Fast and Robust Iterative Closest Point

PCDNF: Revisiting Learning-Based Point Cloud Denoising via Joint Normal Filtering

Point cloud denoising is a fundamental and challenging problem in geometry processing. Existing methods typically involve direct denoising of noisy input or filtering raw normals followed by point position updates. Recognizing the crucial relationship between point cloud denoising and normal filtering, we re-examine this problem from a multitask perspective and propose an end-to-end network called PCDNF for joint normal filtering-based point cloud denoising. We introduce an auxiliary normal filtering task to enhance the network's ability to remove noise while preserving geometric features more accurately. Our network incorporates two novel modules. First, we design a shape-aware selector to improve noise removal performance by constructing latent tangent space representations for specific points, taking into account learned point and normal features as well as geometric priors. Second, we develop a feature refinement module to fuse point and normal features, capitalizing on the strengths of point features in describing geometric details and normal features in representing geometric structures, such as sharp edges and corners. This combination overcomes the limitations of each feature type and better recovers geometric information. Extensive evaluations, comparisons, and ablation studies demonstrate that the proposed method outperforms state-of-the-art approaches in both point cloud denoising and normal filtering.

Accurate Registration of Cross-Modality Geometry via Consistent Clustering

The registration of unitary-modality geometric data has been successfully explored over past decades. However, existing approaches typically struggle to handle cross-modality data due to the intrinsic difference between different models. To address this problem, in this article, we formulate the cross-modality registration problem as a consistent clustering process. First, we study the structure similarity between different modalities based on an adaptive fuzzy shape clustering, from which a coarse alignment is successfully operated. Then, we optimize the result using fuzzy clustering consistently, in which the source and target models are formulated as clustering memberships and centroids, respectively. This optimization casts new insight into point set registration, and substantially improves the robustness against outliers. Additionally, we investigate the effect of fuzzier in fuzzy clustering on the cross-modality registration problem, from which we theoretically prove that the classical Iterative Closest Point (ICP) algorithm is a special case of our newly defined objective function. Comprehensive experiments and analysis are conducted on both synthetic and real-world cross-modality datasets. Qualitative and quantitative results demonstrate that our method outperforms state-of-the-art approaches with higher accuracy and robustness. Our code is publicly available at https://github.com/zikai1/CrossModReg.

Fully automated structured light scanning for high-fidelity 3D reconstruction via graph optimization

Convenient and high-fidelity 3D model reconstruction is crucial for industries like manufacturing, medicine and archaeology. Current scanning approaches struggle with high manual costs and the accumulation of errors in large-scale modeling. This paper is dedicated to achieving industrial-grade seamless and high-fidelity 3D reconstruction with minimal manual intervention. The innovative method proposed transforms the multi-frame registration into a graph optimization problem, addressing the issue of error accumulation encountered in frame-by-frame registration. Initially, a global consistency cost is established based on point cloud cross-multipath registration, followed by using the geometric and color differences of corresponding points as dynamic nonlinear weights. Finally, the iteratively reweighted least squares (IRLS) method is adopted to perform the bundle adjustment (BA) optimization of all poses. Significantly enhances registration accuracy and robustness under the premise of maintaining near real-time efficiency. Additionally, for generating watertight, seamless surface models, a local-to-global transitioning strategy for multiframe fusion is introduced. This method facilitates efficient correction of normal vector consistency, addressing mesh discontinuities in surface reconstruction resulting from normal flips. To validate our algorithm, we designed a 3D reconstruction platform enabling spatial viewpoint transformations. We collected extensive real and simulated model data. These datasets were rigorously evaluated against advanced methods, roving the effectiveness of our approach. Our data and implementation is made available on GitHub for community development.

Implementation and analysis of a parallel kalman filter algorithm for lidar localization based on CUDA technology

Introduction: Navigation satellite systems can fail to work or work incorrectly in a number of conditions: signal shadowing, electromagnetic interference, atmospheric conditions, and technical problems. All of these factors can significantly affect the localization accuracy of autonomous driving systems. This emphasizes the need for other localization technologies, such as Lidar. Methods: The use of the Kalman filter in combination with Lidar can be very effective in various applications due to the synergy of their capabilities. The Kalman filter can improve the accuracy of lidar measurements by taking into account the noise and inaccuracies present in the measurements. Results: In this paper, we propose a parallel Kalman algorithm in three-dimensional space to speed up the computational speed of Lidar localization. At the same time, the initial localization accuracy of the latter is preserved. A distinctive feature of the proposed approach is that the Kalman localization algorithm itself is parallelized, rather than the process of building a map for navigation. The proposed algorithm allows us to obtain the result 3.8 times faster without compromising the localization accuracy, which was 3% for both cases, making it effective for real-time decision-making. Discussion: The reliability of this result is confirmed by a preliminary theoretical estimate of the acceleration rate based on Ambdahl's law. Accelerating the Kalman filter with CUDA for Lidar localization can be of significant practical value, especially in real-time and in conditions where large amounts of data from Lidar sensors need to be processed.

Extrinsic calibration for multi-LiDAR systems involving heterogeneous laser scanning models

In the realm of autonomous driving, there is a pressing demand for heightened perceptual capabilities, giving rise to a plethora of multisensory solutions. Among these, multi-LiDAR systems have gained significant popularity. Within the spectrum of available combinations, the integration of repetitive and non-repetitive LiDAR configurations emerges as a balanced approach, offering a favorable trade-off between sensing range and cost. However, the calibration of such systems remains a challenge due to the diverse nature of point clouds, low-common-view, and distinct densities. This study proposed a novel targetless calibration algorithm for extrinsic calibration between Hybrid-Solid-State-LiDAR(SSL) and Mechanical-LiDAR systems, each employing different scanning modes. The algorithm harnesses planar features within the scene to construct matching costs, while proposing the adoption of the Gaussian Mixture Model (GMM) to address outliers, thereby mitigating the issue of overlapping points. Dynamic trust-region-based optimization is incorporated during iterative processes to enhance nonlinear convergence speed. Comprehensive evaluations across diverse simulated and real-world scenarios affirm the robustness and precision of our algorithm, outperforming current state-of-the-art methods.

Scan Matching-Based Particle Filter for LIDAR-Only Localization

This paper deals with the development of a localization methodology for autonomous vehicles using only a 3D LIDAR sensor. In the context of this paper, localizing a vehicle in a known 3D global map of the environment is equivalent to finding the vehicle's global 3D pose (position and orientation), in addition to other vehicle states, within this map. Once localized, the problem of tracking uses the sequential LIDAR scans to continuously estimate the states of the vehicle. While the proposed scan matching-based particle filters can be used for both localization and tracking, in this paper, we emphasize only the localization problem. Particle filters are a well-known solution for robot/vehicle localization, but they become computationally prohibitive as the states and the number of particles increases. Further, computing the likelihood of a LIDAR scan for each particle is in itself a computationally expensive task, thus limiting the number of particles that can be used for real-time performance. To this end, a hybrid approach is proposed that combines the advantages of a particle filter with a global-local scan matching method to better inform the resampling stage of the particle filter. We also use a pre-computed likelihood grid to speed up the computation of LIDAR scan likelihoods. Using simulation data of real-world LIDAR scans from the KITTI datasets, we show the efficacy of the proposed approach.

Real-Time 6-DOF Pose Estimation of Known Geometries in Point Cloud Data

The task of tracking the pose of an object with a known geometry from point cloud measurements arises in robot perception. It calls for a solution that is both accurate and robust, and can be computed at a rate that aligns with the needs of a control system that might make decisions based on it. The Iterative Closest Point (ICP) algorithm is widely used for this purpose, but it is susceptible to failure in practical scenarios. We present a robust and efficient solution for pose-from-point cloud estimation called the Pose Lookup Method (PLuM). PLuM is a probabilistic reward-based objective function that is resilient to measurement uncertainty and clutter. Efficiency is achieved through the use of lookup tables, which substitute complex geometric operations such as raycasting used in earlier solutions. Our results show millimetre accuracy and fast pose estimation in benchmark tests using triangulated geometry models, outperforming state-of-the-art ICP-based methods. These results are extended to field robotics applications, resulting in real-time haul truck pose estimation. By utilising point clouds from a LiDAR fixed to a rope shovel, the PLuM algorithm tracks a haul truck effectively throughout the excavation load cycle at a rate of 20 Hz, matching the sensor frame rate. PLuM is straightforward to implement and provides dependable and timely solutions in demanding environments.

CNN-Based Fault Detection of Scan Matching for Accurate SLAM in Dynamic Environments

This paper proposes a method for CNN-based fault detection of the scan-matching algorithm for accurate SLAM in dynamic environments. When there are dynamic objects in an environment, the environment that is detected by a LiDAR sensor changes. Thus, the scan matching of laser scans is likely to fail. Therefore, a more robust scan-matching algorithm to overcome the faults of scan matching is needed for 2D SLAM. The proposed method first receives raw scan data in an unknown environment and executes ICP (Iterative Closest Points) scan matching of laser scans from a 2D LiDAR. Then, the matched scans are converted into images, which are fed into a CNN model for its training to detect the faults of scan matching. Finally, the trained model detects the faults when new scan data are provided. The training and evaluation are performed in various dynamic environments, taking real-world scenarios into account. Experimental results showed that the proposed method accurately detects the faults of scan matching in every experimental environment.

Fuzzy Cluster-based Group-wise Point Set Registration with Quality Assessment

This article studies group-wise point set registration and makes the following contributions: "FuzzyGReg", which is a new fuzzy cluster-based method to register multiple point sets jointly, and "FuzzyQA", which is the associated quality assessment to check registration accuracy automatically. Given a group of point sets, FuzzyGReg creates a model of fuzzy clusters and equally treats all the point sets as the elements of the fuzzy clusters. Then, the group-wise registration is turned into a fuzzy clustering problem. To resolve this problem, FuzzyGReg applies a fuzzy clustering algorithm to identify the parameters of the fuzzy clusters while jointly transforming all the point sets to achieve an alignment. Next, based on the identified fuzzy clusters, FuzzyQA calculates the spatial properties of the transformed point sets and then checks the alignment accuracy by comparing the similarity degrees of the spatial properties of the point sets. When a local misalignment is detected, a local re-alignment is performed to improve accuracy. The proposed method is cost-efficient and convenient to be implemented. In addition, it provides reliable quality assessments in the absence of ground truth and user intervention. In the experiments, different point sets are used to test the proposed method and make comparisons with state-of-the-art registration techniques. The experimental results demonstrate the effectiveness of our method. The code is available at https://gitsvn-nt.oru.se/qianfang.liao/FuzzyGRegWithQA.

Feature Consistent Point Cloud Registration in Building Information Modeling

Point Cloud Registration contributes a lot to measuring, monitoring, and simulating in building information modeling (BIM). In BIM applications, the robustness and generalization of point cloud features are particularly important due to the huge differences in sampling environments. We notice two possible factors that may lead to poor generalization, the normal ambiguity of boundaries on hard edges leading to less accuracy in transformation; and the fact that existing methods focus on spatial transformation accuracy, leaving the advantages of feature matching unaddressed. In this work, we propose a boundary-encouraging local frame reference, the PyramidFeature(PMD), consisting of point-level, line-level, and mesh-level information to extract a more generalizing and continuous point cloud feature to encourage the knowledge of boundaries to overcome the normal ambiguity. Furthermore, instead of registration guided by spatial transformation accuracy alone, we suggest another supervision to extract consistent hybrid features. A large number of experiments have demonstrated the superiority of our PyramidNet (PMDNet), especially when the training (ModelNet40) and testing (BIM) sets are very different, PMDNet still achieves very high scalability.

GDR-Net: A Geometric Detail Recovering Network for 3D Scanned Objects

This article addresses the problem of mesh super-resolution such that the geometry details which are not well represented in the low-resolution models can be recovered and well represented in the generated high-quality models. The main challenges of this problem are the nonregularity of 3D mesh representation and the high complexity of 3D shapes. We propose a deep neural network called GDR-Net to solve this ill-posed problem, which resolves the two challenges simultaneously. First, to overcome the nonregularity, we regress a displacement in radial basis function parameter space instead of the vertex-wise coordinates in the euclidean space. Second, to overcome the high complexity, we apply the detail recovery process to small surface patches extracted from the input surface and obtain the overall high-quality mesh by fusing the refined surface patches. To train the network, we constructed a dataset composed of both real-world and synthetic scanned models, including high/low-quality pairs. Our experimental results demonstrate that GDR-Net works well for general models and outperforms previous methods for recovering geometric details.

Analysis of Current Situation, Demand and Development Trend of Casting Grinding Technology

Although grinding is essential in the production of castings, the casting grinding process in manufacturing is complicated and there are many difficulties, such as the large amount of noise in the grinding environment, non-structural casting entities, and the inclination in the overall shape-time variation. Even in the face of complex technology and a variety of difficulties, modern casting grinding technology still demands large-batch production, low cost, fast response, thin brittleness, high precision, etc. The grinding process has a long history. This paper focus on its development from a human-operated, mechanical job, to an automatic grinding task based on compliant control theory. However, the methods mentioned above can no longer satisfy the current production need. In recent years, researchers have proposed intelligent grinding methods to meet the needs of modern casting production, and provided various strategies and alternatives to the challenges of machining accuracy, machining efficiency, and surface consistency. The research direction of casting polishing has mainly focused on online robot detection, material removal prediction, constant grinding contact force control, and high-precision matching. Although applications for online detection and constant grinding contact force control exist in industry, there are challenges in material removal prediction and three-dimensional high-precision matching. This paper also compares and analyzes the advantages and disadvantages of different grinding methods, and puts forward some research directions for future work, so as to promote more intelligent and efficient grinding of complex castings in practical application.

Progress in symmetry preserving robot perception and control through geometry and learning

This article reports on recent progress in robot perception and control methods developed by taking the symmetry of the problem into account. Inspired by existing mathematical tools for studying the symmetry structures of geometric spaces, geometric sensor registration, state estimator, and control methods provide indispensable insights into the problem formulations and generalization of robotics algorithms to challenging unknown environments. When combined with computational methods for learning hard-to-measure quantities, symmetry-preserving methods unleash tremendous performance. The article supports this claim by showcasing experimental results of robot perception, state estimation, and control in real-world scenarios.

A Robust Rigid Registration Framework of 3D Indoor Scene Point Clouds Based on RGB-D Information

Rigid registration of 3D indoor scenes is a fundamental yet vital task in various fields that include remote sensing (e.g., 3D reconstruction of indoor scenes), photogrammetry measurement, geometry modeling, etc. Nevertheless, state-of-the-art registration approaches still have defects when dealing with low-quality indoor scene point clouds derived from consumer-grade RGB-D sensors. The major challenge is accurately extracting correspondences between a pair of low-quality point clouds when they contain considerable noise, outliers, or weak texture features. To solve the problem, we present a point cloud registration framework in view of RGB-D information. First, we propose a point normal filter for effectively removing noise and simultaneously maintaining sharp geometric features and smooth transition regions. Second, we design a correspondence extraction scheme based on a novel descriptor encoding textural and geometry information, which can robustly establish dense correspondences between a pair of low-quality point clouds. Finally, we propose a point-to-plane registration technology via a nonconvex regularizer, which can further diminish the influence of those false correspondences and produce an exact rigid transformation between a pair of point clouds. Compared to existing state-of-the-art techniques, intensive experimental results demonstrate that our registration framework is excellent visually and numerically, especially for dealing with low-quality indoor scenes.

Calibration of Planar Reflectors Reshaping LiDAR's Field of View

This paper describes the calibration method for calculating parameters (position and orientation) of planar reflectors reshaping LiDAR's (light detection and ranging) field of view. The calibration method is based on the reflection equation used in the ICP (Iterative Closest Point) optimization. A novel calibration process as the multi-view data registration scheme is proposed; therefore, the poses of the measurement instrument and parameters of planar reflectors are calculated simultaneously. The final metric measurement is more accurate compared with parameters retrieved from the mechanical design. Therefore, it is evident that the calibration process is required for affordable solutions where the mechanical design can differ from the inaccurate assembly. It is shown that the accuracy is less than 20 cm for almost all measurements preserving long-range capabilities. The experiment is performed based on Livox Mid-40 LiDAR augmented with six planar reflectors. The ground-truth data were collected using Z + F IMAGER 5010 3D Terrestrial Laser Scanner. The calibration method is independent of mechanical design and does not require any fiducial markers on the mirrors. This work fulfils the gap between rotating and Solid-State LiDARs since the field of view can be reshaped by planar reflectors, and the proposed method can preserve the metric accuracy. Thus, such discussion concludes the findings. We prepared an open-source project and provided all the necessary data for reproducing the experiments. That includes: Complete open-source code, the mechanical design of reflector assembly and the dataset which was used in this paper.

Enhanced precision inspection of free-form surface with an improved whale optimization algorithm

For precision inspection of free-form surface parts using non-contact measurement methods, the registration between the actual measurement model and the ideal design model is necessary.The traditional iterative closure point (ICP) method requires good initial parameters to obtain the global optimal transformation matrix, which is difficult to guarantee in the actual detection process. In order to improve the accuracy and robustness of free-form surface precision inspection, an Improved Whale Optimization Algorithm (IWOA) is proposed in this study.This algorithm can solve the required registration parameters by constantly updating the population. A measurement experimental system is designed to test the accuracy of blade registration. The performance of IWOA is evaluated by the actual measurement experiment, and the results are verified by a comparative study with Whale Optimization Algorithm (WOA), Lévy flight trajectory-based Whale Optimization Algorithm (LWOA), and Adaptive Whale Optimization Algorithm (AWOA). The surface registration errors are 0.1711mm for IWOA, 2.0015 mm for WOA, 1.2656 mm for LWOA, 2.8132 mm for AWOA and 2.1537 mm for ICP. The results show that the accuracy of IWOA is more than 7 times higher than other four algorithms. In general, the experiments indicate that IWOA has a good registration ability and can meet the needs of industrial measurement.