Image-based monitoring of structural damage: concrete surface cracks

Nondestructive imaging has been a widely used approach for detection of local structural damage in the engineering community. By combining image analysis methods, quantities describing the type, severity and extent of damage can be extracted within the spatial domain of images. However, the current practice of structural health monitoring requires a temporal characterization of structural damage, or some correlation of structural damage with response data. To accomplish this, one needs to consider the time scale in using any of the nondestructive imaging techniques, which in turn demands the use of spatial-temporal image analysis. In this paper, we address the temporal occurrence of cracks on the surface of concrete structural members, and attempt to monitor cracks, including their inception and propagation, using temporal image data. We assume under some conditions for objects in a pair of temporal images that only planar rigid-body motion takes place in the image domain, while cracks are treated as a type of local anomaly. The unknown motion parameters are estimated by means of a manifold-based optimization procedure, and the obtained manifold distance (MD) measure is used as a motion-invariant feature to describe the temporal occurrence of concrete cracks. Numerical analyses are conducted with the use of video clips from two laboratory experiments. It is concluded in this paper that the MD-based spatial-temporal image analysis can be an effective means for monitoring local damage of structural components that occurs and is accompanied by structural motion induced by loading.

[1]  Ikhlas Abdel-Qader,et al.  ANALYSIS OF EDGE-DETECTION TECHNIQUES FOR CRACK IDENTIFICATION IN BRIDGES , 2003 .

[2]  Jean Ponce,et al.  Computer Vision: A Modern Approach , 2002 .

[3]  Yoshihiko Hamamoto,et al.  A Method for Crack Detection on a Concrete Structure , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[4]  Victoria J. Hodge,et al.  A Survey of Outlier Detection Methodologies , 2004, Artificial Intelligence Review.

[5]  Benjamin A. Graybeal,et al.  Highway Bridge Inspection: State-of-the-Practice Survey , 2001 .

[6]  Bernard Victorri,et al.  Transformation invariance in pattern recognition: Tangent distance and propagation , 2000 .

[7]  Peter W. Hallinan.  A low-dimensional representation of human faces for arbitrary lighting conditions , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[8]  Tony Lindeberg,et al.  Edge Detection and Ridge Detection with Automatic Scale Selection , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[9]  Yann LeCun,et al.  Transformation invariance in pattern recognition: Tangent distance and propagation , 2000, Int. J. Imaging Syst. Technol..

[10]  Nuno Vasconcelos,et al.  A multiresolution manifold distance for invariant image similarity , 2005, IEEE Transactions on Multimedia.

[11]  Tara C. Hutchinson,et al.  Improved image analysis for evaluating concrete damage , 2006 .

[12]  Dana H. Ballard,et al.  Computer Vision , 1982 .

[13]  Ronald Fedkiw,et al.  Level set methods and dynamic implicit surfaces , 2002, Applied mathematical sciences.

[14]  G. De Schutter.  Advanced monitoring of cracked structures using video microscope and automated image analysis , 2002 .

[15]  George Nagy,et al.  Surface tortuosity and its application to analyzing cracks in concrete , 2004, ICPR 2004.

[16]  Shuji Hashimoto,et al.  Accurate extraction and measurement of fine cracks from concrete block surface image , 2002, IEEE 2002 28th Annual Conference of the Industrial Electronics Society. IECON 02.

[17]  James L Noland,et al.  Computer-Aided Structural Engineering (CASE) Project: Decision Logic Table Formulation of ACI (American Concrete Institute) 318-77 Building Code Requirements for Reinforced Concrete for Automated Constraint Processing. Volume 1. , 1986 .

[18]  ZhiQiang Chen,et al.  Application of PDE methods for image-based concrete surface damage detection , 2007, SPIE Smart Structures and Materials + Nondestructive Evaluation and Health Monitoring.