An illustrative non-technical review was published on Towards Data Science regarding our recent Journal paper “Automatic crack classification and segmentation on masonry surfaces using convolutional neural networks and transfer learning”.While new technologies have changed almost every aspect of our lives, the construction field seems to be struggling to catch up. Currently, the structural condition of a building is still predominantly manually inspected. In simple terms, even nowadays when a structure needs to be inspected for any damage, an engineer will manually check all the surfaces and take a bunch of photos while keeping notes of the position of any cracks. Then a few more hours need to be spent at the office to sort all the photos and notes trying to make a meaningful report out of it. Apparently this a laborious, costly, and subjective process. On top of that, safety concerns arise since there are parts of structures with access restrictions and difficult to reach. To give you an example, the Golden Gate Bridge needs to be periodically inspected. In other words, up to very recently there would be specially trained people who would climb across this picturesque structure and check every inch of it.
LINK
Masonry structures represent the highest proportion of building stock worldwide. Currently, the structural condition of such structures is predominantly manually inspected which is a laborious, costly and subjective process. With developments in computer vision, there is an opportunity to use digital images to automate the visual inspection process. The aim of this study is to examine deep learning techniques for crack detection on images from masonry walls. A dataset with photos from masonry structures is produced containing complex backgrounds and various crack types and sizes. Different deep learning networks are considered and by leveraging the effect of transfer learning crack detection on masonry surfaces is performed on patch level with 95.3% accuracy and on pixel level with 79.6% F1 score. This is the first implementation of deep learning for pixel-level crack segmentation on masonry surfaces. Codes, data and networks relevant to the herein study are available in: github.com/dimitrisdais/crack_detection_CNN_masonry.
DOCUMENT
Manual crack inspection is labor-intensive and impractical at scale, prompting a shift toward AI-based segmentation methods. We present a novel crack segmentation model that leverages the Segment Anything Model 2 (SAM 2) through transfer learning to detect cracks on masonry surfaces. Unlike prior approaches that rely on encoders pretrained for image classification, we fine-tune SAM 2, originally trained for segmentation tasks, by freezing its Hiera encoder and FPN neck, while adapting its prompt encoder, LoRA matrices, and mask decoder for the crack segmentation task. No prompt input is used during training to avoid detection overhead. Our aim is to increase robustness to noise and enhance generalizability across different surface types. This work demonstrates the potential of foundational segmentation models in enabling more reliable and field-ready AI-based crack detection tools.
DOCUMENT
This paper outlines an investigation into the updating of fatigue reliability through inspection data by means of structural correlation. The proposed methodology is based on the random nature of fatigue fracture growth and the probability of damage detection and introduces a direct link between predicted crack size and inspection results. A distinct focus is applied on opportunities for utilizing inspection information for the updating of both inspected and uninspected (or uninspectable) locations.
DOCUMENT
In order to guarantee structural integrity of marine structures in an effective way, operators of these structures seek an affordable, simple and robust system for monitoring detected cracks. Such systems are not yet available and the authors took a challenge to research a possibility of developing such a system. The paper describes the initial research steps made. In the first place, this includes reviewing conventional and recent methods for sensing and monitoring fatigue cracks and discussing their applicability for marine structures. A special attention is given to the promising but still developing new sensing techniques. In the second place, wireless network systems are reviewed because they form an attractive component of the desired system. The authors conclude that it is feasible to develop the monitoring system for detected cracks in marine structures and elaborate on implications of availability of such a system on risk based inspections and structural health monitoring systems
DOCUMENT
Abstract: The key challenge of managing Floating Production Storage and Offloading assets (FPSOs) for offshore hydrocarbon production lies in maximizing the economic value and productivity, while minimizing the Total Cost of Ownership and operational risk. This is a comprehensive task, considering the increasing demands of performance contracting, (down)time reduction, safety and sustainability while coping with high levels of phenomenological complexity and relatively low product maturity due to the limited amount of units deployed in varying operating conditions. Presently, design, construction and operational practices are largely influenced by high-cycle fatigue as a primary degradation parameter. Empirical (inspection) practices are deployed as the key instrument to identify and mitigate system anomalies and unanticipated defects, inherently a reactive measure. This paper describes a paradigm-shift from predominant singular methods into a more holistic and pro-active system approach to safeguard structural longevity. This is done through a short review of several synergetic Joint Industry Projects (JIP’s) from different angles of incidence on enhanced design and operations through coherent a-priori fatigue prediction and posteriori anomaly detection and -monitoring.
DOCUMENT
The aim of this paper is to show the benefits of enhancing classic Risk Based Inspection (without fatigue monitoring data) with an Advisory Hull Monitoring System (AHMS) to monitor and justify lifetime consumption to provide more thorough grounds for operational, inspection, repair and maintenance decisions whilst demonstrating regulatory compliance.
DOCUMENT
As part of the American Society of Civil Engineers E-Newsletter at page 5&6.
DOCUMENT
The objective of this study was to determine if a 3-dimensional computer vision automatic locomotion scoring (3D-ALS) method was able to outperform human observers for classifying cows as lame or nonlame and for detecting cows affected and nonaffected by specific type(s) of hoof lesion. Data collection was carried out in 2 experimental sessions (5 months apart).
MULTIFILE
