Automatic surface crack detection using segmentation-based deep-learning approach

In the present study, an integrated framework for automatic detection, segmentation, and measurement of road surface cracks is proposed. First, road images are captured, and crack regions are detected based on the fifth version of the You Only Look Once (YOLOv5) algorithm; then, a modified Residual Unity Networking (Res-UNet) algorithm is proposed for accurate segmentation at the pixel level within the crack regions; finally, a novel crack surface feature quantification algorithm is developed to determine the pixels of crack in width and length, respectively. In addition, a road crack dataset containing complex environmental noise is produced. Different shooting distances, angles, and lighting conditions are considered. Validated through the same dataset and compared with You Only Look at CoefficienTs ++ (YOLACT++) and DeepLabv3+, the proposed method shows higher accuracy for crack segmentation under complex backgrounds. Specifically, the crack damage detection based on the YOLOv5 method achieves a mean average precision of 91%; the modified Res-UNet achieves 87% intersection over union (IoU) when segmenting crack pixels, 6.7% higher than the original Res-UNet; and the developed crack surface feature algorithm has an accuracy of 95% in identifying the crack length and a root mean square error of 2.1 pixels in identifying the crack width, with the accuracy being 3% higher in length measurement than that of the traditional method.

A new fibreoptic reflectometric technique for the automatic detection and measurement of surface cracks is proposed, described and analysed. A relationship between the system output image and the surface crack distribution is obtained from theory and a crack measurement principle is derived. Analysis of the experimental data obtained using a first laboratory prototype has validated the proposed measurement principle. The results of a second generation prototype confirm that the technique promises to be a valuable tool in practical inspection tasks.

Cracks are the result of excessive internal stress released by concrete materials. Cracks reduce the peak stress of the section. Therefore, the deformation energy stored in the structure is lower than a certain limit. Reducing the internal deformation energy by cracking is the inherent characteristic of concrete materials. Many concrete structures will have different degrees and forms of cracks, which is a quite common phenomenon. Cracks have become a common disease of concrete structures, which has long been a technical problem for construction engineers. Traditional crack detection methods of concrete bridges can not meet the needs of modern bridge detection. Based on this, this paper presents a long-distance non-contact surface defect and crack detection system, which is an economical and effective new method for bridge disease detection. This paper analyses the working principle and workflow of the detection system.

The task of bridge inspection is currently carried out by humans, which is time-consuming, costly, and high-risk. There is an urgent need to develop an autonomous system to inspect bridges. Several different approaches have been proposed — Unmanned Aerial Vehicles (drones), and magnetic tracked vehicles — and these solutions lack autonomous driving capabilities. Furthermore, past software solutions, including machine learning, are non real-time solutions and are also limited to locating damage in a single image. This research designs and implements AutoBot: the first integrated, autonomous, wire-ringed, column-climbing robotic system capable of real-time mapping for automatic surface crack detection. Real-time mapping techniques were developed by a combination of two components: YOLO, a single-stage object detection algorithm, and a 3D mapping technique, capable of converting identified cracks into 3D coordinates. Driving was achieved by bang-bang and Proportional Integral (PI) controllers. After tuning on a bridge column model, AutoBot was applied for real-world concrete bridge inspection. The results showed AutoBot successfully climbed a column 1.33 meters in diameter and 5 meters tall at a speed of 4.7 cm/s, completing one cycle of action, climbing and mapping a single meter, in 22 seconds. The detection obtained a mean average precision of 82.6%. Compared to other YOLO algorithms that use the same image test size, AutoBot’s YOLO algorithm had the highest precision, recall, and mean average precision. AutoBot is the first successful demonstration of an autonomous, real-time system capable of inspecting bridges.

Crack detection has always been a dominant requirement for steel industries to ensure quality production and seamless infrastructure maintenance. However, application complexities and defect morphological differences make existing approaches confined. Steel-strip surface often undergoes scratch, crack and fatigue conditions during production. Manual crack detection schemes are no longer effective in current day complex environment. Amongst major steel strip crack detection approaches vision based techniques have been found potential. Filamentous crack which is caused due to fatigue or strain is fine-grained and thin and hence highly difficult to be detected by classical morphology and static threshold based schemes. In the present work steel strip surface crack(filamentous) detection system is developed which employs Varying-Morphological Segmentation (VMS) also called Neuron-Model Segmentation (NMS) in conjunction with local directive filtering and active contour propagation. The proposed method can be stated as an augmented variational framework that employs multi-directional filters for local crack-region identification followed by automated multi-directional region growing and iterative contour evolution which performs level set energy minimization to achieve accurate crack detection even under topological non-linearity and varying illumination conditions .Simulation results with standard benchmark data has confirmed that the proposed method exhibits satisfactory performance for steel strip surface cracks.

Micro-scale cracks on the surface of a magnetic rotor are difficult to detect because of the formation of stains. A method that is based on computer vision and a support vector machine (SVM) that can accurately and rapidly locate micro-scale cracks are proposed. To further highlight the cracks and reduce interference, the image is pre-processed using improved adaptive median filtering, image sharpening, extract feature point, and an expansion based on mathematical morphology. Next, the feature curves of cracks and stains are extracted as training samples using the feature curve extract algorithm and the region orientation algorithm (ROA) for continuous and discontinuous crack curves images, respectively. SVM is later used to distinguish between the two types of image sources. An improved region orientation algorithm (IROA) is proposed to increase the efficiency of discontinuous crack curves images through online detection. Experiment results show that the accuracy of crack detection using ROA is 97.9%, and the accuracy is 94.7% using IROA. However, the IROA algorithm execution time is 3% that of ROA, and IROA's average crack detection time is shorter than that of ROA by 51%. The proposed method provides the basis for the automatic online detection of micro-scale cracks on a magnetic rotor surface and paves the way for the identification of cracks on complex morphologies, such as split cracks and circular cracks.

Automatic concrete cracks detection and mapping of terrestrial laser scan data

Crack detection is essential for guaranteeing airport runway structural reliability. An efficient solution we take is to employ a robot equipped with a camera to perform inspection task. However, automatic crack detection for airport runway is challenging, as the runway surface is seriously polluted by fuel stain and aircraft wheel mark, and the cracks need to be detected luare usually extremely thin. Thus, we propose a CNN model, AggCrack, to perform the crack detection task. AggCrack adopts an innovative semantic-level attention mechanism on the edges of the targets to focus the model on crucial features, and combines edge information and semantic segmentation for more accurate crack detection. We have implemented the algorithm and have it extensively tested on an airport runway dataset collected by our inspection robot from four different airport runways. Compared with four existing deep learning methods, experimental results show that our algorithm outperforms all counterparts. Specifically, it achieves the Precision, Recall and F1-measure at 84.24%, 70.36% and 76.68%, respectively.

Recently, the construction industry has benefited from the increased application of smart construction led by the core technologies of the fourth industrial revolution, such as BIM, AI, modular construction, and AR/VR, which enhance productivity and work efficiency. In addition, the importance of “Off-Site Construction (OSC)”, a factory-based production method, is being highlighted as modular construction increases in the domestic construction market as a means of productivity enhancement. The problem with OSC construction is that the quality inspection of Precast Concrete (PC) members produced at the factory and brought to the construction site is not carried out accurately and systematically. Due to the shortage of quality inspection manpower, a lot of time and money is wasted on inspecting PC members on-site, compromising inspection efficiency and accuracy. In this study, the major inspection items to be checked during the quality inspection are classified based on the existing PC member quality inspection checklist and PC construction specifications. Based on the major inspection items, the items to which AI technology can be applied (for automatic quality inspection) were identified. Additionally, the research was conducted focusing on the detection of cracks, which are one of the major types of defects in PC members. However, accurate detection of cracks is difficult since the inspection mostly relies on a visual check coupled with subjective experience. To automate the detection of cracks for PC members, video images of cracks and non-cracks on the surface were collected and used for image training and recognition using Convolutional Neural Network (CNN) and object detection, one of the deep learning technologies commonly applied in the field of image object recognition. Detected cracks were classified according to set thresholds (crack width and length), and finally, an automated PC member crack detection system that enables automatic crack detection based on mobile and web servers using deep learning and imaging technologies was proposed. This study is expected to enable more accurate and efficient on-site PC member quality inspection. Through the smart PC member quality inspection system proposed in this study, the time required for each phase of the existing PC member quality inspection work was reduced. This led to a reduction of 13 min of total work time, thereby improving work efficiency and convenience. Since quality inspection information can be stored and managed in the system database, human errors can be reduced while managing the quality of OSC work systematically and accurately. It is expected that through optimizing and upgrading our proposed system, quality work for the precise construction of OSC projects can be ensured. At the same time, systematic and accurate quality management of OSC projects is achievable through inspection data. In addition, the smart quality inspection system is expected to establish a smart work environment that enables efficient and accurate quality inspection practices if applied to various construction activities other than the OSC projects.

Detection of surface cracks on slanted surfaces and through thick irregular insulation layers using polarimetric microwave imaging

Karayolu yüzeyindeki asfalt çatlakları en yaygın kaplama hasarlarından biridir. Bu çatlaklar zamanında tespit edilip bakıma alınmazsa büyüyerek trafik güvenliğini ve yoğunluğunu arttıracak boyutlara ulaşmaktadır. Bu nedenle, asfalt çatlaklarının tespitinin hızlı bir şekilde gerçekleştirilmesi çok önemlidir. Geleneksel manuel çatlak tespiti, son derece zaman alıcı, çok maliyetli ve çok çaba gerektirir. Bu nedenle, araştırmacılar odaklarını otomatik asfalt çatlaklarının tespitine yoğunlaştırdılar. Ancak, son yıllarda otomatik çatlak tespiti kapsamlı olarak araştırılmasına rağmen çatlakların farklı yoğunluğa sahip olması ve kaplama ortamının karmaşıklığı nedeniyle hala zor bir görevdir. Bu çalışmada, bu zorluğun üstesinden gelmek için konvolüsyon sinir ağı temelli bir yöntem önerildi. Önerilen yöntem, sınıflandırma ve segmentasyondaki başarısı ve hafifliği bilinen MobileNetv2 ’nin temelde kullandığı konvolüsyon ve ters artıklı blok yapılarını baz alarak geliştirildi. Yapılan deneysel testler sonucunda, önerilen yöntemin performansı literatürdeki diğer yöntemlere göre daha yüksek olduğu görülmektedir. Bu da, otomatik asfalt çatlak tespitinin daha başarılı olması anlamına gelmektedir.

Surface crack detection and temporal evolution analysis are fundamental tasks in remote sensing and photogrammetry, providing critical information for slope stability assessment, infrastructure safety inspection, and long-term geohazard monitoring. However, current unmanned aerial vehicle (UAV)-based crack detection pipelines typically treat spatial detection and temporal change analysis as separate processes, leading to weak geometric consistency across time and limiting the interpretability of crack evolution patterns. To overcome these limitations, we propose the Longitudinal Crack Fitting Network (LCFNet), a unified and physically interpretable framework that achieves, for the first time, integrated time-series crack detection and evolution analysis from UAV remote sensing imagery. At its core, the Longitudinal Crack Fitting Convolution (LCFConv) integrates Fourier-series decomposition with affine Lie group convolution, enabling anisotropic feature representation that preserves equivariance to translation, rotation, and scale. This design effectively captures the elongated and oscillatory morphology of surface cracks while suppressing background interference under complex aerial viewpoints. Beyond detection, a Lie-group-based Temporal Crack Change Detection (LTCCD) module is introduced to perform geometrically consistent matching between bi-temporal UAV images, guided by a partial differential equation (PDE) formulation that models the continuous propagation of surface fractures, providing a bridge between discrete perception and physical dynamics. Extensive experiments on the constructed UAV-Filiform Crack Dataset (10,588 remote sensing images) demonstrate that LCFNet surpasses advanced detection frameworks such as You only look once v12 (YOLOv12), RT-DETR, and RS-Mamba, achieving superior performance (mAP50:95 = 75.3%, F1 = 85.5%, and CDR = 85.6%) while maintaining real-time inference speed (88.9 FPS). Field deployment on a UAV–IoT monitoring platform further confirms the robustness of LCFNet in multi-temporal remote sensing applications, accurately identifying newly formed and extended cracks under varying illumination and terrain conditions. This work establishes the first end-to-end paradigm that unifies spatial crack detection and temporal evolution modeling in UAV remote sensing, bridging discrete deep learning inference with continuous physical dynamics. The proposed LCFNet provides both algorithmic robustness and physical interpretability, offering a new foundation for intelligent remote sensing-based structural health assessment and high-precision photogrammetric monitoring.

A novel approach of surface crack detection using super pixel segmentation

the detection technology of surface crack in building wall is studied to improve the accuracy of detection. To detect surface crack in the building wall, there will be a pixel overlap or distorted in the location of image connection if using traditional detection method to make fusion process for the different pixels. due to the accuracy requirements of image pixels in surface crack detection in building wall is relatively high, resulting in too low accuracy rate of surface crack detection in building wall. In order to avoid the above problem, a detection method for surface crack in building wall based on computer vision is proposed. The crack region’s pixel in the image of building wall’s surface is calculated, and thus to provide the basis for surface crack detection in building wall. According to the theory of computer vision, the spatial location of the surface crack region in building wall is obtained. Experiments show that this detection system can improve the accuracy of detection, and achieve satisfactory results.

Drilling riser is a critical component in offshore oil and gas industry. Due to the complicated alternating stress and corrosive environment, stress corrosion cracking (SCC) is the most common defect on drilling riser in service. A novel chain alternating current field measurement (ACFM) probe array is proposed to detect surface cracks on drilling riser. The finite element method (FEM) is presented for analyzing the characteristic signal of surface crack. The space between the U-shaped excitation yoke and the detecting sensor is determined by simulation. Based on the results of simulation, the chain ACFM probe with giant magneto resistance (GMR) sensor array system is set up, and the drilling riser surface crack detection experiment is carried out. The results show that the maximum spacing of U-shaped excitation yoke and sensor array is 80 mm and 10 mm respectively. Furthermore, the chain ACFM probe with GMR sensor array system can detect and locate the surface cracks on drilling riser rapidly and quantitatively with a single pass scanning.