Autonomous Crack and Bughole Detection for Concrete Surface Image Based on Deep Learning

Abstract

Cracks and bugholes (surface air voids) are common factors that affect the quality of concrete surfaces, so it is necessary to detect them on concrete surfaces. To improve the accuracy and efficiency of the detection, this research implements a novel deep learning technique based on DeepLabv3+ to detect cracks and bugholes on concrete surfaces. Firstly, in the decoder, the 3 × 3 convolution of the feature fusion part is improved to a 3-layer depth separable convolution to reduce the information loss during upsampling. Secondly, the original expansion rate combination is changed from 1, 6, 12, 18 to 1, 2, 4, 8 to improve the segmentation effect of the model on the image. Thirdly, a weight value is added to each channel of the Atrous Spatial Pyramid Polling (ASSP) module, and the feature maps that contribute significantly to the target prediction are learned and screened. To use this method, a database is built containing 16,662 256 × 256 pixel images of bugholes and cracks on concrete surfaces. The two defects included in those images are labeled manually. The DeepLabv3+ architecture is then modified, trained, validated and tested using this database. A strategy of model-based transfer learning is applied to optimize and accelerate the learning efficiency of the model. The weights and biases of the Xception part of the model are initialized by the pretrained backbones. The results are 97.63% (crack), 93.53% (bughole) Average Precision (AP), 95.58% Mean Average Precision (MAP) and 81.87% Mean Intersection over Union (MIoU). A comparative study is conducted to verify the performance of the proposed method, and the results demonstrate that the proposed approach performs significantly better in crack and bughole detection on concrete surfaces.

CNN-Based Image Quality Classification Considering Quality Degradation in Bridge Inspection Using an Unmanned Aerial Vehicle

“…Also, image processing techniques for a large number of high-resolution inspection images are not suitable as they require a lot of processing time. As parallel operation using a graphic processing unit (GPU) was developed in the computer vision field, studies on models for damage detection and classification using convolutional networkbased deep learning algorithms were carried out [11]- [13]. The damage detection model using deep learning extracts similarly recognized results by continuously learning and adjusting the features of labels from image datasets with preguided labels.…”

Enhancing Pavement Distress Detection Using a Morphological Constraints-Based Data Augmentation Method

“…Detection networks based on deep convolutional neural networks have become the most popular algorithms among researchers in the area of pavement distress detection [1][2][3][4][5][6][7][8][9][10][11][12]. With the development of deep learning theory and the improvement of computer hardware performance, the depth and breadth of detection networks have been increasing to achieve superior accuracy, along with a rapid increase in the number of parameters.…”

A Real-Time Detection Method for Concrete Surface Cracks Based on Improved YOLOv4

“…In addition, it has been emphasized in image classification and object detection [15]. Researchers have developed many methods based on deep learning to detect pavement cracks [16][17][18], concrete cracks [19][20][21][22], concrete bug holes [23][24][25], and other defects [26][27][28][29][30][31]. CNN-based crack detection methods generally have problems, such as excessive training parameters and complex network structures.…”