Concrete Surface Images Research Articles

Concrete Spalling Severity Classification Using Image Texture Analysis and a Novel Jellyfish Search Optimized Machine Learning Approach

During the phase of building survey, spalling and its severity should be detected as earlier as possible to provide timely information on structural heath to building maintenance agency. Correct detection of spall severity can significantly help decision makers develop effective maintenance schedule and prioritize their financial resources better. This study aims at developing a computer vision-based method for automatic classification of concrete spalling severity. Based on input image of concrete surface, the method is capable of distinguishing between a minor spalling in which the depth of the broken-off material is less than the concrete cover layer and a deep spalling in which the reinforcing steel bars have been revealed. To characterize concrete surface condition, image texture descriptors of statistical measurement of color channels, gray-level run length, and center-symmetric local binary pattern are used. Based on these texture-based features, the support vector machine classifier optimized by the jellyfish search metaheuristic is put forward to construct a decision boundary that partitions the input data into two classes of shallow spalling and deep spalling. A dataset consisting of 300 image samples has been collected to train and verify the proposed computer vision method. Experimental results supported by the Wilcoxon signed-rank test point out that the newly developed method is highly suitable for concrete spall severity classification with accuracy rate = 93.33%, F1 score = 0.93, and area under the receiver operating characteristic curve = 0.97.

Automated image segmentation of air voids in hardened concrete surface using photometric stereo method

ABSTRACT The accumulative freeze-thaw cycles in cold regions could cause deteriorations to concrete pavements. The measurement of air-void system inside hardened concrete is important for estimating the freeze-thawing performance of a concrete pavement. The segmentation of air voids from the concrete surface image is one of the most essential and challenging steps for automated air-void measurement. Conventional automated air-voids segmentation methods rely on a color enhancement step to manually create a contrast between air voids and non-air-voids. This study aims to investigate the use of a photometric stereo method for automated segmentation of air voids in hardened concrete surface without a need for contrast enhancement. In the study, the photometric stereo system with a Charge-Coupled Device (CCD) camera and six illumination lights was designed to collect images of polished concrete specimen surfaces under various lighting directions. Two air-void segmentation approaches were developed in the study. One approach interpreted the air voids by the surface depth. The other approach interpreted the air voids by the surface normal. Consequently, the segmentation results were refined by a set of image processing procedures. The results showed that the proposed automated air-void segmentation procedures could detect air voids in concrete surface with a satisfactory accuracy.

A Hybrid Image Enhancement Algorithm for Effective Concrete Surface Crack Classification

Huge number of images are acquired and analysed every day for a range of applications in civil infrastructure. One such application is the identification of cracks in concrete surface images, which is a challenge owing to their low contrast and resolution, blurriness, noise and information loss. Existing image enhancement algorithms improve either contrast or resolution to a rather limited extent. This paper proposes a Hybrid Image Enhancement (HIE) algorithm to improve both the contrast and resolution of concrete surface images using the Wavelet transform and Singular Value Decomposition (SVM). The enhanced concrete surface crack images are classified into specific crack types. The classification comprises preprocessing, crack detection, feature extraction and crack classification. The images are initially preprocessed using the Wiener filter to remove blurriness, following which cracks are detected using morphological operations and discontinuities in the segmented crack regions eliminated using the K-Dimensional Tree algorithm. Features are extracted from the segmented regions using statistical and geometric features. The image is classified thereafter into specific crack types using algorithms from three different neural network, kernel and tree based categories. The proposed HIE algorithm is validated using quantitative metrics and the results obtained are compared with those from State-of-the-Art methods and datasets. The results have shown that the HIE algorithm offers significantly improved accuracy of between 6% and 10% in the classification of concrete surface images.

Development of Deep Learning Model for the Recognition of Cracks on Concrete Surfaces

This paper is devoted to the development of a deep learning- (DL-) based model to detect crack fractures on concrete surfaces. The developed model for the classification of images was based on a DL Convolutional Neural Network (CNN). To train and validate the CNN model, a database containing 40,000 images of concrete surfaces (with and without cracks) was collected from the available literature. Several conditions on the concrete surfaces were taken into account such as illumination and surface finish (i.e., exposed, plastering, and paint). Various error measurement criteria such as accuracy, precision, recall, specificity, and F1-score were employed for accessing the quality of the developed model. Results showed that for the training dataset (50% of the database), the precision, recall, specificity, F1-score, and accuracy were 99.5%, 99.8%, 99.5%, 99.7%, and 99.7%, respectively. On the other hand, for the validating dataset, the precision, recall, specificity, F1-score, and accuracy are 96.5%, 98.8%, 96.6%, 97.7%, and 97.7%, respectively. Thus, the developed CNN model may be considered valid because it performs the classification of cracks well using the testing data. It is also confirmed that the developed DL-based model was robust and efficient, as it can take into account different conditions on the concrete surfaces. The CNN model developed in this study was compared with other works in the literature, showing that the CNN model could improve the accuracy of image classification, in comparison with previously published results. Finally, in further work, such model could be combined with Unmanned Aerial Vehicles (UAVs) to increase the productivity of concrete infrastructure inspection.

Automated bughole detection and quality performance assessment of concrete using image processing and deep convolutional neural networks

Concrete is ubiquitous in the modern construction and building industry, bugholes are one of the most typical imperfections on concrete surface, and traditional manual inspection techniques are inefficient and difficult to rapidly deploy. With the development of image processing and deep learning techniques, new opportunities and possible solutions are available for bughole detection. This paper not only dedicates to propose a novel approach to automatically extract bugholes in the concrete surface images with high fidelity by combining the advantages of image processing and deep convolutional neural network (DCNN), but also attempts to assess the quality performance of concrete based on the detection results. Firstly, a series of image processing procedures were performed to highlight the characteristics of bugholes in the acquired images and reduce the data size. Secondly, a DCNN was proposed to automatically detect bugholes in the images, an inception module consisting of multiple convolutions and a max pooling operation was introduced into the network to efficiently extract multiscale features and reduce the model parameters. Favorable detection results were obtained in the experimental tests, especially the small bugholes (i.e., diameter ranging from 0.3 mm to 1 mm) can be accurately detected. Finally, the quality performance of concrete specimens was assessed based on the detection results, the potential relationship between the attributes of bugholes and compressive strength of concrete specimens was revealed through a fitting function. The proposed method makes both the detection of bugholes and assessment of concrete automatable, efficient, and low cost, potentially aiding engineers in inspecting concrete structures in a fast and reliable manner.

Variable Selection from Image Texture Feature for Automatic Classification of Concrete Surface Voids.

Machine learning plays an important role in computational intelligence and has been widely used in many engineering fields. Surface voids or bugholes frequently appearing on concrete surface after the casting process make the corresponding manual inspection time consuming, costly, labor intensive, and inconsistent. In order to make a better inspection of the concrete surface, automatic classification of concrete bugholes is needed. In this paper, a variable selection strategy is proposed for pursuing feature interpretability, together with an automatic ensemble classification designed for getting a better accuracy of the bughole classification. A texture feature deriving from the Gabor filter and gray-level run lengths is extracted in concrete surface images. Interpretable variables, which are also the components of the feature, are selected according to a presented cumulative voting strategy. An ensemble classifier with its base classifier automatically assigned is provided to detect whether a surface void exists in an image or not. Experimental results on 1000 image samples indicate the effectiveness of our method with a comparable prediction accuracy and model explicable.

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

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 up sampling. 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.

Real-time monitoring for vibration quality of fresh concrete using convolutional neural networks and IoT technology

Vibration quality is critical to ensure the concrete strength, which directly affects the long-term safe operation of concrete structures. The vibration duration and vibration depth are key parameters to guarantee vibration quality. However, traditional manual inspection on concrete surface to judge the vibration duration and estimation of vibration depth is subjective and unreliable. Moreover, existing studies monitor the vibration duration based on the knowledge from prior experiments, ignoring the influence of concrete heterogeneity. Thus, a real-time monitoring method for vibration quality of fresh concrete based on ResNet with 50 layers (ResNet-50) and Internet of Things (IoT) technology is proposed. The IoT-based monitoring framework is proposed to measure vibration depth and capture concrete surface image (CSI). A three-category classification model of CSI is established based on fine-tuned ResNet-50 model using a self-constructed dataset with 15,006 images to determine proper vibration duration. A large-scale hydraulic engineering application verifies the performance of the proposed method.

Automated crack segmentation via saturation channel thresholding, area classification and fusion of modified level set segmentation with Canny edge detection

Automatic detection of complex cracks on rough concrete surfaces via image processing is a challenging task. The most current effective methods involve deep learning schemes. These are usually computationally and structurally complex. Recently, relatively simplified algorithms were developed for effective segmentation of crack features. However, these approaches still could not consistently and accurately extract such features from extremely noisy images of rough concrete surfaces with complex crack patterns. This study describes crack feature segmentation algorithms based on wavelet coefficient adjustment, nonlinear filter pre-processing, saturation channel extraction, adaptive threshold-based edge detection and fuzzy clustering-based area classification. Additional modifications include a new energy function for active contour segmentation algorithm. Adaptive localized mask generation is also proposed for automatic region-based segmentation. Furthermore, a binary fusion stage is incorporated for improved edge feature extraction. The quantitative and visual evaluation of the proposed schemes show improvement in results compared to several recent state-of-the-art algorithms.

Crack Detection from a Concrete Surface Image Based on Semantic Segmentation Using Deep Learning

Crack Detection from a Concrete Surface Image Based on Semantic Segmentation Using Deep Learning

Automatic bridge crack identification from concrete surface using ResNeXt with postprocessing

In this study, the bridge concrete structure is taken as the research object, and the real image is used for crack identification. In structural engineering, surface cracks are the main indexes of durability and service performance of structures. Artificial visual inspection is often considered ineffective in terms of cost, safety, evaluation accuracy, and reliability. In this article, a simple, high-classification framework based on ResNeXt with postprocessing (ResNeXt+PP) model is provided to effectively identify concrete cracks. During the training phase of the method, image binarization approach is used to extract the candidate crack regions. It is difficult to automatic identify cracks from images containing actual cracks and noises, especially, shadows, stains, masses, and holesoften occur in concrete surfaces. Thereafter, classification models are constructed based on ResNeXt+PP module. Based on the new concrete surface images including cracks and noncracks, the obtained methods for crack identification are compared quantitatively and qualitatively. Besides, the five complete raw images are used to study the robustness and practicability of the method. The binary transformation process based on a binarization method of adaptive crack width is adopted to identify crack pixels in subimages. Results show that the trained improved ResNeXt+PP can automatically detect cracks and noncracks in the raw image. The obtained results that the method is superior to multiple methods and the application prospect of autonomous concrete structure driver for bridge detection robot are presented.

Enhanced Intelligent Identification of Concrete Cracks Using Multi-Layered Image Preprocessing-Aided Convolutional Neural Networks.

Crack identification plays an essential role in the health diagnosis of various concrete structures. Among different intelligent algorithms, the convolutional neural networks (CNNs) has been demonstrated as a promising tool capable of efficiently identifying the existence and evolution of concrete cracks by adaptively recognizing crack features from a large amount of concrete surface images. However, the accuracy as well as the versatility of conventional CNNs in crack identification is largely limited, due to the influence of noise contained in the background of the concrete surface images. The noise originates from highly diverse sources, such as light spots, blurs, surface roughness/wear/stains. With the aim of enhancing the accuracy, noise immunity, and versatility of CNN-based crack identification methods, a framework of enhanced intelligent identification of concrete cracks is established in this study, based on a hybrid utilization of conventional CNNs with a multi-layered image preprocessing strategy (MLP), of which the key components are homomorphic filtering and the Otsu thresholding method. Relying on the comparison and fine-tuning of classic CNN structures, networks for detection of crack position and identification of crack type are built, trained, and tested, based on a dataset composed of a large number of concrete crack images. The effectiveness and efficiency of the proposed framework involving the MLP and the CNN in crack identification are examined by comparative studies, with and without the implementation of the MLP strategy. Crack identification accuracy subject to different sources and levels of noise influence is investigated.

Automatic Crack Detection for Concrete Infrastructures Using Image Processing and Deep Learning

Automatic crack detection is a main task in a crack map generation of the existing concrete infrastructure inspection. This paper presents an automatic crack detection and classification method based on genetic algorithm (GA) to optimize the parameters of image processing techniques (IPTs). The crack detection results of concrete infrastructure surface images under various complex photometric conditions still remain noise pixels. Next, a deep convolution neural network (CNN) method is applied to classify crack candidates and non-crack candidates automatically. Moreover, the proposed method is compared with the state-of-the-art methods for crack detection. The experimental results validate the reasonable accuracy in practical application.

Automatic crack distress classification from concrete surface images using a novel deep-width network architecture

The condition monitoring of concrete surface plays a significant role in civil infrastructure management system. Crack is the main threat to concrete surface of buildings, bridges, roads and pavements. This issue has been researched for several decades, however, it is still a challenge to classify crack since there are many inferior factors, e.g., intense inhomogeneity, structure complexity and background noise of concrete surface. In this paper, a novel deep-width network (DWN) architecture is used for binary and multi-label concrete surface crack classification without handcraft feature extraction. It intelligently learns cracking structures from input raw images by linear and nonlinear mapping process, flexible dynamically updates new weights and efficiently constructs the network by adding new incremental samples. The presented crack distress classification method is tested on two concrete surface crack image datasets and compared with many popular classification methods like sparse autoencoder (SAE), convolution neural network (CNN), and broad learn system (BLS). Experimental results demonstrate that it obviously outperforms those methods both in accuracy and efficiency.

The Algorithm of Concrete Surface Crack Detection Based on the Genetic Programming and Percolation Model

Because of the impact of the variation in different concrete surface images, such as the heterogeneity of the detection environment, uneven illumination, stains, the block, and water leakage, the existing crack detection algorithms cannot detect the real crack quickly and effectively. In this paper, a genetic algorithm based on genetic programming (GP) and percolation model is proposed. This method involves three steps. First, the cracks are pre-extracted by the image processing model of GP. Second, the crack tip is calculated after the crack skeleton is extracted. With the endpoint as the anchor point, high speed, and high precision percolation are used to detect the cracks with small width accurately. Concurrently, the fracture unit areas are scanned for connection. Finally, the pre-extracted cracks are connected with the cracks detected by the percolation, and the mass interference area is removed to obtain the real cracks on the concrete surface. The simulation results show that the concrete surface crack detection algorithm based on the GP and percolation model can effectively combine both of their advantages. The algorithm proposed in this paper can detect real concrete surface cracks accurately and effectively with strong robustness.

Deep‐Learning‐Based Bughole Detection for Concrete Surface Image

Bugholes are surface imperfections that appear as small pits and craters on concrete surface after the casting process. The traditional measurement methods are carried out by in situ manual inspection, and the detection process is time‐consuming and difficult. This paper proposed a deep‐learning‐based method to detect bugholes on concrete surface images. A deep convolutional neural network for detecting bugholes on concrete surfaces was developed, by adding the inception modules into the traditional convolution network structure to solve the problem of the relatively small size of input image (28 × 28 pixels) and the limited number of labeled examples in training set (less than 10 K). The effects of noise such as illumination, shadows, and combinations of several different surface imperfections in real‐world environments were considered. From the results of image test, the proposed DCNN had an excellent bughole detection performance and the recognition accuracy reached 96.43%. By the comparative study with the Laplacian of Gaussian (LoG) algorithm and the Otsu method, the proposed DCNN had good robustness which can avoid the interference of cracks, color‐differences, and nonuniform illumination on the concrete surface.

High performance green concrete (HPGC) with improved strength and chloride ion penetration resistance by synergistic action of fly ash, nanoparticles and corrosion inhibitor

This work reports a novel high performance green concrete fabricated by incorporating fly ash, nanoparticles and corrosion inhibiting admixture into conventional M45 grade concrete. The optimal composition of the new mix was found to be 40 wt% fly ash, 2 wt% nano-TiO2 and nano-CaCO3 in 1:1 ratio, 2 wt% sodium nitrite based corrosion inhibitor and 56% Ordinary Portland Cement, referred hereafter as CFNI. The properties of CFNI were compared with that of conventional concrete to assess the synergistic role of various additives. Field Emission Scanning Electron Microscope images of CFNI showed a homogeneous distribution of hydration products over the surface. The Confocal Laser Scanning Microscopy images of concrete surfaces and pore size estimation from Mercury Ion Porosimetry confirmed that only gel pores at the nanoscale are present in the CFNI specimens. The compressive strength, flexural strength and split tensile strength of CFNI, measured as per ASTM/Indian standards, showed noticeable enhancement. The chloride ion penetration resistance, carbonation, water permeability and water sorptivity of CFNI was found to be superior as compared to conventional concrete. This study establishes that synergistic action of fly ash, nanoparticles and inhibitor facilitated the improvement in strength and durability of the new green concrete CFNI, which is very promising not only for cost reduction and improved properties of concrete structures, but also reduces energy consumption and green house gas emissions.

A methodology framework for retrieval of concrete surface crack′s image properties based on hybrid model

Regular concrete surface crack inspection is critical since cracks are one of the earliest signs of deteriorating in concrete structures. With recent digital imaging and processing techniques, computer vision-based inspection shows huge potential in this field. A novel image processing framework for automatically retrieving multiple crack properties from concrete surface images is proposed. The framework includes (1) a crack extraction algorithm which combines edge detecting and seed growing; (2) a skeleton optimizing method which contains short branch deleting and polyline approximation algorithm; (3) a hybrid crack model which classifies crack segments into disc-shaped and bar-shaped parts based on their skeleton topological information, and (4) a triad labelling method that indicates the interrelationships between different cracks. Contrast experiments showed that the proposed segmentation method can extract more complete crack segments. Real image experiments indicated that the framework is effective and helpful for subsequent concrete structure health assessment.

Pixel-Wise Crack Detection Using Deep Local Pattern Predictor for Robot Application.

Robotic vision-based crack detection in concrete bridges is an essential task to preserve these assets and their safety. The conventional human visual inspection method is time consuming and cost inefficient. In this paper, we propose a robust algorithm to detect cracks in a pixel-wise manner from real concrete surface images. In practice, crack detection remains challenging in the following aspects: (1) detection performance is disturbed by noises and clutters of environment; and (2) the requirement of high pixel-wise accuracy is difficult to obtain. To address these limitations, three steps are considered in the proposed scheme. First, a local pattern predictor (LPP) is constructed using convolutional neural networks (CNN), which can extract discriminative features of images. Second, each pixel is efficiently classified into crack categories or non-crack categories by LPP, using as context a patch centered on the pixel. Lastly, the output of CNN—i.e., confidence map—is post-processed to obtain the crack areas. We evaluate the proposed algorithm on samples captured from several concrete bridges. The experimental results demonstrate the good performance of the proposed method.

Development of an Automatic Crack Inspection System for Concrete Tunnel Lining Based on Computer Vision Technologies

This paper presents an automatic crack inspection system for concrete tunnel lining based on image processing technique and computer vision. The system includes a video image acquisition device, an image stitching software, and a crack detection software. Firstly, the video image acquisition device uses six video cameras and three illuminators mounted on a steel framework which is capable of sliding from side to top of the inspecting vehicle to shoot the full surface of the tunnel lining. Secondly, the image stitching software based on image matching technique was developed to create layout panorama from the tunnel lining surface images, making it easier to visualize a large and detailed section of the tunnel lining. Finally, we propose a semi-automatic crack detection software relied on a combination of image processing technique and interactive genetic algorithm (iGA) to crack detection for concrete surface images of the tunnel lining. Experimental results demonstrate the effectiveness of the proposed method.