Automatic Crack Detection and Measurement of Concrete Structure Using Convolutional Encoder-Decoder Network

Abstract

The detection and measurement of crack at pixel level is a challenge to existing methods. To overcome this challenge, this paper proposes a convolutional encoder-decoder network (CedNet) to detect crack from image, and the maximum widths and orientations of cracks are measured using image postprocessing techniques. To realize this, a database including 1800 crack images (with 761×569 pixel resolution) taken from concrete structures is built. Then the CedNet is designed, trained and validated using the built database. The validating results show 98.90% accuracy, 93.58% precision, 94.73% recall, 93.18% F-measure, 87.23% intersection over union (IoU) of crack and 98.82% IoU of background. Subsequently, the robustness and adaptability of the trained model is tested. To measure true maximum widths and orientations of cracks, a laboratory experiment is carried out to calibrate a relation between ratio (pixel distance / real distance) and field of view (camera's view range on concrete surface included in image) and distance from the smartphone to concrete surface. In the post-processing techniques, the perspective transformation is employed to correct distorted images caused by the existence of the oblique angles between the smartphone and concrete surfaces. Then the maximum widths and orientations of cracks in predicted results are measured respectively using the Euclidean distance transformation and least squares principle. As comparison, two existing deep learning-based crack detection and measurement method are used to examine the performance of the proposed approach. The comparison results show that the proposed method substantiates quite good performance to detect cracks and measure maximum widths and orientations of cracks in our database.

Study on Crack Resistance of Hydraulic Roller Compacted Concrete Dam with Fly Ash Admixture

“…The experimental equipment is shown in Table 1. The cement used in the experiment is P • O42.5R ordinary portland cement produced by Dalian cement plant, and the cement is placed in a dry and ventilated place to ensure that the cement will not be affected by moisture and caking [7][8] . In the process of concrete configuration, adding admixtures can improve the performance of concrete and reduce the cost.…”

Exploring the Detection Accuracy of Concrete Cracks Using Various CNN Models

“…Human-based visual inspection is a familiar method for inspecting and evaluating the health of concrete structures. However, the human-based visual inspection and evaluation are time-consuming and subjective [11]. e accuracy of damage diagnosis depends mainly on the skill level and experience of the inspectors.…”

Evaluating the Work Productivity of Assembling Reinforcement through the Objects Detected by Deep Learning

“…Cha et al [ 55 , 56 , 57 , 58 ] used deep learning technology based on convolutional neural networks to complete the identification and location of surface cracks in concrete structures, the volume measurement of surface corrosion on steel structures, and the volume measurement of concrete spalling damage. Concrete surface defect identification is also an issue that has been studied frequently in recent years, and representative ones are Xu et al [ 59 ], G Li et al [ 60 ], S Li et al [ 61 ], Miao et al [ 62 ] and others. However, most objects covered in the literature mentioned above are materials of existing built structures, which are not strictly speaking construction materials.…”