Matching Algorithm for 3D Point Cloud Recognition and Registration Based on Multi-Statistics Histogram Descriptors

Establishing an effective local feature descriptor and using an accurate key point matching algorithm are two crucial tasks in recognizing and registering on the 3D point cloud. Because the descriptors need to keep enough descriptive ability against the effect of noise, occlusion, and incomplete regions in the point cloud, a suitable key point matching algorithm can get more precise matched pairs. To obtain an effective descriptor, this paper proposes a Multi-Statistics Histogram Descriptor (MSHD) that combines spatial distribution and geometric attributes features. Furthermore, based on deep learning, we developed a new key point matching algorithm that could identify more corresponding point pairs than the existing methods. Our method is evaluated based on Stanford 3D dataset and four real component point cloud dataset from the train bottom. The experimental results demonstrate the superiority of MSHD because its descriptive ability and robustness to noise and mesh resolution are greater than those of carefully selected baselines (e.g., FPFH, SHOT, RoPS, and SpinImage descriptors). Importantly, it has been confirmed that the error of rotation and translation matrix is much smaller based on our key point matching algorithm, and the precise corresponding point pairs can be captured, resulting in enhanced recognition and registration for three-dimensional surface matching.

Learning Rotations

Many problems in computer vision today are solved via deep learning. Tasks like pose estimation from images, pose estimation from point clouds or structure from motion can all be formulated as a regression on rotations. However, there is no unique way of parametrizing rotations mathematically: matrices, quaternions, axis-angle representation or Euler angles are all commonly used in the field. Some of them, however, present intrinsic limitations, including discontinuities, gimbal lock or antipodal symmetry. These limitations may make the learning of rotations via neural networks a challenging problem, potentially introducing large errors. Following recent literature, we propose three case studies: a sanity check, a pose estimation from 3D point clouds and an inverse kinematic problem. We do so by employing a full geometric algebra (GA) description of rotations. We compare the GA formulation with a 6D continuous representation previously presented in the literature in terms of regression error and reconstruction accuracy. We empirically demonstrate that parametrizing rotations as bivectors outperforms the 6D representation. The GA approach overcomes the continuity issue of representations as the 6D representation does, but it also needs fewer parameters to be learned and offers an enhanced robustness to noise. GA hence provides a broader framework for describing rotations in a simple and compact way that is suitable for regression tasks via deep learning, showing high regression accuracy and good generalizability in realistic high-noise scenarios.

Trajectory Similarity Analysis with the Weight of Direction and k-Neighborhood for AIS Data

Automatic Identification System (AIS) data have been widely used in many fields, such as collision detection, navigation, and maritime traffic management. Similarity analysis is an important process for most AIS trajectory analysis topics. However, most traditional AIS trajectory similarity analysis methods calculate the distance between trajectory points, which requires complex and time-consuming calculations, often leading to substantial errors when processing AIS trajectory data characterized by substantial differences in length or uneven trajectory points. Therefore, we propose a cell-based similarity analysis method that combines the weight of the direction and k-neighborhood (WDN-SIM). This method quantifies the similarity between trajectories based on the degree of proximity and differences in motion direction. In terms of its effectiveness and efficiency, WDN-SIM outperformed seven traditional methods for trajectory similarity analysis. Particularly, WDN-SIM has a high robustness to noise and can distinguish the similarities between trajectories under complex situations, such as when there are opposing directions of motion, large differences in length, and uneven point distributions.

Point Set Registration Based on Improved KL Divergence

A point set registration algorithm based on improved Kullback–Leibler (KL) divergence is proposed. Each point in the point set is represented as a Gaussian distribution. The Gaussian distribution contains the position information of the candidate point and surrounding ones. In this way, the entire point set can be modeled as a Gaussian mixture model (GMM). The registration problem of two point sets is further converted as a minimization problem of the improved KL divergence between two GMMs, and the genetic algorithm is used to optimize the solution. Experimental results show that the proposed algorithm has strong robustness to noise, outliers, and missing points, which achieves better registration accuracy than some state-of-the-art methods.

Complementary Fourier Single-Pixel Imaging

Single-pixel imaging, with the advantages of a wide spectrum, beyond-visual-field imaging, and robustness to light scattering, has attracted increasing attention in recent years. Fourier single-pixel imaging (FSI) can reconstruct sharp images under sub-Nyquist sampling. However, the conventional FSI has difficulty balancing imaging quality and efficiency. To overcome this issue, we proposed a novel approach called complementary Fourier single-pixel imaging (CFSI) to reduce the number of measurements while retaining its robustness. The complementary nature of Fourier patterns based on a four-step phase-shift algorithm is combined with the complementary nature of a digital micromirror device. CFSI only requires two phase-shifted patterns to obtain one Fourier spectral value. Four light intensity values are obtained by loading the two patterns, and the spectral value is calculated through differential measurement, which has good robustness to noise. The proposed method is verified by simulations and experiments compared with FSI based on two-, three-, and four-step phase shift algorithms. CFSI performed better than the other methods under the condition that the best imaging quality of CFSI is not reached. The reported technique provides an alternative approach to realize real-time and high-quality imaging.

Study on an Integral Algorithm of Load Identification Based on Displacement Response

Load identification is a very important and challenging indirect load measurement method because load identification is an inverse problem solution with ill-conditioned characteristics. A new method of load identification is proposed here, in which a virtual function was introduced to establish integral structure equations of motion, and partial integration was applied to reduce the response types in the equations. The effects of loading duration, the type of basis function, and the number of basis function expansion items on the calculation efficiency and the accuracy of load identification were comprehensively taken into account. Numerical simulation and experimental results showed that our algorithm could not only effectively identify periodic and random loads, but there was also a trade-off between the calculation efficiency and identification accuracy. Additionally, our algorithm can improve the ill-conditionedness of the solution of load identification equations, has better robustness to noise, and has high computational efficiency.