GACM: A Graph Attention Capsule Model for the Registration of TLS Point Clouds in the Urban Scene

Point cloud registration is the foundation and key step for many vital applications, such as digital city, autonomous driving, passive positioning, and navigation. The difference of spatial objects and the structure complexity of object surfaces are the main challenges for the registration problem. In this paper, we propose a graph attention capsule model (named as GACM) for the efficient registration of terrestrial laser scanning (TLS) point cloud in the urban scene, which fuses graph attention convolution and a three-dimensional (3D) capsule network to extract local point cloud features and obtain 3D feature descriptors. These descriptors can take into account the differences of spatial structure and point density in objects and make the spatial features of ground objects more prominent. During the training progress, we used both matched points and non-matched points to train the model. In the test process of the registration, the points in the neighborhood of each keypoint were sent to the trained network, in order to obtain feature descriptors and calculate the rotation and translation matrix after constructing a K-dimensional (KD) tree and random sample consensus (RANSAC) algorithm. Experiments show that the proposed method achieves more efficient registration results and higher robustness than other frontier registration methods in the pairwise registration of point clouds.

Few-shot learning for deformable image registration in 4DCT images

Objectives: To develop a rapid and accurate 4D deformable image registration (DIR) approach for online adaptive radiotherapy. Methods: We propose a deep learning (DL)-based few-shot registration network (FR-Net) to generate deformation vector fields from each respiratory phase to an implicit reference image, thereby mitigating the bias introduced by the selection of reference images. The proposed FR-Net is pretrained with limited unlabeled 4D data and further optimized by maximizing the intensity similarity of one specific four-dimensional computed tomography (4DCT) scan. Because of the learning ability of DL models, the few-shot learning strategy facilitates the generalization of the model to other 4D data sets and the acceleration of the optimization process. Results: The proposed FR-Net is evaluated for 4D groupwise and 3D pairwise registration on thoracic 4DCT data sets DIR-Lab and POPI. FR-Net displays an averaged target registration error of 1.48 mm and 1.16 mm between the maximum inhalation and exhalation phases in the 4DCT of DIR-Lab and POPI, respectively, with approximately 2 min required to optimize one 4DCT. Overall, FR-Net outperforms state-of-the-art methods in terms of registration accuracy and exhibits a low computational time. Conclusion: We develop a few-shot groupwise DIR algorithm for 4DCT images. The promising registration performance and computational efficiency demonstrate the prospective applications of this approach in registration tasks for online adaptive radiotherapy. Advances in knowledge: This work exploits DL models to solve the optimization problem in registering 4DCT scans while combining groupwise registration and few-shot learning strategy to solve the problem of consuming computational time and inferior registration accuracy.

Pairwise Registration Algorithm for Large-Scale Planar Point Cloud Used in Flatness Measurement

In this paper, an optimized three-dimensional (3D) pairwise point cloud registration algorithm is proposed, which is used for flatness measurement based on a laser profilometer. The objective is to achieve a fast and accurate six-degrees-of-freedom (6-DoF) pose estimation of a large-scale planar point cloud to ensure that the flatness measurement is precise. To that end, the proposed algorithm extracts the boundary of the point cloud to obtain more effective feature descriptors of the keypoints. Then, it eliminates the invalid keypoints by neighborhood evaluation to obtain the initial matching point pairs. Thereafter, clustering combined with the geometric consistency constraints of correspondences is conducted to realize coarse registration. Finally, the iterative closest point (ICP) algorithm is used to complete fine registration based on the boundary point cloud. The experimental results demonstrate that the proposed algorithm is superior to the current algorithms in terms of boundary extraction and registration performance.

Robust Coarse-to-Fine Registration Scheme for Mobile Laser Scanner Point Clouds Using Multiscale Eigenvalue Statistic-Based Descriptor

To overcome the drawbacks of pairwise registration for mobile laser scanner (MLS) point clouds, such as difficulty in searching the corresponding points and inaccuracy registration matrix, a robust coarse-to-fine registration method is proposed to align different frames of MLS point clouds into a common coordinate system. The method identifies the correct corresponding point pairs from the source and target point clouds, and then calculates the transform matrix. First, the performance of a multiscale eigenvalue statistic-based descriptor with different combinations of parameters is evaluated to identify the optimal combination. Second, based on the geometric distribution of points in the neighborhood of the keypoint, a weighted covariance matrix is constructed, by which the multiscale eigenvalues are calculated as the feature description language. Third, the corresponding points between the source and target point clouds are estimated in the feature space, and the incorrect ones are eliminated via a geometric consistency constraint. Finally, the estimated corresponding point pairs are used for coarse registration. The value of coarse registration is regarded as the initial value for the iterative closest point algorithm. Subsequently, the final fine registration result is obtained. The results of the registration experiments with Autonomous Systems Lab (ASL) Datasets show that the proposed method can accurately align MLS point clouds in different frames and outperform the comparative methods.

Groupwise Image Alignment via Self Quotient Images

Compared with pairwise registration, the groupwise one is capable of handling a large-scale population of images simultaneously in an unbiased way. In this work we improve upon the state-of-the-art pixel-level, Least-Squares (LS)-based groupwise image registration methods. Specifically, the registration technique is properly adapted by the use of Self Quotient Images (SQI) in order to become capable for solving the groupwise registration of photometrically distorted, partially occluded as well as unimodal and multimodal images. Moreover, the proposed groupwise technique is linear to the cardinality of the image set and thus it can be used for the successful solution of the problem on large image sets with low complexity. From the application of the proposed technique on a series of experiments for the groupwise registration of photometrically and geometrically distorted, partially occluded faces as well as unimodal and multimodal magnetic resonance image sets and its comparison with the Lucas–Kanade Entropy (LKE) algorithm, the obtained results look very promising, in terms of alignment quality, using as figures of merit the mean Peak Signal to Noise Ratio ( m P S N R ) and mean Structural Similarity ( m S S I M ), and computational cost.