To cope with the challenges some commonly used displacement sensors may face in structural health monitoring, we proposed a wireless binocular stereovision measurement system based on the improved coarse-to-fine matching algorithm. The vision measurement system can perceive multipoint three-dimensional displacement and consists of two cameras, one remote control unit, and a solar panel. The improved coarse-to-fine matching algorithm only requires a flat surface with some painted textures instead of designed markers with refined patterns (circle, square, and chessboard). Omitting the textures keeps a balance between measurement accuracy and the burden of the target installation in the actual field of structural health monitoring. The proposed coarse-to-fine matching algorithm utilizes scale-invariant feature transform (SIFT) points to generate a robust initial guess and combines improved least squares matching (LSM) algorithm for advanced corresponding point matching. A precalculated look-up table for interpolation and parallel computation is used for higher matching precision and computational efficiency. Several experiments were conducted to present the accuracy and feasibility of the proposed metering system. A simulation test, an indoor shaking table test with several commonly used displacement sensors, and an outdoor experiment consider the natural condition. Experimental results verified that the proposed matching methodology could achieve 0.2-pixel matching accuracy, 0.1mm measuring precision in a laboratory, and millimeter-level precision in real conditions.

Geometric building models are essential in BIM technology. The reconstruction results using current methods are usually represented using mesh, which is limited to visualization purposes and hard to directly import into BIM or modeling software for further application. In this paper, we propose a building model reconstruction method based on a transformer network (DeepBuilding). Instead of reconstructing the polyhedron model of buildings, we strive to recover the CAD modeling operation of constructing the building models from the building point cloud. By representing the building model with its modeling sequence, the reconstruction results can be imported into BIM software for further application. We first translate the procedure of constructing a building model into a command sequence that can be vectorized and processed by the transformer network. Then, we propose a transformer-based network that can convert input point clouds into the vectorized representation of the modeling sequences by decoding the geometry information encoded in the point features. A tool is developed to convert the vectorized modeling sequence into a 3D shape representation (such as mesh) or file format that other BIM software supports. Comprehensive experiments are conducted, and the evaluation results demonstrate that our method can produce competitive reconstruction results with high geometric fidelity while preserving more details of the building reconstruction.

In the shaking table test of large cassette structure, story drift is an essential set of experimental data. The traditional method of displacement measurement is limited to problems such as necessary full contact with the structure model for installation of sensors, large work of installation, and easily interfered by environment. The noncontact displacement measurement method, such as optical measuring technology, can solve the above problems and serve as an effective supplementary method for traditional displacement measuring in the shaking table test. This paper proposed a vison‐based displacement measuring method. Predesigned artificial targets which act as sensors are installed on each floor of the cassette structure model. A high‐speed industrial camera is used to acquire the series of the images of the artificial targets on the structure model during the shaking table test. A Python‐OpenCV‐based structural calculation program combining computer vision and machine vision is developed to extract and calculate the displacement of the artificial targets from the series of the images acquired. The proposed method is applied in a shaking table test of a reduced‐scale fifteen‐floor reinforced concrete cassette structure model, in which the laser displacement meter and the seismic geophone are also applied as a comparison. The experimental results acquired by the proposed method are compared with the results acquired by the laser displacement meter and the seismic geophone. The average error of the story drift obtained by the proposed vision‐based measurement method is within 5% and is in good agreement with the laser displacement meter and the seismic geophone, which confirms the effectiveness of the proposed method.

Transient distractors in dynamic, real-world 3D scenes challenge 3D Gaussian splatting (3DGS) by violating the multi-view consistency assumption, which is essential for accurate 3D reconstruction. Existing methods struggle to accurately identify the boundaries, shadows, and small-scale regions of transient distractors, causing residual transient artifacts to remain in the scenes. Meanwhile, valid static regions may be incorrectly identified as transient distractors, resulting in the loss of useful scene observations and further degrading reconstruction quality. To address these challenges, we propose DifSplat, a novel distractor-free 3D scene reconstruction framework that exploits the priors of visual foundation models. Specifically, we combine an adaptive feature-aware uncertainty estimation strategy with a transient mask optimization strategy guided by high-resolution image residuals, enabling more accurate identification of transient distractors while preserving the static scene. Furthermore, we introduce an inpainting-guided image replacement strategy that utilizes a video diffusion model to inpaint only the regions occluded by transient distractors in the renderings. The inpainted regions are then used to replace the corresponding regions in the original input views, providing additional static scene cues for fine-tuning 3DGS. Extensive experiments on benchmark datasets demonstrate that our proposed method achieves state-of-the-art distractor-free reconstruction quality in both indoor and complex outdoor scenes.