Enhanced concrete crack detection using YOLOv8: a multi-background approach

Degradation of concrete and steel reinforcement due to corrosion is a worldwide issue that deteriorates the durability and integrity of concrete structures. Even though nowadays precast concrete has been used widely to replace conventional concrete structures, the joints between the precast concrete elements are also prone to corrosion due to the different concrete interfaces. The difference between precast element and cast in-situ concrete is a weak point that creates a pathway to the penetration of corrosive agents. These interface differences can lead to differential movement and stress concentrations, eventually developing a minor crack that allows the ingress of corrosive agents. The void and micro-cracks that may exist during the construction process exacerbate the corrosion process. Once the steel reinforcement starts corroding, it creates expensive stress within the concrete joints. When this stress exceeds the stress capacity of the concrete, cracks are developed, leading to spalling and delamination. The precast concrete joint weakness exposes it to the degradation of the physical properties of concrete and steel reinforcement, eventually affecting the durability and integrity of precast concrete structures. This paper gives a brief review of the corrosion effect on the physical properties of materials at precast concrete joints and encourages other researchers to explore further in this field.

The accurate detection and segmentation of concrete cracks are crucial for maintaining the integrity and safety of infrastructure. Traditional manual inspection methods are often constrained by background complexity and environmental noise, while deep learning models face challenges related to data dependency and poor generalization in complex scenarios. To address these issues, this paper proposes an enhanced transFissNet model that integrates a ResNet101 backbone with Transformer modules for self-attention and multi-scale feature extraction. The model improves the robustness of crack detection under varying lighting conditions and irregular crack morphologies. Experimental results on multiple benchmark datasets demonstrate that transFissNet achieves an accuracy of 96.8%, outperforming existing mainstream methods. The proposed approach provides a reliable and scalable solution for automated crack segmentation and contributes to the advancement of intelligent structural health monitoring.

Comparison of deep convolutional neural networks and edge detectors for image-based crack detection in concrete

Non-destructive testing

Recently, interest in automatic crack detection on concrete structure images for non-destructive inspection has been increasing. In general, there are various noises such as irregularly illuminated conditions, shading, blemishes and divots in the concrete images. These lead to difficulties for automatic crack detection. This paper presents two p re-processings in order to remove such noises for crack detection. First, slight variations like irregularly illuminated conditions and shading are removed from concrete images by the subtraction pre-processing with the smoothed image. Secondly, a line filter based on the Hessian matrix is used to emphasize line structures associated with cracks. Finally, thresholding processing is used to separate cracks from background. The performance of the proposed method is evaluated by ROC analysis with 50 real images. The experimental results show that the proposed method is effective for detecting cracks on noisy concrete images

Fatigue crack detection using smart sensor technologies

The detection of cracks in sleepers is important in ensuring safe operation of trains and the crack width is a key index in this process. The traditional YOLOv5 model can not achieve satisfactory detection results in the face of large changes in the scale of the target and interference of background information in the detection process. In this paper, a method to detect and measure the fine crack of sleeper based on improved YOLOv5 model of cascade fusion and edge fitting algorithm is proposed to solve these problems. An adaptive multi-scale feature fusion technique is proposed to achieve multi-scale feature fusion efficiently and solve the problem of large changes in the scale of the target. An improved method of feature recombination of attention mechanism is used to solve the interference problem of background information. On this basis, a method based on cascade fusion is proposed to fuse the above improvements and reconstruct the structure of the YOLOv5 model. Moreover, a fitting algorithm of the crack edge is proposed to realize the precise measurement of the maximum width of the fine crack on sleepers. Finally, the process of crack detection and width measurement of sleeper is developed and the performance of the method proposed in this paper is verified by experiments through self-made data sets. The experimental results show that the precision of crack detection is increased from 84.08% to 96.86%, and the recall is increased from 78.13% to 96.46%. The increases are 12.78% and 18.33% respectively. At the same time, the average detection time is reduced from 15.23 ms to 10.04 ms. The measurement accuracy of the maximum crack width is 0.05 mm.

ABSTRACTVital signs are crucial indicators of an individual's physiological well‐being and represent one of the primary evaluations conducted in clinical and hospital environments. A comprehensive evaluation of a patient's health state depends on these signs which include heart rate (HR), respiratory rate (RR), blood oxygen saturation (SpO2), blood pressure (BP) and body temperature (BT). In recent years, there has been significant interest in using imaging photoplethysmography (iPPG) with consumer‐level cameras for contactless health monitoring (CHM) to accurately assess vital signs. The introduction of iPPG in CHM signifies the beginning of a remarkable era in the history of healthcare, whereby diagnostic processes are enhanced via the integration of technology and patient well‐being. This review article presents a comprehensive examination of CHM techniques utilising machine learning (ML) and deep learning (DL) algorithms for the assessment of critical vital signs. The article addresses the challenges and research gaps identified in recent studies, particularly those related to variations in lighting conditions, head movements and the impact of different colour types on the accuracy and reliability of CHM techniques. Finally, we propose several recommendations aimed to enhance the efficiency of CHM systems. These include the development of more robust learning algorithms and the creation of diverse datasets that encompass a wide range of demographics including variations in gender, skin colour and lighting conditions.

Detection and assessment of cracks in civil engineering structures such as roads, bridges, dams and pipelines are crucial tasks for maintaining the safety and cost-effectiveness of those concrete structures. With the recent advances in machine learning, the development of ANN- and CNN-based algorithms has become a popular approach for the automated detection and identification of concrete cracks. However, most of the proposed models are trained on images taken in ideal conditions and are only capable of achieving high accuracy when applied to the concrete images devoid of irregular illumination conditions, shadows, shading, blemishes, etc. An overview of challenges related to the automatic detection of concrete cracks in the presence of shadows is presented in this paper. In particular, difficulties associated with the application of deep learning-based methods for the classification of concrete images with shadows are demonstrated. Moreover, the limitations of the shadow removal techniques for the improvement of the crack detection accuracy are discussed.

Crack detection in structures is an important and time-consuming element of monitoring the health of structures and ensuring structural safety. The traditional visual inspection of structures can be unsafe and may produce inconsistent results. Thus, there is a need for a method to easily and accurately identify and analyze cracks. In this study, algorithms for automatically detecting the size and location of cracks in concrete images were developed. Cracks were automatically detected in a total of 10 steps. In steps 5 and 9, two user algorithms were added to increase crack detection accuracy, where 1000 crack images and 1000 non-crack images were used, respectively. In the crack image, 100% of the cracks were detected, but 95.3% of the results were very good, even if the results that were not bad in terms of quality were excluded. In addition, the accuracy of detecting non-crack images was also very good (96.9%). Thus, it is expected that the crack detection algorithm presented in this study will be able to detect the location and size of cracks in concrete. Moreover, these algorithms will help in observing the soundness of structures and ensuring their safety.

The collapse of structures in urban areas is a growing concern that demands effective and reliable methods for assessing structural integrity. The urban landscape of Lagos Island, boasts a diverse array of buildings, but many face structural distress due to factors like age, environmental conditions, poor construction practices, posing risks to occupants and the community. This research assessed the effectiveness of various Non-Destructive Testing (NDT) techniques using Schmidt/Rebound Hammer test and Ultrasonic Pulse Velocity Testing to evaluate the structural integrity of Ten (10) distressed buildings on Lagos Island, taking into account local environmental conditions and construction practices. The outcome of this research shows that the Rebound Hammer and Pulse Velocity tests provides a comprehensive understanding of the material’s properties and quality. Likewise, the comparative analysis of the Rebound Hammer and Pulse Velocity tests shows that both methods offer valuable insights into the quality and integrity of concrete structures with the Pulse Velocity test showing a slightly higher consistency in results. The Rebound Hammer method readings were averagely higher by 5N/m² to Pulse Velocity test readings. Therefore, Pulse Velocity test is more consistence, detects internal structural defects like cracks, voids and honeycombs homogeneity than Rebound Hammer method.

Monitoring Jackson Pratt and Hemovac drains plays a crucial role in assessing a patient's recovery and identifying potential postoperative complications. Accurate and regular monitoring of the blood volume in the drain is essential for making decisions about patient care. However, transferring blood to a measuring cup and recording it is a challenging task for both patients and doctors, exposing them to bloodborne pathogens such as the human immunodeficiency virus (HIV), hepatitis B virus (HBV), and hepatitis C virus (HCV). To automate the recording process with a non-contact approach, we propose an innovative approach that utilizes deep learning techniques to detect a drain in a photograph, compute the blood level in the drain, estimate the blood volume, and display the results on both web and mobile interfaces. Our system employs semantic segmentation on images taken with mobile phones to effectively isolate the blood-filled portion of the drain from the rest of the image and compute the blood volume. These results are then sent to mobile and web applications for convenient access. To validate the accuracy and effectiveness of our system, we collected the Drain Dataset, which consists of 1,004 images taken under various background and lighting conditions. With an average error rate of less than 5% in milliliters, our proposed approach achieves highly accurate blood level detection and estimation, as demonstrated by our trials on this dataset. The system also exhibits robustness to variations in lighting conditions and drain shapes, ensuring its applicability in different clinical scenarios. The proposed automated blood volume estimation system can significantly reduce the time and effort required for manual measurements, enabling healthcare professionals to focus on other critical tasks. The dataset and annotations are available at: https://www.kaggle.com/datasets/ayenahin/liquid-volume-detection-from-drain-images and the code for the web application is available at https://github.com/itsjustaplant/AwesomeProject.git.

SUT-Crack: A comprehensive dataset for pavement crack detection across all methods

Variation in lighting conditions is a major cause of performance degradation in pattern recognition when using optical imaging. In this study, infrared (IR) and depth images were considered as possible robust alternatives against variations in illumination, particularly for improving the performance of automatic lip-reading. The variations due to lighting conditions were quantitatively analyzed for optical, IR, and depth images. Then, deep neural network (DNN)-based lip-reading rules were built for each image modality. Speech recognition techniques based on IR or depth imaging required an additional light source that emitted light in the IR range, along with a special camera. To mitigate this problem, we propose a method that does not use an IR/depth image directly, but instead estimates images based on the optical RGB image. To this end, a modified U-net was adopted to estimate the IR/depth image from an optical RGB image. The results show that the IR and depth images were rarely affected by the lighting conditions. The recognition rates for the optical, IR, and depth images were 48.29%, 95.76%, and 92.34%, respectively, under various lighting conditions. Using the estimated IR and depth images, the recognition rates were 89.35% and 80.42%, respectively. This was significantly higher than for the optical RGB images.

Recent advances in autonomy and robotics have moti-vated a renewed interest in performing rendezvous and other mission-critical maneuvers autonomously with robotic space-craft. A key enabler for all autonomous proximity operations is knowledge of the relative state of one spacecraft with respect to the other. There are a variety of sensing approaches available for estimating this relative state, including visible-spectrum cam-eras, LiDAR devices, or a combination of the two. For on-orbit proximity operations using vision-based sensing, a particular challenge is the variability of lighting conditions caused by shad-ows cast by the target spacecraft or eclipses caused by planetary bodies. A complete position and velocity state estimate of the target spacecraft may not be attainable during cases of high temporal lighting variability or a lighting environment which exceeds the dynamic range of the vision-based sensor. This work focuses on low-cost vision-based sensing systems and com-puter vision algorithms for enabling target spacecraft velocity state estimation in challenging lighting conditions. A hardware demonstration of velocity state estimation in variable lighting conditions was conducted using a Raspberry Pi camera, stepper and DC motors, and a planar grid of optical fiducial markers created using the Aruco Python OpenCV library. Performance characterizations of camera pose estimation and marker iden-tification for single axis rotation in variable lighting conditions were conducted to establish baselines for noise and marker iden-tification limitations. Variable intensity LED panel light were used to control the lighting conditions ranging from 100Lm to 1, 000Lm. Pose estimate measurement noise was observed to be inversely related to lighting intensity. Specifically, maximum 1σ noise figures for the 100Lm and 1,000Lm test cases were measured to be ±0.080° and ±0.034 respectively demonstrating a degradation in pose estimation accuracy in low light conditions. Additionally, the performance of the computer vision-based Aruco marker detection algorithm was shown to degrade for images with significant amounts of motion blur. To address this limitation, long exposure test cases are conducted to charac-terize the performance of a computer vision-based velocity state estimation algorithm developed under the assumption of single axis relative rotation between the target and chaser satellite. Using a 0.33 second exposure time for the Raspberry Pi camera and rotation rates about the camera boresight axis of 6° /s to 20° /s, images of Aruco markers with varying degrees of motion blur were collected. The velocity state estimation algorithm developed as part of this work produced estimates within 5° /s of the true rotation rate as measured by incremental encoders mounted on the stepper motors. These results demonstrate the ability of the developed algorithm to produce accurate velocity estimates for single axis relative rotation in variable lighting conditions. This work's significance is the extension of vision-based velocity state estimation in challenging lighting conditions analogous to those encountered on-orbit which render current methods unusable.