Oblique photography is a regional digital surface model generation technique that can be widely used for building 3D model construction. However, due to the lack of geometric and semantic information about the building, these models make it difficult to differentiate more detailed components in the building, such as roofs and balconies. This paper proposes a deep learning-based method (U-NET) for constructing 3D models of low-rise buildings that address the issues. The method ensures complete geometric and semantic information and conforms to the LOD2 level. First, digital orthophotos are used to perform building extraction based on U-NET, and then a contour optimization method based on the main direction of the building and the center of gravity of the contour is used to obtain the regular building contour. Second, the pure building point cloud model representing a single building is extracted from the whole point cloud scene based on the acquired building contour. Finally, the multi-decision RANSAC algorithm is used to segment the building detail point cloud and construct a triangular mesh of building components, followed by a triangular mesh fusion and splicing method to achieve monolithic building components. The paper presents experimental evidence that the building contour extraction algorithm can achieve a 90.3% success rate and that the resulting single building 3D model contains LOD2 building components, which contain detailed geometric and semantic information.

Underwater crack detection in dam structures is of significant importance to ensure structural safety, assess operational conditions, and prevent potential disasters. Traditional crack detection methods face various limitations when applied to underwater environments, particularly in high dam underwater environments where image quality is influenced by factors such as water flow disturbances, light diffraction effects, and low contrast, making it difficult for conventional methods to accurately extract crack features. This study proposes a dual-stage underwater crack detection method based on Cycle-GAN and YOLOv11 called Edge-Enhanced Underwater CrackNet (E²UCN) to overcome the limitations of existing image enhancement methods in retaining crack details and improving detection accuracy. First, underwater concrete crack images were collected using an underwater remotely operated vehicle (ROV), and various complex underwater environments were simulated to construct a test dataset. Then, an improved Cycle-GAN image style transfer method was used to enhance the underwater images. Unlike conventional GAN-based underwater image enhancement methods that focus on global visual quality, our model specifically constrains edge preservation and high-frequency crack textures, providing a novel solution tailored for crack detection tasks. Subsequently, the YOLOv11 model was employed to perform object detection on the enhanced underwater crack images, effectively extracting crack features and achieving high-precision crack detection. The experimental results show that the proposed method significantly outperforms traditional methods in terms of crack detection accuracy, edge clarity, and adaptability to complex backgrounds, effectively improving underwater crack detection accuracy (precision = 0.995, F1 = 0.99762, mAP@0.5 = 0.995, and mAP@0.5:0.95 = 0.736) and providing a feasible technological solution for intelligent inspection of high dam underwater cracks.

Underwater crack detection in dam structures is of significant engineering importance and scientific value for ensuring the structural safety, assessing operational conditions, and preventing potential disasters. Traditional crack detection methods face various limitations when applied in underwater environments, particularly in high dam underwater environments where image quality is influenced by factors such as water flow disturbances, light diffraction effects, and low contrast, making it difficult for conventional methods to accurately extract crack features. This paper proposes a dual-stage underwater crack detection method based on Cycle-GAN and YOLOv11, called Edge Enhanced Underwater CrackNet (E2UCN), to overcome the limitations of existing image enhancement methods in retaining crack details and improving detection accuracy. First, underwater concrete crack images were collected using an underwater remotely operated vehicle (ROV), simulating various complex underwater environments to construct a test dataset. Then, an improved Cycle-GAN image style transfer method was used to enhance the underwater images, emphasizing crack edges and high-frequency details, avoiding the issues of blurred crack edges and detail loss in existing underwater image enhancement methods. Subsequently, the YOLOv11 model was employed to perform object detection on the enhanced underwater crack images, effectively extracting crack features and achieving high-precision crack detection. Experimental results show that the proposed method significantly outperforms traditional methods in terms of crack detection accuracy, edge clarity, and adaptability to complex backgrounds, effectively improving underwater crack detection accuracy and providing a feasible technological solution for intelligent inspection of high dam underwater cracks.

With the aging of hydraulic engineering and the increasing complexity of underwater environments, the detection of underwater hazards in hydraulic structures has become an urgent need. Traditional detection methods, due to difficulties in operation, low efficiency, and poor accuracy, have become increasingly inadequate to meet practical requirements. Therefore, this paper proposes a computer vision-based method for underwater hazard detection in hydraulic structures. The aim is to achieve automatic, efficient, and accurate detection of underwater hazards in hydraulic structures through image processing and analysis techniques.

Water conveyance tunnels in pumped storage power stations serve as critical pathways connecting the upper and lower reservoirs. Current safety evaluation standards for these tunnels remain insufficient and inadequately address their structural characteristics. Taking the safety evaluation practice of a pumped storage power station as an example, this paper emphasizes that routine inspections and safety monitoring data analysis are vital components of safety evaluation. Given the challenges posed by significant elevation differences and difficult manual inspections in pumped storage tunnels, the application of autonomous collision-proof unmanned aerial vehicles (UAVs) is proposed. This approach enhances inspection efficiency and quality while reducing safety risks for operational personnel. Monitoring sensors embedded within the tunnels dynamically reflect their operational behavior, providing direct insights into structural safety. Analysis of monitoring data reveals that, in addition to reservoir water level fluctuations, temperature (water temperature) significantly influences structural behavior and should be prioritized in safety evaluations.