Traditional Registration Methods Research Articles

3D Reconstruction Approach for Outdoor Scene Based on Multiple Point Cloud Fusion

Multiple point cloud fusion is one of the most widely used methods for outdoor scene 3D reconstruction. However, being based on the traditional registration methods, their performance critically influences the quality of the 3D reconstruction. This paper proposes a 3D reconstruction method that fuses different sensors point cloud, which comes from laser scanning and structure from motion. First, a scale-based principal component analysis–iterative closest point (a scaled PCA–ICP) algorithm is addressed to eliminate different scales of two view points. Further, the feature points are extracted automatically for accurate registration by analyzing the persistence of feature points with discretely sampling on different sphere radii. Finally, the optimization ICP method is used to match multiple point cloud to achieve accurate reconstruction of outdoor scenes robustly. The experimental evaluation demonstrates that the proposed method is able to produce reliable registration results for the outdoor scene.

VoxelMorph: A Learning Framework for Deformable Medical Image Registration

We present VoxelMorph, a fast learning-based framework for deformable, pairwise medical image registration. Traditional registration methods optimize an objective function for each pair of images, which can be time-consuming for large datasets or rich deformation models. In contrast to this approach, and building on recent learning-based methods, we formulate registration as a function that maps an input image pair to a deformation field that aligns these images. We parameterize the function via a convolutional neural network (CNN), and optimize the parameters of the neural network on a set of images. Given a new pair of scans, VoxelMorph rapidly computes a deformation field by directly evaluating the function. In this work, we explore two different training strategies. In the first (unsupervised) setting, we train the model to maximize standard image matching objective functions that are based on the image intensities. In the second setting, we leverage auxiliary segmentations available in the training data. We demonstrate that the unsupervised model's accuracy is comparable to state-of-the-art methods, while operating orders of magnitude faster. We also show that VoxelMorph trained with auxiliary data improves registration accuracy at test time, and evaluate the effect of training set size on registration. Our method promises to speed up medical image analysis and processing pipelines, while facilitating novel directions in learning-based registration and its applications. Our code is freely available at https://github.com/voxelmorph/voxelmorph.

Automatic Dewarping of Retina Images in Adaptive Optics Confocal Scanning Laser Ophthalmoscope

Retina images acquired by an adaptive optics confocal scanning laser ophthalmoscope (AOSLO) usually need to remove image warp to improve image quality. The most significant task of AOSLO image dewarping is image registration. Most traditional feature-based registration algorithms used for AOSLO images are based on Gaussian scale space. However, the homogeneous Gaussian blurring reduces the localization accuracy of feature points and the distinctiveness of feature descriptors. In this paper, the accelerated KAZE (AKAZE) feature based on nonlinear scale space was utilized to register AOSLO retinal images for the first time, and an efficient strategy based on matched feature points for frame selection was proposed to automatically accomplish AOSLO retinal image dewarping. Moreover, a flexible method based on power spectra analysis is proposed to study the minimum number of frames needed to accomplish image dewarping. The extensive experiments demonstrated that the AKAZE method is more suitable for AOSLO image dewarping, benefitted with better accuracy, robustness, and rapidity compared with several traditional registration methods based on Gaussian scale space.

Robust image registration of printed circuit boards using improved SIFT‐PSO algorithm

Printed circuit board (PCB) layout is becoming high density, high performance, light, and short. In the automatic PCB defect detection system, image registration of PCB plays an important role. However, most of the traditional registration methods are inefficient, and cannot cope with the problems of image distortion, affine, noise, and so on. To address this issue, the authors propose an improved scale invariant feature transform (SIFT) feature extraction algorithm combined with particle swarm optimisation (PSO) to register the images of PCB which placed on a conveyor belt. The advantage of the presented approach is that the registration results are more robust and efficient by optimising the existing PCB image matching framework. The experimental results on the proposed PCB datasets show that the speed of the proposed method (improved SIFT-PSO) is faster than the traditional SIFT feature registration method, and the average computing time of processing single picture can be improved by 10 s, the registration accuracy can be improved by 3–4%. Compared with the experimental results of other algorithms, the root-mean-square error can be reduced to 0.5146 by using the proposed method. Thus, the proposed method (improved SIFT-PSO) is more accurate and robust in real-time inspection system of PCB.

Registration for images in the presence of additive and multiplicative fixed-pattern noise.

Image registration under conditions of fixed-pattern noise is a difficult problem that has not been solved in the literature. While traditional registration methods are adequate for additive random noise, these are not suited to spatially invariant noise that is additive or multiplicative. We present a method for image registration using a difference operation in the frequency domain. Shift values are then computed by dividing by the object Fourier transform and inverse transforming. The method described is valid for both additive and multiplicative noise and determines shifts with sub-pixel accuracy. Additionally, minimal prior knowledge of the corrupting pattern is required. We compare our method with previous registration methods for varying amounts of noise. Results are presented for both simulated images and images recorded from a thermal camera with significant fixed-pattern noise.

A target-oriented segmentation method for specific tissues in MRI images of the brain

The multi-atlas based segmentation method can achieve the accurate segmentation of specific tissues of the human brain in the magnetic resonance imaging (MRI). The correct image registration and fusion scheme used in this method have an impact on the accuracy of segmentation. Similar to any traditional rigid registration method, we use the same method in our proposed target-oriented registration for the coarse registration between the target image and atlas image. However, to improve the registration accuracy in the area to be segmented, we propose a target-oriented image registration method for the refinement. We employ the distribution probability of the tissue (to be segmented) in the sparse patch-based label fusion process. Our aim is to determine if the proposed registration method can contribute the segmentation accuracy and which label fusion method is a good fit with this target-oriented registration. To evaluate the efficiency of our proposed method, we compare the performance of the majority voting method (MV), the nonlocal patch-based method (Nonlocal-PBM) and the sparse patch-based method (Sparse-PBM). Experimental results show that more accurate segmentation results can be obtained with the proposed registration method in this study. This result can provide more accurate clinical diagnosis information.

Multilevel active registration for kinect human body scans: from low quality to high quality

Registration of 3D human body has been a challenging research topic for over decades. Most of the traditional human body registration methods require manual assistance, or other auxiliary information such as texture and markers. The majority of these methods are tailored for high-quality scans from expensive scanners. Following the introduction of the low-quality scans from cost-effective devices such as Kinect, the 3D data capturing of human body becomes more convenient and easier. However, due to the inevitable holes, noises and outliers in the low-quality scan, the registration of human body becomes even more challenging. To address this problem, we propose a fully automatic active registration method which deforms a high-resolution template mesh to match the low-quality human body scans. Our registration method operates on two levels of statistical shape models: (1) the first level is a holistic body shape model that defines the basic figure of human; (2) the second level includes a set of shape models for every body part, aiming at capturing more body details. Our fitting procedure follows a coarse-to-fine approach that is robust and efficient. Experiments show that our method is comparable with the state-of-the-art methods for high-quality meshes in terms of accuracy and it outperforms them in the case of low-quality scans where noises, holes and obscure parts are prevalent.

Application of bonebed-malleus short process registration in minimally invasive cochlear implantation

Purpose: This article proposed and investigated the application of bonebed-malleus short process registration in minimally invasive cochlear implantation, and assessed the value of the proposed strategy for image-guided otologic surgery.Materials and methods: Ten temporal bone specimens were marked with both shallow and deep targets in order to measure registration resolutions. Two registration methods were applied. Method A (a new registration method) consisted of bonebed-malleus short process registration, while method B (traditional registration method) comprised registration using four titanium screws attached at the mastoid surface. The target registration errors (TRE) were measured at both the shallow and deep fiducial targets. After registration achieved by method A, percutaneous cochlear drilling was conducted on the other eight temporal bone specimens in order to observe the deviation from the target point and entry point.Results: Using method A, the error observed at the shallow fiducial markers of specimens was less than 1 mm, while the error observed at the deep fiducial markers was approximately equal to 1 mm. No significant difference was observed when results were compared with the application of method B. In eight studied cases using method A, drilling operations were successfully conducted. The deviations from the target point and the entry point were 0.84 ± 0.30 and 0.66 ± 0.51 mm, respectively.Conclusions: Results of the present study indicated that the new registration method demonstrated identical accuracy when compared to traditional registration method, achieved less invasiveness. Thus, the proposed method might be a feasible registration method for image-guided otologic surgery due to its mild invasiveness and high accuracy.

Efficient registration of terrestrial LiDAR scans using a coarse-to-fine strategy for forestry applications

Terrestrial Laser Scanning (TLS) plays an increasing role in acquiring 3-dimensional forest structure information. Obstructions and stem density often need multiple scans, making the registration procedure vitally important. Since natural features are difficult to find, traditional registration methods often use artificial reflectors as tie points in forest areas. However, the placement of reflectors reduces the scanning efficiency, especially in forest stands with severe obstructions. In this paper, an efficient registration method using a coarse-to-fine strategy is proposed to overcome the challenge of placing artificial targets so as to improve the scanning efficiency. The coarse registration step utilizes the backsighting orientation approach to form a coarse alignment. Unlike other backsighting research used in urban areas, we solely rely on a TLS system with an internal compass and a built-in inclination sensor. In the fine registration step, stem center locations are calculated in each individual scan. Then, corresponding stem center pairs are found between adjacent scans with the help of the coarse registration results. They are used as tie points to perform a rigid-body transformation for the fine registration. The proposed coarse-to-fine registration method was tested at two forest sites in northeast China. The registration accuracy is approximately 1.5cm. Results also show that the diameters at breast height (DBHs) extracted from registered TLS data sets are highly correlated with field-measured DBHs (coefficient of determination (R2): 0.92, root mean square error (RMSE): 0.27cm). Considering both the scanning efficiency and accuracy, the proposed coarse-to-fine registration method provides a feasible and effective way for forest measurements.

Automatic Registration Method for Optical Remote Sensing Images with Large Background Variations Using Line Segments

Image registration is an essential step in the process of image fusion, environment surveillance and change detection. Finding correct feature matches during the registration process proves to be difficult, especially for remote sensing images with large background variations (e.g., images taken pre and post an earthquake or flood). Traditional registration methods based on local intensity probably cannot maintain steady performances, as differences are significant in the same area of the corresponding images, and ground control points are not always available in many disaster images. In this paper, an automatic image registration method based on the line segments on the main shape contours (e.g., coastal lines, long roads and mountain ridges) is proposed for remote sensing images with large background variations because the main shape contours can hold relatively more invariant information. First, a line segment detector called EDLines (Edge Drawing Lines), which was proposed by Akinlar et al. in 2011, is used to extract line segments from two corresponding images, and a line validation step is performed to remove meaningless and fragmented line segments. Then, a novel line segment descriptor with a new histogram binning strategy, which is robust to global geometrical distortions, is generated for each line segment based on the geometrical relationships,including both the locations and orientations of theremaining line segments relative to it. As a result of the invariance of the main shape contours, correct line segment matches will have similar descriptors and can be obtained by cross-matching among the descriptors. Finally, a spatial consistency measure is used to remove incorrect matches, and transformation parameters between the reference and sensed images can be figured out. Experiments with images from different types of satellite datasets, such as Landsat7, QuickBird, WorldView, and so on, demonstrate that the proposed algorithm is automatic, fast (4 ms faster than the second fastest method, i.e., the rotation- and scale-invariant shape context) and can achieve a recall of 79.7%, a precision of 89.1% and a root mean square error (RMSE) of 1.0 pixels on average for remote sensing images with large background variations.

A Linear Feature-Based Approach for the Registration of Unmanned Aerial Vehicle Remotely-Sensed Images and Airborne LiDAR Data

Compared with traditional manned airborne photogrammetry, unmanned aerial vehicle remote sensing (UAVRS) has the advantages of lower cost and higher flexibility in data acquisition. It has, therefore, found various applications in fields such as three-dimensional (3D) mapping, emergency management, and so on. However, due to the instability of the UAVRS platforms and the low accuracy of the onboard exterior orientation (EO) observations, the use of direct georeferencing image data leads to large location errors. Light detection and ranging (LiDAR) data, which is highly accurate 3D information, is treated as a complementary data source to the optical images. This paper presents a semi-automatic approach for the registration of UAVRS images and airborne LiDAR data based on linear control features. The presented approach consists of three main components, as follows. (1) Buildings are first separated from the point cloud by the integrated use of height and size filtering and RANdom SAmple Consensus (RANSAC) plane fitting, and the 3D line segments of the building ridges and boundaries are semi-automatically extracted through plane intersection and boundary regularization with manual selections; (2) the 3D line segments are projected to the image space using the initial EO parameters to obtain the approximate locations, and all the corresponding 2D line segments are semi-automatically extracted from the UAVRS images. Meanwhile, the tie points of the UAVRS images are generated using a Förstner operator and least-squares image matching; and (3) by use of the equations derived from the coplanarity constraints of the linear control features and the colinear constraints of the tie points, block bundle adjustment is carried out to update the EO parameters of the UAVRS images in the coordinate framework of the LiDAR data, achieving the co-registration of the two datasets. Experiments were performed to demonstrate the validity and effectiveness of the presented method, and a comparison with the traditional registration method based on LiDAR intensity images showed that the presented method is more accurate, and a sub-pixel accuracy level can be achieved.

基于角点特征的遥感图像快速配准

针对遥感图像传统配准算法匹配速度较慢、不满足实时性要求等问题，本文提出了一种结合改进AGAST与FREAK算法的遥感图像快速配准方法。首先，利用改进AGAST检测算法分别快速检测参考图像和待配准图像中的特征点；然后用FREAK算法获取二进制描述符串，利用级联匹配计算特征向量之间的汉明距离，获得特征点匹配对；最后利用改进的相似三角形剔除方法去掉错误的匹配对，并结合最小二乘法，估算出空间几何变换参数，实现两幅图像的配准。实验结果表明，本文方法在保证遥感图像配准精度的同时，配准速度相比于传统配准方法得到较大提升。 In this paper, because the traditional registration algorithms for remote sensing image are slower and don’t meet the requirements of real-time problem, a new method is proposed based on the combination of improved AGAST and FREAK for fast remote sensing images registration. Firstly, the improved AGAST is used to detect the feature points between reference image and image that is to be registered; Secondly, FREAK algorithm is used to obtain a binary string descriptor, and hamming distance between features vector is computed by using a cascade match to get matching feature points; Finally, wrong match pairs are eliminated by using the improved similar triangle method, and the optimal spatial geometric transform parameters are estimated using the least square method to accomplish the two images registration. Experimental results show that the pro- posed method improves the registration rate compared to the traditional registration methods, and ensures accuracy at the same time.

Atlas to patient registration with brain tumor based on a mesh-free method.

Brain atlas to patient registration in the presence of tumors is a challenging task because its presence cause brain structure deformations and introduce large intensity variation between the affected areas. This large dissimilarity affects the results of traditional registration methods based on intensity or shape similarities. In order to overcome these problems, we propose a novel method that brings closer the atlas and the patient's image by simulating the mechanical behavior of brain deformation under a tumor pressure. The proposed method use a mesh-free total Lagrangian Explicit Dynamic algorithm for the simulation of atlas deformation and a data driven model of the tumor using multi-modal MRI segmentation. Experimental results look structurally very similar to the patient's image and outperform two of the top ranking algorithms.

应用显著纹理特征的医学图像配准

Traditional registration methods based on geometric measurement can not match the medical image with local deformation. to solve the problem, an improved iterative closest points (icp) algorithm about human visual cognitive process is proposed base on the salient texture. firstly, the method establishes the model for the salient texture feature of a medical image based on active appearance model (aam) algorithm, and it gives the feature point with more salient for a larger weight to complete the image match in the first step. then, it introduces the salient texture distance to the traditional space distance. by simulating the human visual cognitive process proposed by gestalt, the linear decreasing weight is used to balance the two kinds of distance measuring methods. with the algorithm, a whole registration is obtained by the geometric distance in the early stage. on the other hand, the feature points of local deformation are accurately registrated with the texture features in the later stage. at last, a series of experiments are performed on real live images. the experiment results show that the algorithm can get a good matching result, and the registration accuracy is 78.82%, increasing by 22.22% as compared with those of other popular algorithms. the experimental results also show that it is not sensitive to the rotation of the images. it concludes that the algorithm solves the registration problems of local deformation in medical organs and achieves higher precision and stronger robustness. ©, 2015, chinese academy of sciences. all right reserved.

Quick Registration Method Based on Image Region Correlation

Binocular vision system can be widely used in CNC machine tools chatter monitoring, due to its simple system and automatic measurement function. Traditional registration method cannot balance the contradiction between precision and speed of registration; restrict its application in high speed monitoring system. So based on traditional feature point registration method, it proposes a new method to obtain more accurate matching feature points by using complexity distribution feature of image region to determine the distribution of feature region and the bidirectional similarity and triangle similar method, which realize quick registration. From the simulation and implementation effect perspective, this method is feasible for the image registration in high-speed monitoring system.

Curvelet-based registration of multi-component seismic waves

Abstract Registration of the travel time of PP waves and PS waves on the same coordinate is critical for joint interpretation in multi-component seismic exploration. In this paper, we propose a new curvelet-based registration method to improve the precision of registration, especially for the data with heavy random noises. By making registration in curvelet multiscale spaces from coarser to finer scale, the proposed method is not sensitive to initial values of velocity ratio of PP waves and PS waves. Applications of the new method to real seismic dataset from Shengli Oilfield, China show good registered results in terms of both qualitative and quantitative analysis, in comparison with a traditional registration method and a wavelet-based method.

Registration of Aerial Imagery and Lidar Data in Desert Areas Using the Centroids of Bushes as Control Information

Geometric registration of multiple-source data is of great value for fusion processing and is very beneficial for the research of desert ecosystems. A lidar point cloud and optical image are two typical data that need to be integrated for data assimilation and information retrieval. This paper aims to solve the registration problem of aerial imagery and airborne lidar data in desert areas where traditional registration methods have difficulties in identifying registration primitives. In many deserts, such as the Sahara in Africa and Gobi in China, we observe that there are unevenly distributed desert bushes, which can be used as cues for registration. In this paper, we propose a registration approach using the centroids of bushes as registration primitives. This approach employs similar triangles created from both centroids as the evidence for matching and verifies the registration by the RANSAC algorithm. Experiments using data taken from the Dunhuang Gobi Desert in China show the registration surface model visually, and at the same time quantifies the deviation error, which corroborates that the proposed registration method is effective and feasible in desert areas.

Novel registration for microcomputed tomography and bioluminescence imaging based on iterated optimal projection

As a high-sensitivity imaging modality, bioluminescence tomography can reconstruct the three-dimensional (3-D) location of an internal luminescent source based on the 3-D surface light distribution. However, we can only get the multi-orientation two-dimensional (2-D) bioluminescence distribution in the experiments. Therefore, developing an accurate universal registration method is essential for following bioluminescent source reconstruction. We can then map the multi-orientation 2-D bioluminescence distribution to the 3-D surface derived from anatomical information with it. We propose a 2-D -to-3-D registration method based on iterated optimal projection and applied it in a registration and reconstruction study of three transgenic mice. Compared with traditional registration methods based on the fixed points, our method was independent of the markers and the registration accuracy of the three experiments was improved by 0.3, 0.5, and 0.4 pixels, respectively. In addition, based on the above two registration results using the two registration methods, we reconstructed the 3-D location of the inner bioluminescent source in the three transgenic mice. The reconstruction results showed that the average error distance between the center of the reconstructed element and the center of the real element were reduced by 0.32, 0.48, and 0.39 mm, respectively.

Multiple information‐based spot matching method for 2‐DE images

Spot matching is considered as one of key elements in protein identification based on 2-DE while it is a difficult problem. We propose a novel simple and accurate method for matching spots in 2-DE images. The method, inspired from the principle of attraction, is based on the simultaneous exploitation of multiple information such as spot distance, spot intensity, and spot pattern information. The proposed method was evaluated using both simulated and real 2-DE images of the Escherichia coli proteome, and was also compared with the traditional Demons, thin-plate spline, and B-spline registration methods. The results show that the proposed method allows matching accurately and automatically spots in 2-DE images, and presents significantly improved performance compared to traditional registration methods.

Parameter-Free Elastic Deformation Approach for 2D and 3D Registration Using Prescribed Displacements

A parameter-free approach for non-rigid image registration based on elasticity theory is presented. In contrast to traditional physically-based numerical registration methods, no forces have to be computed from image data to drive the elastic deformation. Instead, displacements obtained with the help of mapping boundary structures in the source and target image are incorporated as hard constraints into elastic image deformation. As a consequence, our approach does not contain any parameters of the deformation model such as elastic constants. The approach guarantees the exact correspondence of boundary structures in the images assuming that correct input data are available. The implemented incremental method allows to cope with large deformations. The theoretical background, the finite element discretization of the elastic model, and experimental results for 2D and 3D synthetic as well as real medical images are presented.