A Real-Time Bridge Crack Detection Method Based on an Improved Inception-Resnet-v2 Structure

Abstract

Bridge crack detection is essential to ensure bridge safety. The introduction of deep learning technology has made it possible to detect bridge cracks automatically and accurately. In this study, the Inception-Resnet-v2 algorithm was systematically improved and applied to the real-time detection of bridge cracks. We propose an end-to-end bridge crack detection model based on a convolutional neural network. This model combines the advantages of Inception convolution and residual networks, broadening the network width and alleviating the training problem of the deep network. The calculation speed is improved while still ensuring accuracy. Multi-scale feature fusion enables the network to extract contextual information of different scales, which improves the accuracy of crack recognition. The GKA (K-means clustering method based on a genetic algorithm) realizes the accurate segmentation of the target area, greatly enhances the clustering effect, and effectively improves the detection speed. In this model, large fracture datasets are used for training and testing without pre-training. The experimental results show that the performance of this method was improved in all aspects: accuracy, 99.24%; recall, 99.03%; F-measure, 98.79%; and FPS(Frames Per Second), 196. INDEX TERMS bridge crack detection, Inception-Resnet-v2, multiscale feature fusion, GKAThis work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.

Application of Distributed Network in Bridge Structure Safety Inspection

“…In determining the index weight, it has very strong subjectivity, which cannot reflect the risk level [4]. In fact, the safety of bridge structure is a huge uncertainty system, which is mainly manifested in the uncertainty of evaluation factors and the fuzziness and randomness of factor data [5].…”

Concrete Surface Crack Recognition Based on Coordinate Attention Neural Networks

“…In the future, cameras, smartphones, and other shooting equipment should be used to collect concrete crack images in different scenes, expand the dataset, and improve the generalization of the model. Network model Recall (%) F1-score (%) Precision (%) DCNN [22] 76 73 77 ResNet50 [15] 79 76 79 SENet [23] 81 79 82 ResNet50-BAM [24] 84 82 83 ResNet50-CBAM [25] 84 80 85 SCHNet [14] 85 84 84 CaNet 86 85 87…”

“…However, as the number of network layers rises, over-fitting and network model degradation issues will also arise, making it more difficult to train models and preventing the system from convergence. He K and others [ 15 ] created a residual block by incorporating shortcut connections into the original DCNN [ 24 ] network structure (RB). Figure 4 depicts the RB structure.…”

“…Experiments show that the average IOU reaches 85.31%. Wang et al [ 15 ] used the improved inception RESNET V2 model to identify bridge cracks. The experimental results show that each performance index has been improved to varying degrees: the accuracy is 99.24%; the recall rate is 99.03%; fF-measure is 98.79%; FPS is 196.…”

Avpd: An Anti-virus Model with Remote Thread Injection for Android Based on ResNet50

“…ResNet is a machine learning model commonly used in machine learning and deep learning and has essential applications in multiple fields. With different groups of suitable options, it works well in Meteorological Learning [8], Medical Rectal Cancer [9], Signature Recognition [10], Acoustic Modeling [11], Masked Face Recognition [12], Physics of fluid flow [13], Civil engineering-bridge cracks [14], Voice recording for language recognition [15], and dentification of breast cancer pathological sections [16]. We use file diffraction mapping to convert the .apk files into an image with as many file features as possible and subsequently put it into a deep learning network for training.…”