Search Results (52)

To solve the low efficiency of traditional sheet metal measurement, this paper proposes a digital inspection method for sheet metal parts based on 3D point clouds. The 3D point cloud data of sheet metal parts are collected using a 3D laser scanner, and the topological relationship is established by using a K-dimensional tree (KD tree). The pass-through filtering method is adopted to denoise the point cloud data. To preserve the fine features of the parts, an improved voxel grid method is proposed for the downsampling of the point cloud data. Feature points are extracted via the intrinsic shape signatures (ISS) algorithm and described using the fast point feature histograms (FPFH) algorithm. After rough registration with the sample consensus initial alignment (SAC-IA) algorithm, an initial position is provided for fine registration. The improved iterative closest point (ICP) algorithm, used for fine registration, can enhance the registration accuracy and efficiency. The greedy projection triangulation algorithm optimized by moving least squares (MLS) smoothing ensures surface smoothness and geometric accuracy. The reconstructed 3D model is projected onto a 2D plane, and the actual dimensions of the parts are calculated based on the pixel values of the sheet metal parts and the conversion scale. Experimental results show that the measurement error of this inspection system for three sheet metal workpieces ranges from 0.1416 mm to 0.2684 mm, meeting the accuracy requirement of ±0.3 mm. This method provides a reliable digital inspection solution for sheet metal parts. Full article

Significant morphological transformations resulting from open-pit mining activities always present major problems with site safety and slope stability. This study investigates an active marble quarry in Dinar, Türkiye by combining geospatial analysis and photogrammetry based on unmanned aerial vehicles (UAV). Acquired in 2024 and 2025, high-resolution images were combined with dense point clouds produced by Structure from Motion (SfM) methods. Iterative Closest Point (ICP) registration (RMSE = 2.09 cm) and Multiscale Model-to-Model Cloud Comparison (M3C2) analysis was used to quantify the surface changes. The study found a volumetric increase of 7744.04 m³ in the dump zones accompanied by an excavation loss of 8359.72 m³, so producing a net difference of almost 615.68 m³. Surface risk factors were evaluated holistically using a variety of morphometric criteria. These measures covered surface variation in several respects: their degree of homogeneity, presence of any unevenness or texture, verticality, planarity, and linearity. Surface variation > 0.20, roughness > 0.15, and verticality > 0.25 help one to identify zones of increased instability. Point cloud modeling derived from UAVs and GIS-based spatial analysis were integrated to show that morphological anomalies are spatially correlated with possible failure zones. Full article

Spatially referenced and geometrically accurate laser scanning is essential for the safety monitoring of an underground mine. However, the spatial inconsistency of point clouds collected by heterogeneous platforms presents challenges in achieving seamless fusion. In our study, the terrestrial and handheld laser scanning (TLS and HLS) point cloud registration method based on the coarse-to-fine strategy is proposed. Firstly, the point features (e.g., target spheres) are extracted from TLS and HLS point clouds to provide the coarse transform parameters. Then, the fine registration algorithm based on identical area extraction and improved 3D normal distribution transform (3D-NDT) is adopted, which achieves the datum unification of the TLS and HLS point cloud. Finally, the roughness is calculated to downsample the fusion point cloud. The proposed method has been successfully tested on two cases (simulated and real coal mine point cloud). Experimental results showed that the registration accuracy of the TLS and HLS point cloud is 4.3 cm for the simulated mine, which demonstrates the method can capture accurate and complete spatial information about underground mines. Full article

Multiplatform fusion point clouds can effectively compensate for the disadvantages of individual platform point clouds in forest parameter extraction, maximizing the potential of LiDAR technology. However, existing registration algorithms often suffer from insufficient feature extraction and limited registration accuracy. To address these issues, we propose a ULS (Unmanned Aerial Vehicle Laser Scanning)-TLS (Terrestrial Laser Scanning) point cloud data registration method based on Similar Distance Search (SDS). This method enhances coarse registration by accurately retrieving points with similar features, leading to high overlap in the rough registration stage and further improving fine registration precision. (1) The proposed method was tested on four natural forest plots, including Pinus densata Mast., Pinus yunnanensis Franch., Pices asperata Mast., Abies fabri (Mast.) Craib, and demonstrated high registration accuracy. Both coarse and fine registration achieved superior results, significantly outperforming existing algorithms, with notable improvements over the TR algorithm. (2) In addition, the study evaluated the accuracy of individual tree parameter extraction from fusion point clouds versus single-platform point clouds. While ULS point clouds performed slightly better in some metrics, the fused point clouds offered more consistent and reliable results across varying conditions. Overall, the proposed SDS method and the resulting fusion point clouds provide strong technical support for efficient and accurate forest resource management, with significant scientific implications. Full article

The traditional Iterative Closest Point (ICP) algorithm often suffers from low computational accuracy and efficiency in certain scenarios. It is highly sensitive to the initial pose, has a poor ability to resist interference, and frequently becomes trapped in local optima. Extracting feature points accurately from partially overlapping points with weak three-dimensional features, such as smooth planes or surfaces with low curvature, is challenging using only the traditional ICP algorithm for registration. This research introduces a “First Rough then Precise” registration strategy. Initially, the target position is extracted in complex environments using an improved clustering method, which simultaneously reduces the impact of environmental factors and noise on registration accuracy. Subsequently, an improved method for calculating normal vectors is applied to the Fast Point Feature Histogram (FPFH) to extract feature points, providing data for the Sample Consistency Initial Algorithm (SAC-IA). Lastly, an improved ICP algorithm, which has strong anti-interference capabilities for partially overlapping point clouds, is utilized to merge such point clouds. In the experimental section, we validate the feasibility and precision of the proposed algorithm by comparing its registration outcomes with those of various algorithms, using both standard point cloud dataset models and actual point clouds obtained from camera captures. Full article

The bevel cutting of large-thickness plates is a key process in modern industries. However, traditional processing method such as air-arc gouging bevel cutting or laser bevel cutting may cause serious deformation and rough surface quality due to the defects of the thermal cutting method. In order to improve the quality and efficiency of bevel processing, the abrasive waterjet cutting method is used in this research to overcome the challenge for bevel machining of high-strength DH40 steel plates with a large thickness. For different kinds of beveled structures, a 3D camera is used to measure the reference points defined on the workpiece and the SVD registration algorithm is adopted to transform the theoretical coordinate system to the actual coordinate system. Furthermore, the distance between the nozzle and the workpiece surface is also measured and compensated for to ensure the consistency of the bevel width. Finally, experiments are carried out for different kinds of bevels to verify the feasibility of the proposed method for high precision processing for beveled structures. The developed method has been effectively applied in the actual shipbuilding industry. Full article

Background: Management of PICC dressing can be performed at home by the patient through adequate training and telenursing. This trial verifies that the incidence of catheter-related complications in home patients, assisted by telenursing, is not greater than that observed in outpatients. Methods: This clinical trial is composed of 72 patients with malignant tumors who underwent long-term chemotherapy with PICC insertion. They were randomly divided into an experimental group (33 cases) and a calibration group (39 cases). The control group received outpatient dressing for the PICC at the hospital, while the experimental group received a telenursing intervention about the management of the PICC. The incidence of catheter-related infections, the ability of self-management, and a rough cost/benefit estimation were compared between the two groups. This trial was performed according to the CONSORT 2010 checklist. Results: The two groups do not significantly differ in relation to age, sex, and PICCs in terms of the body side insertion, the type of dressing, and the agents used for cleaning. The analysis of the results showed that in the home-managed group, the clinical events reported during the connection were higher when compared with the outpatient group (p < 0.001). The patients in the homecare group developed frequent complications resulting from skin redness (p < 0.001). Conclusion: The use of telenursing for patient education in cancer centers can reduce nurses’ working time, improving the self-management capacity of patients with a long-term PICC. This trial was retrospectively registered with the Clinical Trial Gov on the 18 May 2023 with registration number NCT05880420. Full article

In order to automate defect detection with few samples using unsupervised learning, this paper, considering materials commonly used in aircraft, proposes a phased array ultrasonic detection defect identification method using non-defect samples for training, and three-dimensional characterization is completed on this basis. A phased array ultrasonic device was used to detect two typical structures: a carbon fiber composite cylinder structure and a metal L-shaped structure. No damage label image was required, and the non-damaged sample was used as the the network training input. Based on contrast learning and the cross-registration loss of common features, a feature-matching network was constructed to extract the common features of undamaged detection data, and the performance was optimized by combining STN and GCNet modules. When the detection data of the sample were input to the aforementioned network, the defect distribution representing the location and rough shape of the defect was obtained through Mahalanobis distance calculation. The length was estimated using the S-scan image sequence sampling method. Additionally, the depth of the hole was estimated by combining the B-scan data with line recognition. According to the original model of the sample, the 3D characterization of defects was completed by pyautocad. In the experimental stage, three ablation experiments were carried out to verify the necessity of each module, and performance comparisons were mainly evaluated by F1 score and visualization using four existing well-known anomaly detection methods. Full article

Simultaneous localization and mapping (SLAM) algorithms are widely applied in fields such as autonomous driving and target tracking. However, the effect of moving objects on localization and mapping remains a challenge in natural dynamic scenarios. To overcome this challenge, this paper proposes an algorithm for dynamic point cloud detection that fuses laser and visual identification data, the multi-stage moving object identification algorithm (MoTI). The MoTI algorithm consists of two stages: rough processing and precise processing. In the rough processing stage, a statistical method is employed to preliminarily detect dynamic points based on the range image error of the point cloud. In the precise processing stage, the radius search strategy is used to statistically test the nearest neighbor points. Next, visual identification information and point cloud registration results are fused using a method of statistics and information weighting to construct a probability model for identifying whether a point cloud cluster originates from a moving object. The algorithm is integrated into the front-end of the LOAM system, which significantly improves the localization accuracy. The MoTI algorithm is evaluated on an actual indoor dynamic environment and several KITTI datasets, and the results demonstrate its ability to accurately detect dynamic targets in the background and improve the localization accuracy of the robot. Full article

Digital representations of anatomical parts are crucial for various biomedical applications. This paper presents an automatic alignment procedure for creating accurate 3D models of upper limb anatomy using a low-cost handheld 3D scanner. The goal is to overcome the challenges associated with forearm 3D scanning, such as needing multiple views, stability requirements, and optical undercuts. While bulky and expensive multi-camera systems have been used in previous research, this study explores the feasibility of using multiple consumer RGB-D sensors for scanning human anatomies. The proposed scanner comprises three Intel^® RealSenseTM D415 depth cameras assembled on a lightweight circular jig, enabling simultaneous acquisition from three viewpoints. To achieve automatic alignment, the paper introduces a procedure that extracts common key points between acquisitions deriving from different scanner poses. Relevant hand key points are detected using a neural network, which works on the RGB images captured by the depth cameras. A set of forearm key points is meanwhile identified by processing the acquired data through a specifically developed algorithm that seeks the forearm’s skeleton line. The alignment process involves automatic, rough 3D alignment and fine registration using an iterative-closest-point (ICP) algorithm expressly developed for this application. The proposed method was tested on forearm scans and compared the results obtained by a manual coarse alignment followed by an ICP algorithm for fine registration using commercial software. Deviations below 5 mm, with a mean value of 1.5 mm, were found. The obtained results are critically discussed and compared with the available implementations of published methods. The results demonstrate significant improvements to the state of the art and the potential of the proposed approach to accelerate the acquisition process and automatically register point clouds from different scanner poses without the intervention of skilled operators. This study contributes to developing effective upper limb rehabilitation frameworks and personalized biomedical applications by addressing these critical challenges. Full article

The accurate and efficient segmentation of large-scale urban point clouds is crucial for many higher-level tasks, such as boundary line extraction, point cloud registration, and deformation measurement. In this paper, we propose a novel supervoxel segmentation approach to address the problem of under-segmentation in local regions of point clouds at various resolutions. Our approach introduces distance constraints from boundary points to supervoxel planes in the merging stage to enhance boundary segmentation accuracy between non-coplanar supervoxels. Additionally, supervoxels with roughness above a threshold are re-segmented using random sample consensus (RANSAC) to address multi-planar coupling within local areas of the point clouds. We tested the proposed method on two publicly available large-scale point cloud datasets. The results show that the new method outperforms two classical methods in terms of boundary recall, under-segmentation error, and average entropy in urban scenes. Full article

This paper proposes a stereo-vision-based method that detects and registers the positions and postures of muti-type, randomly placed miniature circuit breaker (MCB) components within scene point clouds acquired by a 3D stereo camera. The method is designed to be utilized in the flexible assembly of MCBs to improve the precision of gripping small-sized and complex-structured components. The proposed method contains the following stages: First, the 3D computer-aided design (CAD) models of the components are converted to surface point cloud models by voxel down-sampling to form matching templates. Second, the scene point cloud is filtered, clustered, and segmented to obtain candidate-matching regions. Third, point cloud features are extracted by Intrinsic Shape Signatures (ISSs) from the templates and the candidate-matching regions and described by Fast Point Feature Histogram (FPFH). We apply Sample Consensus Initial Alignment (SAC-IA) to the extracted features to obtain a rough matching. Fourth, fine registration is performed by employing Iterative Closest Points (ICPs) with a K-dimensional Tree (KD-tree) between the templates and the roughly matched targets. Meanwhile, Random Sample Consensus (RANSAC), which effectively solves the local optimal problem in the classic ICP algorithm, is employed to remove the incorrectly matching point pairs for further precision improvement. The experimental results show that the proposed method achieves spatial positioning errors smaller than 0.2 mm and postural estimation errors smaller than 0.5°. The precision and efficiency meet the requirements of the robotic flexible assembly for MCBs. Full article

Microscopic visual measurement is one of the main methods used for precision measurements. The observation morphology and image registration algorithm used in the measurement directly affect the accuracy and speed of the measurement. This paper analyzes the influence of morphology on different image registration algorithms through the imaging process of surface morphology and finds that complex morphology has more features, which can improve the accuracy of image registration. Therefore, the surface microstructure of ultra-precision machining is an ideal observation object. In addition, by comparing and analyzing the measurement results of commonly used image registration algorithms, we adopt a method of using the high-speed SURF algorithm for rough measurement and then combining the robust template-matching algorithm with image interpolation for precise measurements. Finally, this method has a repeatability of approximately 54 nm when measuring a planar displacement of 25 μm. Full article

There are significant background changes and complex spatial correspondences between multi-modal remote sensing images, and it is difficult for existing methods to extract common features between images effectively, leading to poor matching results. In order to improve the matching effect, features with high robustness are extracted; this paper proposes a multi-temporal remote sensing matching algorithm CMRM (CNN multi-modal remote sensing matching) based on deformable convolution and cross-attention. First, based on the VGG16 backbone network, Deformable VGG16 (DeVgg) is constructed by introducing deformable convolutions to adapt to significant geometric distortions in remote sensing images of different shapes and scales; second, the features extracted from DeVgg are input to the cross-attention module to better capture the spatial correspondence of images with background changes; and finally, the key points and corresponding descriptors are extracted from the output feature map. In the feature matching stage, in order to solve the problem of poor matching quality of feature points, BFMatcher is used for rough registration, and then the RANSAC algorithm with adaptive threshold is used for constraint. The proposed algorithm in this paper performs well on the public dataset HPatches, with MMA values of 0.672, 0.710, and 0.785 when the threshold is selected as 3–5. The results show that compared to existing methods, our method improves the matching accuracy of multi-modal remote sensing images. Full article

Feature matching is a core step in multi-source remote sensing image registration approaches based on feature. However, for existing methods, whether traditional classical SIFT algorithm or deep learning-based methods, they essentially rely on generating descriptors from local regions of feature points, which can lead to low matching success rates due to various challenges, including gray-scale changes, content changes, local similarity, and occlusions between images. Inspired by the human approach of finding rough corresponding regions globally and then carefully comparing local regions, and the excellent global attention property of transformers, the proposed feature matching network adopts a coarse-to-fine matching strategy that utilizes both global and local information between images to predict corresponding feature points. Importantly, the network has great flexibility of matching corresponding points for any feature points and can be effectively trained without strong supervised signals of corresponding feature points and only require the true geometric transformation between images. The qualitative experiment illustrate the effectiveness of the proposed network by matching feature points extracted by SIFT or sampled uniformly. In the quantitative experiments, we used feature points extracted by SIFT, SuperPoint, and LoFTR as the keypoints to be matched. We then calculated the mean match success ratio (MSR) and mean reprojection error (MRE) of each method at different thresholds in the test dataset. Additionally, boxplot graphs were plotted to visualize the distributions. By comparing the MSR and MRE values as well as their distributions with other methods, we can conclude that the proposed method consistently outperforms the comparison methods in terms of MSR at different thresholds. Moreover, the MSR of the proposed method remains within a reasonable range compared to the MRE of other methods. Full article