Abstract
Detection of defects including cracks and spalls on wall surface in high-rise buildings is a crucial task of buildings' maintenance. If left undetected and untreated, these defects can significantly affect the structural integrity and the aesthetic aspect of buildings. Timely and cost-effective methods of building condition survey are of practicing need for the building owners and maintenance agencies to replace the time- and labor-consuming approach of manual survey. This study constructs an image processing approach for periodically evaluating the condition of wall structures. Image processing algorithms of steerable filters and projection integrals are employed to extract useful features from digital images. The newly developed model relies on the Support vector machine and least squares support vector machine to generalize the classification boundaries that categorize conditions of wall into five labels: longitudinal crack, transverse crack, diagonal crack, spall damage, and intact wall. A data set consisting of 500 image samples has been collected to train and test the machine learning based classifiers. Experimental results point out that the proposed model that combines the image processing and machine learning algorithms can achieve a good classification performance with a classification accuracy rate = 85.33%. Therefore, the newly developed method can be a promising alternative to assist maintenance agencies in periodic building surveys.
Highlights
During the construction and maintenance of high-rise buildings, it is very crucial to attain good surface quality of structures due to safety and esthetics aspects
It is because during the operation phase, the surface of slab structure is concealed by floor coverings such as ceramic or stone tiles. erefore, this study focuses on the visual assessment of wall structures
In Vietnam, periodic surveys on building condition are usually performed by visual assessment of human inspectors. is fact is common in other countries because visual changes in structures can directly point out the potential problems of building structures [2]
Summary
During the construction and maintenance of high-rise buildings, it is very crucial to attain good surface quality of structures due to safety and esthetics aspects. The process of visual assessment, measurement, data processing, and report can be very time consuming especially for high-rise buildings with large surface areas needed to be inspected periodically It is immensely beneficial for the building owners and maintenance agencies if the manual inspection process can be replaced by a more productive and consistent method of surveying [7]. E objective of the current study is to combine image processing techniques and advanced machine learning algorithms into an integrated model that is capable of detecting and categorizing the defective areas on wall structures. By using an intelligent model that can recognize and categorize types of cracks and spalling areas simultaneously, the task of periodic building condition survey can be executed in a more effective manner. E rest of the paper is organized as follows: the research methodology is reviewed briefly followed by the description of the newly constructed automatic approach for wall defect detection; the fourth section reports experimental results of this study, followed by the conclusion in the final section
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have