B样条函数设计出一种双“S"形模糊隶属度函数作为灰度变换函数。提出的路面裂缝图像增强技术中的灰度变换函数不仅能和渡越点的位置很好地结合，而且其形状调节因子具备良好的灰度集中能力，仅需很少次数选代增强就能达到突出路面裂纹的效果，实验结果显示，利用提出的图像增强技术可使路面裂缝病害像素正确检测率达到95%，该技术很大程度地提高了路面裂缝自动检测系统的可靠性和检测精度。
关
词：路面病害检测;CCD摄像机；图像增强；模潮测度；灰度变换
中图分类号：TP391.4;U416.03
文献标识码：A
doi;10, 3788/OPE, 20101808. 1869
Applicationofautomaticimageenhancingtechnique
toroaddefectdetectionsystems
ZHANG Da-qi, QU Shi-ru, HE Li
(DepartmentofAutomation，NorthwesternPolytechnicalUniversity,Xi'an710072,China) Abstract: In order to improve precision and adaptive capability of road defect detection system, an image en-hancement technique for automatic road defect is investigated. To estimate the crossover points of gray trans form, a new 3-D pattern formed with two local features of the neighborhood of each pixel and one global fea-ture based fuzzy measurement is constructed for pixel classification. In design of a fuzzy membership function with image enhancement ability, the Non-uniform Rational B-Splines(NURBS) is used to produce a double S shape fuzzy membership function as the gray transform function, The gray transform function can easily be u-nited with the crossover points perfectly and its designable shape can offer capability of gray level centraliza-tion. Therefore, the method can obtain the road crack only by a few operations of iteration and enhancement. Experimental results testify that this adaptive technique can provide satisfactory enhancement effects and the detection accuracy of road crack region pixels reaches 95%. The proposed technique shows better reliability and precision for road defect detection systems.
Key words: detection of road defect; CCD camera; image enhancement; fuzzy measurement; gray
transform
收稿日期：2009-04-09；修订日期：2010-02-24.
基金项目：陕西省科学技术研究发展计划资助项目(No.2008K07-14)