An accurate and timely cracking assessment, including the presence, location and crack geometric feature measurement, is crucial for evaluating concrete wind towers. Therefore, the early identification of cracks is a critical procedure in promptly evaluating structural integrity. This study proposed an ad-hoc encoder–decoder network based on DeepLabv3+ with depth separable convolutions to automatically segment cracks from real-world images captured from various concrete wind towers. The combined advantages of the improved DeepLabv3+ and the lightweight MobileNet v2 are suitable as a benchmark due to their high performance and universality. Four experiments were conducted to determine the model design choice and crack feature measurement capability: (1) six parametric tests using various pre-trained base networks and algorithm optimisers, (2) the influence of complex background noise (i.e., handwriting script) on crack segmentation performance, (3) comparative studies with cutting-edge pixel-wise segmentation models and (4) crack feature measurement (i.e., length and width). The research outcome demonstrated that DeepLabv3+ with MobileNet v2 can potentially be applied for efficient and accurate crack segmentation in concrete wind towers with complex backgrounds.

This study introduced a framework that facilitates bridge diagnostic and prognostic evaluations and related visualizations, leveraging building information modeling (BIM) techniques and data-driven structural health monitoring. Diagnostic and prognostic algorithms are proposed and able to provide intuitive and accessible structural insights via three-dimensional visualizations supported by the BIM techniques. Through the data communication channel established, virtual model information was successfully embedded into the bridge health evaluations, emphasizing the contribution of BIM techniques for data analysis. The proposed algorithms were applied to a case study of a reinforced concrete bridge. Strain distribution along the bridge deck was mapped in the 3D virtual model, which was able to precisely identify the critical location for potential damage. The residual fatigue life of different parts of the bridge deck was estimated and visualized by considering the main effects of traffic loading, exhibiting good alignments with the diagnostic results. The proposed framework is able to provide understandable and actionable structural information for stakeholders, facilitating the timely identification of structural issues and long-term planning of maintenance schedules.

Line feature matching is a crucial aspect of computer vision and image processing tasks, attracting significant research attention. Most line matching algorithms predominantly rely on local feature descriptors or deep learning modules, which often suffer from low robustness and poor generalization. In response, this paper presents a novel line feature matching approach grounded in point–line invariants through spatial invariant relationships. By leveraging a robust point feature matching algorithm, an initial set of point feature matches is acquired. Subsequently, the line feature supporting area is partitioned, and a constant ratio invariant is formulated based on the distances from point to line features within corresponding neighborhood domains. Additionally, a direction vector invariant is also introduced, jointly constructing a dual invariant for line matching. An initial matching matrix and line feature match pairs are derived using this dual invariant. Subsequent geometric constraints within line feature matches eliminate residual outliers. Comprehensive evaluations under diverse imaging conditions, along with comparisons to several state-of-the-art algorithms, demonstrate that our proposal achieved remarkable performance in terms of both accuracy and robustness. Our implementation code will be publicly released upon the acceptance of this paper.

This paper proposes a color image digital watermarking method based on Singular Value Decomposition. Aiming at the binary text image's characteristics of simple pixel, complex texture and bad immunity of information concealment, a digital watermarking embedment location choosing method based upon Singular Value Decomposition has been put forward. This method divides binary text images into different DCT classes. Equivalence classes are further divided into different DCT subclasses according to each pixel's degree and texture changes between blocks. The method has strong resistance to attacks like filtering and zooming. Experimental results indicate that detection in the LL band is robust for one group of attacks, and detection in the HH band is robust for another group of attacks.