Study On The Bridge Bottom Crack Inspection And Recognition Method Based On Image Processing

The highway bridge has been a very important part of the transportation construction in our country.In recent years,the number of bridges in need of maintenance are increasing due to reform and opening up.Therefore,the need for bridge safety testing especially for bridge crack detection has been raised to a new level.The traditional detection method not only has high risk,high cost,but also has low detection efficiency,low detection accuracy and low reliability.The rapid development of modern computer technology and the continuous improvement of computer hardware performance,making it possible to apply fastest growing digital image processing technology to bridge crack detection.Therefore,it is of great importance to propose a new visual crack detection method to complete bridge health evaluation.In this paper,an image processing algorithm for crack detection of concrete bridges is proposed based on a self-designed bridge detection device which can acquire the image of bridge bottom surface in real time.The crack classification is completed by using the classification method based on machine learning.Finally,the calculation of the maximum width of the bridge crack is carried out,which will make an important contribution to the improvement of bridge detecting and maintenance in transportation.The main works are as follows:(1)The image is pretreated to enhance the target cracks and weaken the noise and disruptors.Pretreatment includes grayscale,filtering and image enhancement.Then,the processed image is coarsely segmented.By using image morphological analysis method,the noise block in the image is filtered,and the target of the bridge crack is preliminarily separated.(2)Connection the crack fragments.Due to the above image processing method may destroy the connectivity of the cracks.In order to achieve a more continuous and complete crack,this paper proposes a crack connection algorithm based on the KD tree.First,obtain the minimum convex polygon of the crack target,and identify the start and end point of each crack fragment.Second,connect the two endpoints from different fragments if their pixel distance is less than the set threshold.Third,fill the connected line segments by testing the grayscale characteristics of the connection region.Finally,a complete crack target is extracted.(3)Classify the cracks.Due to different shapes of cracks have different degree of harm on the bridge,it is necessary to classify cracks after the complete crack target extract.In this paper,the classification of SVM decision tree based on learning type is proposed based on the classification requirements of cracks.According to the different characteristics of the crack,the 7 dimension characteristic vector of the crack is extracted.The SVM classifier is then trained according to the training sample.Finally,the validation samples are input into the trained SVM classifier.Then,the validation classification is performed.The results show that the classification method used in this paper has high accuracy of bridge cracks classification and can be applied to the project.(4)Calculation crack length and maximum width.Aiming at the low calculation accuracy of the geometric information such as the length and width of crack,the skeleton point of the crack is calculated in the second value image.The length of the crack is obtained by skeleton,and the image refinement is improved.The calculation of the maximum width of the crack in the algorithm was calculated by the two-valued morphological corrosion algorithm.By comparing the measured results with the measured results,the conclusion is drawn.The proposed crack maximum width calculation method can meet the requirement of engineering practice in the recognition of the precision.Currently,the use of digital image processing technology on concrete bridge crack detection has obtained a widespread concern.This visual detection method not only can free humans from heavy and dangerous work,but also can greatly improve the working efficiency and reduce the cost.It can effectively eliminate the subjective interference.This visual detection method has high practical value and application prospects.