Proposed Registration Algorithm Research Articles

Robust colored point cloud alignment based on L*a*b* guided and Cauchy kernel

AbstractPrecision agriculture benefits from point set registration, which can monitor plant health and growth in real time, promote the precise application of fertilizers and pesticides, and provide technical support for achieving sustainable development of agriculture. In this work, we propose a robust point set registration method for precision agriculture based on L*a*b* color guidance, bidirectional search and Cauchy distribution. First, the L*a*b* color guidance is applied to establish accurate correspondences between agricultural RGB‐D data. Second, the bidirectional nearest neighbor search strategy between point sets improves the reliability of establishing correspondences and broadens the convergence domain of the algorithm. Third, Cauchy distribution is utilized as an energy function for noise suppression, which further improves the robustness of the algorithm in dealing with complex vegetation scenes. Finally, results of ablation and simulation experiments indicate that the proposed registration algorithm can achieve more accurate and robust alignment results than other classic and state‐of‐the‐art point cloud registration algorithms to achieve monitoring and comparison of plant growth.

Robust point cloud registration for map-based autonomous robot navigation

Robust point cloud registration for map-based autonomous robot navigation

Affine Iterative Closest Point Algorithm Based on Color Information and Correntropy for Precise Point Set Registration.

In this paper, we propose a novel affine iterative closest point algorithm based on color information and correntropy, which can effectively deal with the registration problems with a large number of noise and outliers and small deformations in RGB-D datasets. Firstly, to alleviate the problem of low registration accuracy for data with weak geometric structures, we consider introducing color features into traditional affine algorithms to establish more accurate and reliable correspondences. Secondly, we introduce the correntropy measurement to overcome the influence of a large amount of noise and outliers in the RGB-D datasets, thereby further improving the registration accuracy. Experimental results demonstrate that the proposed registration algorithm has higher registration accuracy, with error reduction of almost 10 times, and achieves more stable robustness than other advanced algorithms.

Non-rigid registration for medical images based on deformable convolution and multi-scale feature focusing modules

Non-rigid registration plays an important role in medical image analysis. U-Net has been proven to be a hot research topic in medical image analysis and is widely used in medical image registration. However, existing registration models based on U-Net and its variants lack sufficient learning ability when dealing with complex deformations, and do not fully utilize multi-scale contextual information, resulting insufficient registration accuracy. To address this issue, a non-rigid registration algorithm for X-ray images based on deformable convolution and multi-scale feature focusing module was proposed. First, it used residual deformable convolution to replace the standard convolution of the original U-Net to enhance the expression ability of registration network for image geometric deformations. Then, stride convolution was used to replace the pooling operation of the downsampling operation to alleviate feature loss caused by continuous pooling. In addition, a multi-scale feature focusing module was introduced to the bridging layer in the encoding and decoding structure to improve the network model's ability of integrating global contextual information. Theoretical analysis and experimental results both showed that the proposed registration algorithm could focus on multi-scale contextual information, handle medical images with complex deformations, and improve the registration accuracy. It is suitable for non-rigid registration of chest X-ray images.

Point cloud registration based on the dark forest algorithm and its application in coal industry

Being sensitive to initial position and noise is the key problem that must be solved in point cloud registration. To improve the overall performance of registration methods, a point cloud registration method based on the Dark Forest Algorithm is proposed in this paper. The introduction of swarm intelligence enhances the adaptability of the registration method to the initial position and improves the robustness of the point cloud registration system. Furthermore, the application of the Dark Forest Algorithm with four capability enhancement strategies: the hierarchical elite, civilization self-decision, suspicion chain, and technology explosion has improved the comprehensive competitiveness in point cloud registration. The mentioned strategies have brought a great positive impact on the registration methods in solving the far initial position, breaking away from the local optimal solution, and weakening the noise interference. The paper aims to provide the Dark Forest Algorithm and the point cloud registration method based on it, which are elaborated on in detail and compared to other existing algorithms to prove the comprehensive performance, respectively. Then, the point cloud registration experiment for coal-wall point clouds was carried out and the results indicate that the proposed registration algorithm is better than other algorithms for standard point cloud dataset and coal-wall point cloud, which demonstrates that the proposed registration method has strong potential competitiveness.

Freeform optics characterization with surface registration and fitting algorithms for optical point-based spatial path 3D topography metrology.

Accurate characterization of the form error for freeform optics is critical for controlled manufacturing and evaluation of optical properties. To solve the difficulty of current surface registration and fitting algorithms, and improve characterization accuracy of the form error of freeform optics for optical point-based spatial path 3D topography metrology, in this paper, improved surface registration and fitting algorithms are proposed, including a B-spline surface description of freeform optics, point orthogonal projection, registration parameter optimization, and B-spline fitting. Limited by the angular characteristics of an optical point-based sensor, the slope and reference frame of freeform optics must be flexibly adjusted, and polynomial surfaces are described and fitted as B-spline surfaces based on B-spline geometric invariance. To efficiently determine corresponding points on B-spline surfaces, the point orthogonal projection algorithm without Bezier subdivision is proposed using the first-order Newton method. Then, the iteration procedure of coordinate adjustment in sphere space using Lie algebra registration parameters is proposed to solve the difficulty of the current registration parameter optimization procedure. To fit a spatial path form error, the least squares B-spline fitting method is proposed to improve the Zernike method. Through simulation experiments, the proposed registration algorithm with good convergence can improve accuracy by one to two orders of magnitude compared with current registration algorithms. Through repeated experiments of a freeform prism, the proposed method can significantly improve the peak-to-valley and RMS accuracies compared with the stylus method, and characterize the mid-high frequency form error (about 200nm) of a freeform prism.

Spectral Clustering Super-Resolution Imaging Based on Multispectral Camera Array.

Although multispectral and hyperspectral imaging acquisitions are applied in numerous fields, the existing spectral imaging systems suffer from either low temporal or spatial resolution. In this study, a new multispectral imaging system-camera array based multispectral super resolution imaging system (CAMSRIS) is proposed that can simultaneously achieve multispectral imaging with high temporal and spatial resolutions. The proposed registration algorithm is used to align pairs of different peripheral and central view images. A novel, super-resolution, spectral-clustering-based image reconstruction algorithm was developed for the proposed CAMSRIS to improve the spatial resolution of the acquired images and preserve the exact spectral information without introducing false information. The reconstructed results showed that the spatial and spectral quality and operational efficiency of the proposed system are better than those of a multispectral filter array (MSFA) based on different multispectral datasets. The PSNR of the multispectral super-resolution images obtained by the proposed method were respectively higher by 2.03 and 1.93 dB than those of GAP-TV and DeSCI, and the execution time was significantly shortened by approximately 54.55 s and 9820.19 s when the CAMSI dataset was used. The feasibility of the proposed system was verified in practical applications based on different scenes captured by the self-built system.

Accurate and fast registration algorithm for multi-height lensless in-line on-chip holographic microscopy

Lensless in-line on-chip holographic microscope has cost-effective and compact designs that can offer sub-micron resolution over a large field-of-view. In multi-height lensless on-chip holographic microscopy, the in-line hologram series are recorded at different positions along the optical axis, thus, there inevitably exists several kinds of error sources including shifts, scales, and rotations. Therefore, digitally registering and aligning these in-line holograms is of great concern for iterative phase-retrieved recovery. Here, we proposed an accurate and fast registration method, which consists of three major steps. First, Fourier-transform-based phase correlation method is used to roughly correct the spatial translation through locating the correlation peak. Second, we proposed a morphology-based method to accurately search for the matching feature points to obtain the accurate scaling factors, where samples themselves are used as markers without any labeling. Third, the phase correlation method is used for precisely registration again. Experimental results verified the validity and effectiveness of the proposed registration algorithm. And by the comparative experiments with the existing popular registration algorithms, our proposed registration algorithm can register and align the multi-height in-line holograms with greater precision and speed.

Bathymetric LiDAR and multibeam echo-sounding data registration methodology employing a point cloud model

Airborne LiDAR bathymetry (ALB) and multibeam echosounders (MBESs) are the most commonly used technologies for underwater topographical measurements. However, ALB cannot obtain underwater information in deep water. Due to concerns about the safety of the survey vessels, it is difficult to take measurements in shallow water using an MBES. To maximize the complementary advantages of these two technologies, this paper proposes a point cloud registration algorithm for ALB and MBES data based on azimuth angle features. First, the topographical curvature features of ALB and the MBES point cloud data are extracted by using a cylindrical neighborhood model and a quadric surface fitting algorithm. Then, the azimuth angle similarity of the curvature feature points is used to match the corresponding points. Finally, a truncated least-squares-based iterative nearest-adjacent point (TrICP) method is utilized to realize multisource data registration. To verify the performance of the proposed registration algorithm, four areas with typical ALB and MBES point cloud data from Xisha Island, South China Sea, are used as the study areas. Compared to the traditional and typical curvature-based registration (CR) algorithm for point cloud data registration, the proposed algorithm obtains average RMSE values of 0.278 m, 0.252 m, 0.214 m and 0.177 m in the four typical study areas. The corresponding registration accuracy is improved by 91%, 73%, 84% and 49%, respectively. The experimental results show that the proposed algorithm is more reliable and effective for ALB and MBES point cloud registration than the previous algorithms.

Artificial Intelligence Registration of Image Series Based on Multiple Features

Multi-source image series vary in quality. To fuse the feature information of multi-source image series, it is necessary to deeply explore the relevant registration and fusion techniques. The existing techniques of image registration and fusion lack a unified multi-feature-based algorithm framework, and fail to achieve real-time accurate registration. To solve these problems, this paper probes into the artificial intelligence (AI) registration of image series based on multiple features. Firstly, the Harris corner detector was selected to extract the corners of multi-source image series, before explaining and improving the flow of the algorithm. In addition, the deep convolutional neural network (DCNN) VGG16 was improved to extract the features of multi-source image series. Finally, the spatial transformation network was adopted to pre-register the image series, and the image series was deformed and restored based on the region-constrained moving least squares. The proposed registration algorithm was proved effective through experiments.

A Two-stage Registration Method for Dental Volumetric Data and Mesh Data

Dental computed tomography (CT) images and optical surface scan data are widely used in dental computer-aided design systems. Registration is essential if they are used in software systems. Existing automatic registration methods are either time-consuming or rough, and interactive registration methods are experience-dependent and tedious because of a great deal of purely manual interactions. For overcoming these disadvantages, a two-stage registration method is proposed. In the rough registration stage, the rough translation and rotation matrices are obtained by applying unit quaternion based method on the points interactively selected from the two types of data. In the precise registration stage, the stridden sampling is used to reduce computational complexity and the proposed registration algorithm with scale transformation is used for precise registration. The proposed method offers a good trade-off between precision and time cost. The experimental results demonstrate that the proposed method provides faster convergence and smaller registration errors than existing methods.

A Two-stage Registration Method for Dental Volumetric Data and Mesh Data

Dental computed tomography (CT) images and optical surface scan data are widely used in dental computer-aided design systems. Registration is essential if they are used in software systems. Existing automatic registration methods are either time-consuming or rough, and interactive registration methods are experience-dependent and tedious because of a great deal of purely manual interactions. For overcoming these disadvantages, a two-stage registration method is proposed. In the rough registration stage, the rough translation and rotation matrices are obtained by applying unit quaternion based method on the points interactively selected from the two types of data. In the precise registration stage, the stridden sampling is used to reduce computational complexity and the proposed registration algorithm with scale transformation is used for precise registration. The proposed method offers a good trade-off between precision and time cost. The experimental results demonstrate that the proposed method provides faster convergence and smaller registration errors than existing methods.

Robust and Accurate Nonrigid Point Set Registration Algorithm to Accommodate Anisotropic Positional Localization Error Based on Coherent Point Drift

Nonrigid point set (PS) registration is an outstanding and fundamental problem in the fields of robotics, computer vision, medical image analysis, and image-guided surgery (IGS). The aim of a nonrigid registration problem is to align together two point sets where one has been deformed. The assumption of isotropic localization error is shared in the previous nonrigid registration algorithms. In this article, we have derived and presented a novel nonrigid registration algorithm, where the position localization error (PLE) is generalized to be anisotropic, which means that the error distribution is not the same in different spatial directions. The motivation of considering the anisotropic characteristic is that the PLE is actually different in three spatial directions in real applications of registrations, such as IGS. Mathematically, the difficulty in dealing with the anisotropic error case comes from the change from a standard deviation that is a scalar to a covariance matrix. The formulas for updating the parameters in both expectation and maximization steps are derived. More specifically, in the expectation step, we compute the posterior probabilities that represent the correspondences between points in two PSs. In the maximization step, given the current posteriors, the covariance matrix of the PLE and the nonrigid transformation are updated. To further speed up the proposed algorithm, the low-rank approximation variation of our method is also presented. We have demonstrated through experiments on both general and medical data sets (corrupted with noise) that the proposed algorithm outperforms the state-of-the-art ones in terms of registration accuracy and robustness to noise. More specifically, all the experimental results have passed the statistical tests at the 5% significance level. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —This article was motivated by solving the problem of nonrigidly registering two point sets where one has been deformed and corrupted with anisotropic noise. Most existing registration methods generally assume the positional error to be the same in all directions, which in fact is not the case in real scenarios. This article presents a new robust method that assumes the positional error to be anisotropic, which is the case in point sets coming from the stereo reconstruction. The nonrigid registration problem is formulated as a maximum-likelihood (ML) problem and solved with the expectation–maximization (EM) technique. We have demonstrated through extensive experiments on both general and medical data sets that the proposed registration algorithm achieves significantly improved accuracy, robustness to noise, and outliers compared with state-of-the-art algorithms. The algorithm is particularly suitable for biomedical applications involving the registration, such as medical imaging and image-guided surgery (IGS).

A Two-Stage Registration Method for Dental Volumetric Data and Mesh Data

Dental computed tomography (CT) images and optical surface scan data are widely used in dental computer-aided design systems. Registration is essential if they are used in software systems. Existing automatic registration methods are either time-consuming or rough, and interactive registration methods are experience-dependent and tedious because of a great deal of purely manual interactions. For overcoming these disadvantages, a two-stage registration method is proposed. In the rough registration stage, the rough translation and rotation matrices are obtained by applying unit quaternion based method on the points interactively selected from the two types of data. In the precise registration stage, the stridden sampling is used to reduce computational complexity and the proposed registration algorithm with scale transformation is used for precise registration. The proposed method offers a good trade-off between precision and time cost. The experimental results demonstrate that the proposed method provides faster convergence and smaller registration errors than existing methods.

Automatic Registration of Remote Sensing Images Based on Revised SIFT With Trilateral Computation and Homogeneity Enforcement

Automatic registration of remote sensing images is an essential task that requires the establishment of appropriate correspondences between the sensed image and the reference image. Among the feature-based matching approaches, attempts relied on the scale-invariant feature transform (SIFT) algorithm have shown particular superiority over other methods. From the perspective of automatic registration, the challenges of SIFT-based methods involve the elimination of mismatches and the homogeneity of matches. While many outlier removal methods have been proposed, the strategies for uniform distribution have been lacking. To address these two issues, this article investigates a new remote sensing image registration algorithm based upon a revised SIFT scheme. Additionally, an outlier removal mechanism founded on a trilateral computation (Tc) recipe and a homogeneity enforcement (He) layout according to a divide-and-conquer inclusion tactic are proposed. Finally, a stochastic competition process based upon game theory is introduced to secure an appropriate amount of correct matches in the proposed Tc and He (TcHe)-SIFT framework. A wide variety of multispectral and multitemporal remote sensing images with various scenarios were exploited to evaluate the proposed registration algorithm. Experimental results demonstrated the advantages of our developed remote sensing image registration algorithm over the state-of-the-art SIFT-based methods. We believe that this new registration technique is of potential in a number of remote sensing image processing applications.

Improved extended Gaussian image and its application on 3D point clouds registration

To solve the problem of lacking geometric and topological information for conventional 3D point clouds registration algorithm, this paper proposed a novel 3D point clouds registration algorithm based on improved extended Gaussian image. The proposed registration algorithm first estimates a normal vector and curvature of every point by least square method. Then, according to the normal vector to calculate extended Gaussian image (EGI) and complex extended Gaussian image (CEGI). By using the calculated EGI/CEGI and spherical harmonic function, a correlated function is constructed to calculate 3D rotation space to obtain initial positions coarse registration result. At last, by using the Fourier transform to estimate translation vector and coarse registration, the iterative closest point algorithm is used to obtain the fine registration results. Experiments on three groups of different 3D point clouds are performed to validate the proposed registration algorithm. Experimental results have shown that the proposed algorithm has good performances on registration of different forms of 3D point clouds. The robustness and efficiency of our proposed algorithm can effectively solve the problem that it is difficult to find the target or the homonymic feature points in the registration process of 3D point clouds.

Direct 3D ultrasound fusion for transesophageal echocardiography

BackgroundReal-time three-dimensional transesophageal echocardiography (3D TEE) has been increasingly used in clinic for fast 3D analysis of cardiac anatomy and function. However, 3D TEE still suffers from the limited field of view (FoV). It is challenging to adopt conventional multi-view fusion methods to 3D TEE images because feature-based registration methods tend to fail in the ultrasound scenario, and conventional intensity-based methods have poor convergence properties and require an iterative coarse-to-fine strategy. MethodsA novel multi-view registration and fusion method is proposed to enlarge the FoV of 3D TEE images efficiently. A direct method is proposed to solve the registration problem in the Lie algebra space. Fast implementation is realized by searching voxels on three orthogonal planes between two volumes. Besides, a weighted-average 3D fusion method is proposed to fuse the aligned images seamlessly. For a sequence of 3D TEE images, they are fused incrementally. ResultsQualitative and quantitative results of in-vivo experiments indicate that the proposed registration algorithm outperforms a state-of-the-art PCA-based registration method in terms of accuracy and efficiency. Image registration and fusion performed on 76 in-vivo 3D TEE volumes from nine patients show apparent enlargement of FoV (enlarged around two times) in the obtained fused images. ConclusionsThe proposed methods can fuse 3D TEE images efficiently and accurately so that the whole Region of Interest (ROI) can be seen in a single frame. This research shows good potential to assist clinical diagnosis, preoperative planning, and future intraoperative guidance with 3D TEE.

Dense Registration and Mosaicking of Fingerprints by Training an End-to-End Network

Dense registration of fingerprints is a challenging task due to elastic skin distortion, low image quality, and self-similarity of ridge pattern. To overcome the limitation of handcraft features, we propose to train an end-to-end network to directly output pixel-wise displacement field between two fingerprints. The proposed network includes a siamese network for feature embedding, and a following encoder-decoder network for regressing displacement field. By applying displacement fields reliably estimated by tracing high quality fingerprint videos to challenging fingerprints, we synthesize a large number of training fingerprint pairs with ground truth displacement fields. In addition, based on the proposed registration algorithm, we propose a fingerprint mosaicking method based on optimal seam selection. Registration and matching experiments on FVC2004 databases, Tsinghua Distorted Fingerprint (TDF) database, and NIST SD27 latent fingerprint database show that our registration method outperforms previous dense registration methods in accuracy and efficiency. Mosaicking experiment on FVC2004 DB1 demonstrates that the proposed algorithm produced higher quality fingerprints than other algorithms which also validates the performance of our registration algorithm.

OCTRexpert:A Feature-based 3D Registration Method for Retinal OCT Images.

Medical image registration can be used for studying longitudinal and cross-sectional data, quantitatively monitoring disease progression and guiding computer assisted diagnosis and treatments. However, deformable registration which enables more precise and quantitative comparison has not been well developed for retinal optical coherence tomography (OCT) images. This paper proposes a new 3D registration approach for retinal OCT data called OCTRexpert. To the best of our knowledge, the proposed algorithm is the first full 3D registration approach for retinal OCT images which can be applied to longitudinal OCT images for both normal and serious pathological subjects. In this approach, a pre-processing method is first performed to remove eye motion artifact and then a novel design-detection-deformation strategy is applied for the registration. In the design step, a couple of features are designed for each voxel in the image. In the detection step, active voxels are selected and the point-to-point correspondences between the subject and template images are established. In the deformation step, the image is hierarchically deformed according to the detected correspondences in multi-resolution. The proposed method is evaluated on a dataset with longitudinal OCT images from 20 healthy subjects and 4 subjects diagnosed with serious Choroidal Neovascularization (CNV). Experimental results show that the proposed registration algorithm consistently yields statistically significant improvements in both Dice similarity coefficient and the average unsigned surface error compared with the other registration methods.

An Integrated Approach to Registration and Fusion of Hyperspectral and Multispectral Images

Combining a hyperspectral (HS) image and a multispectral (MS) image - an example of image fusion - can result in a spatially and spectrally high-resolution image. Despite the plethora of fusion algorithms in remote sensing, a necessary prerequisite, namely registration, is mostly ignored. This limits their application to well-registered images from the same source. In this article, we propose and validate an integrated registration and fusion approach (code available at https://github.com/zhouyuanzxcv/Hyperspectral). The registration algorithm minimizes a least-squares (LSQ) objective function with the point spread function (PSF) incorporated together with a nonrigid freeform transformation applied to the HS image and a rigid transformation applied to the MS image. It can handle images with significant scale differences and spatial distortion. The fusion algorithm takes the full high-resolution HS image as an unknown in the objective function. Assuming that the pixels lie on a low-dimensional manifold invariant to local linear transformations from spectral degradation, the fusion optimization problem leads to a closed-form solution. The method was validated on the Pavia University, Salton Sea, and the Mississippi Gulfport datasets. When the proposed registration algorithm is compared to its rigid variant and two mutual information-based methods, it has the best accuracy for both the nonrigid simulated dataset and the real dataset, with an average error less than 0.15 pixels for nonrigid distortion of maximum 1 HS pixel. When the fusion algorithm is compared with current state-of-the-art algorithms, it has the best performance on images with registration errors as well as on simulations that do not consider registration effects.