几何联合分段亮度的线阵图像配准

目的 以非平行于目标的姿态成像时,线阵相机采集的图像的几何变换规律与面阵相机不同,这导致面阵图像的几何变换模型及其直接配准方法无法实现线阵图像的配准;同时,亮度恒常假设无法解决大视场镜头引起的图像亮度衰减问题。因此,提出了一种几何联合分段亮度的线阵图像直接配准方法。方法 根据线阵图像的几何变换模型和分段增益—偏置亮度模型,将线阵图像的配准问题表示为一个非线性最小二乘问题。采用高斯—牛顿法对配准问题中的几何变换参数和亮度变换参数联合进行优化;此外,针对以单位变换为初始值时配准图像存在较大几何误差致使优化不收敛,设计了一种初始值快速搜索策略。结果 实验数据包含本文采集的线阵图像数据集和真实列车线阵图像。配准结果表明,采用本文方法配准后的标注点坐标均方根误差均小于1个像素,优于采用面阵图像几何变换模型的直接配准方法。算法对亮度变化具有更强的鲁棒性,提高了线阵图像配准的成功率。结论 本文提出的几何联合分段亮度线阵图像配准方法可以精确、鲁棒地对齐非平行姿态线阵相机所采集的图像。     

Joint photometric and geometric image registration in the total least square sense

This paper presents a novel robust image alignment technique that performs joint geometric and photometric registration in the total least square (TLS) sense. Therefore, we employ the total least square metric instead of the ordinary least square (OLS) metric, which is commonly used in the literature. While the OLS model is sufficient to tackle geometric registration problems, it gives no mutually consistent estimates when dealing with photometric deformations. By introducing a new TLS model, we obtain mutually consistent parameters. Experimental results show that our method is indeed more consistent and accurate in presence of noise compared to existing joint registration algorithms.     

Applicability of the SIFT operator to geometric SAR image registration

The SIFT operator's success for computer vision applications makes it an attractive alternative to the intricate feature based SAR image registration problem. The SIFT operator processing chain is capable of detecting and matching scale and affine invariant features. For SAR images, the operator is expected to detect stable features at lower scales where speckle influence diminishes. To adapt the operator performance to SAR images we analyse the impact of image filtering and of skipping features detected at the highest scales. We present our analysis based on multisensor, multitemporal and different viewpoint SAR images. The operator shows potential to become a robust alternative for point feature based registration of SAR images as subpixel registration consistency was achieved for most of the tested datasets. Our findings indicate that operator performance in terms of repeatability and matching capability is affected by an increase in acquisition differences within the imagery. We also show that the proposed adaptations result in a significant speed-up compared to the original SIFT operator.     

New UAV image registration method based on geometric constrained belief propagation

Multimedia Tools and Applications - Image registration is a crucial step in the field of computer vision. However, the traditional scale invariant feature transform (SIFT) based method often...     

New feature points based on geometric invariants for 3D image registration

We introduce in this paper a new type of feature points of 3D surfaces, based on geometric invariants. We call this new type of feature points the extremal points of the 3D surfaces, and we show that the relative positions of those 3D points are invariant according to 3D rigid transforms (rotation and translation). We show also how to extract those points from 3D images, such as Magnetic Resonance images (MRI) or Cat-Scan images, and also how to use them to perform precise 3D registration. Previously, we described a method, called the Marching Lines algorithm, which allow us to extract the extremal lines, which are geometric invariant 3D curves, as the intersection of two implicit surfaces: the extremal points are the intersection of the extremal lines with a third implicit surface. We present an application of the extremal points extraction to the fully automatic registration of two 3D images of the same patient, taken in two different positions, to show the accuracy and robustness of the extracted extremal points.     

Medical image segmentation, volume representation and registration using spheres in the geometric algebra framework

This paper presents an algorithm to model volumetric data and other one for non-rigid registration of such models using spheres formulated in the geometric algebra framework. The proposed algorithm for modeling, as opposite to the Union of Spheres method, reduces the number of entities (spheres) used to model 3D data. Our proposal is based in marching cubes idea using, however, spheres, while the Union of Spheres uses Delaunay tetrahedrization. The non-rigid registration is accomplished in a deterministic annealing scheme. At the preprocessing stage we segment the objects of interest by a segmentation method based on texture information. This method is embedded in a region growing scheme. As our final application, we present a scheme for surgical object tracking using again geometric algebra techniques.     

基于几何特征相似度评价的跨尺度显微图像配准

原子力显微镜能够在光学显微镜的协助下, 克服自身成像范围的限制获得更大的成像视野, 同时保证纳米 级的成像精度. 该方法需要实现原子力显微镜成像结果在光学视野中的精确定位, 而解决该问题的关键是进行两种 显微图像之间的准确配准. 因此, 本文提出了一种基于几何特征相似度评估的跨尺度图像配准算法, 为进一步在原 子力/光学显微镜共焦系统中实现精确定位和成像提供了基础. 具体而言, 本文首先利用原子力显微镜的探针在样 品表面进行压印, 刻画出固定尺寸的几何图案,用以标定原子力显微镜和光学显微镜成像尺度之间的比例, 为图像 配准提供先验知识. 随后, 本文设计了一种先进的图像处理算法, 分别提取原子力/光学显微镜图像中几何图案的特 征, 并将其存储为内角向量和边长向量. 最后, 基于成像尺度比例和几何特征, 提出了一种新型的几何特征相似度 评价函数, 通过对内角特征相似度和边长特征相似度进行加权融合, 实现高精度的跨尺度显微图像配准. 实验部分 针对四种不同几何图案进行图像配准, 并对实验结果进行详细分析, 验证了本文方法的良好性能.     

几何特征在点云配准中的应用

提出一种基于几何特征的三维数据配准算法。该算法针对点云中各点p_i的k邻近点Nbhd(p_i)构造三棱锥体,将三棱锥体各侧棱p_iv_j（j=1,2,...,）和其中轴线p_io的夹角记作θⁱ_j,所有夹角按照右手系来依次形成夹角序列（θⁱ₁θⁱ_2...）作为三棱锥的几何特征。通过比较三棱锥体的几何特征来确定有效点对。算法实现时,首先对初始数据通过抽取有效点对,建立名义上的对应关系,然后采用四元组法求得坐标变换的旋转和平移矩阵,实现数据配准。     

Digital image registration using projections

In many application fields (e.g., aerospace and biomedical image processing), one has to deal with a sequence of images whose observation is made difficult by unpredictable relative movements of the camera and the scene. In order to obtain a stable display, the displacement of each image in the sequence with respect to one chosen as a reference must be preliminarily determined. This would usually require two-dimensional algorithms, involving a considerable computational effort. This work discusses a new algorithm for image registration, which requires only one-dimensional Fourier transformations. Preliminary experimental results are reported.     

基于特征匹配的亚像素级全景图像配准算法

为了提高全景图全自动拼接中图像配准的速度和匹配稳健性,提出了一种基于相对距离法去除外点的亚像素级图像配准算法,并给出了分析和实验结果,亚像素级像素定位误差在0.01~0.1之内。在对12组图像匹配的实验结果表明,该匹配算法的匹配正确率达到100%,且匹配的时间小于目前通用的RANSAC匹配算法。     

Translational photometric alignment of single-view image sequences

Photometric stereo is a well-established method to estimate surface normals of an object. When coupled with depth-map estimation, it can be used to reconstruct an object’s height field. Typically, photometric stereo requires an image sequence of an object under the same viewpoint but with differing illumination directions. One crucial assumption of this configuration is perfect pixel correspondence across images in the sequence. While this assumption is often satisfied, certain setups are susceptible to translational errors or misalignments across images. Current methods to align image sequences were not designed specifically for single-view photometric stereo. Thus, they either struggle to account for changing illumination across images, require training sets, or are overly complex for these conditions. However, the unique nature of single-view photometric stereo allows one to model misaligned image sequences using the underlying image formation model and a set of translational shifts. This paper introduces such a technique, entitled translational photometric alignment, that employs the Lambertian model of image formation. This reduces the alignment problem to minimizing a nonlinear sum-squared error function in order to best reconcile the observed images with the generative model. Thus, the end goal of translational photometric alignment is not only to align image sequences, but also to produce the best surface-normal estimates given the observed images. Controlled experiments on the Yale Face Database B demonstrate the high accuracy of translational photometric alignment. The utility and benefits of the technique are further illustrated by additional experiments on image sequences suffering from uncontrolled real-world misalignments.     

A modified medical image registration

Medical image registration is commonly used in clinical diagnosis, treatment, quality assurance, evaluation of curative efficacy and so on. In this paper, the edges of the original reference and floating images are detected by the B-spline gradient operator and then the binarization images are acquired. By computing the binarization image moments, the centroids are obtained. Also, according to the binarization image coordinates, the rotation angles of the reference and floating images are computed respectively, on the foundation of which the initial values for registering the images are produced. When searching the optimal geometric transformation parameters, the modified peak signal-to-noise ratio (MPSNR) is viewed as the similarity metric between the reference and floating images. At the same time, the simplex method is chosen as multi-parameter optimization one. The experimental results show that, this proposed method has a fairly simple implementation, a low computational load, a fast registration and good registration accuracy. It also can effectively avoid trapping in the local optimum and is adapted to both mono-modality and multi-modality image registrations. Also, the improved iterative closest point algorithm based on acquiring the initial values for registration from the least square method (LICP) is introduced. The experiments reveal that the measure acquiring the initial values for registration from image moments and the least square method (LSM) is feasible and resultful strategy.     

Image registration using Markov random coefficient and geometric transformation fields

Image registration is central to different applications such as medical analysis, biomedical systems, and image guidance. In this paper we propose a new algorithm for multimodal image registration. A Bayesian formulation is presented in which a likelihood term is defined using an observation model based on coefficient and geometric fields. These coefficients, which represent the local intensity polynomial transformations, as the local geometric transformations, are modeled as prior information by means of Markov random fields. This probabilistic approach allows one to find optimal estimators by minimizing an energy function in terms of both fields, making the registration between the images possible.     

An automatic image registration and overlay system

In this paper we present an automatic algorithm for registering and overlaying imagery. The algorithm basically attempts to find by successive approximations the best affine transformation or second order polynomial relating to the two images. The method requires the specification of only a matching pair of control points, then new control points are found approximately by extrapolating the old affine transformation to larger areas and then using correlation to find the best match. Thus an obvious advantage of this algorithm lies in its automatic features in locating and matching more potential ground control points. This paper also discusses the effect of the distribution of control points on the affine transformation. Finally, the method is tested on Landsat data and the results are discussed.     

Efficient and accurate image based camera registration

A technique for efficient and accurate camera registration based on stereo image analysis is presented. Initially, few correspondences are estimated with high accuracy using a probabilistic relaxation technique. Accuracy is achieved by considering the continuous approximations of selected image areas using second order polynomials and a relaxation rule defined according to the likelihood that estimates obey stereoscopic constraints. The extrinsic camera parameters are then obtained using a novel efficient and robust approach derived from the classic eight point algorithm. Efficiency is achieved by solving a parametric linear optimization problem rather than a nonlinear one as more conventional methods attempt to do. Robustness is obtained by applying two novel strategies: normalization of the initial data via a simple but efficient diagonal scaling approach, and regularization of the underlying linear parametric optimization problem using meaningful constraints. The performance of the presented methods is assessed in several computer experiments using natural video data.     

Graph-based markerless registration of city maps using geometric hashing

Recently, augmenting paper maps with additional dynamic information on mobile devices has become popular. A central task in this context is to register high-resolution paper maps to digital maps on a mobile device, which was typically performed by means of RFID tags or visual markers on specially prepared paper maps. In this paper we present a novel graph-based approach for a markerless registration of city maps. The goal is to find the best registration between a given image, which shows a small part of a city map, and stored map data. The proposed method creates a graph representation of a given input image and robustly finds an optimal registration using a geometric hashing technique. It is translation, scale and rotation invariant, and robust against noise and missing data. Experiments on both synthetic and real data are presented to demonstrate the algorithmic performance.     

半自动全向图与卫星遥感图快速配准

折反射全向图和卫星遥感图配准属于异构传感器图像配准问题,目前快速有效的解决方法比较少,但应用需求又比较多,鉴于此,提出了一种基于等角原理的半自动快速配准算法。通过全向Hough变换方法提取全向图中建筑物顶部轮廓直线,同时手工找出卫星图中建筑物顶部轮廓直线,通过角度关系结合投票方法计算出全向图可能拍摄位置,并用所有可能位置组成可行集,从可行集中选出最满意解。仿真实验与实景实验均表明该方法快速有效。     

Learning geometric and photometric features from panoramic LiDAR scans for outdoor place categorization

Semantic place categorization, which is one of the essential tasks for autonomous robots and vehicles, allows them to have capabilities of self-decision and navigation in unfamiliar environments. In particular, outdoor places are more difficult targets than indoor ones due to perceptual variations, such as dynamic illuminance over 24 hours and occlusions by cars and pedestrians. This paper presents a novel method of categorizing outdoor places using convolutional neural networks (CNNs), which take omnidirectional depth/reflectance images obtained by 3D LiDARs as the inputs. First, we construct a large-scale outdoor place dataset named Multi-modal Panoramic 3D Outdoor (MPO) comprising two types of point clouds captured by two different LiDARs. They are labeled with six outdoor place categories: coast, forest, indoor/outdoor parking, residential area, and urban area. Second, we provide CNNs for LiDAR-based outdoor place categorization and evaluate our approach with the MPO dataset. Our results on the MPO dataset outperform traditional approaches and show the effectiveness in which we use both depth and reflectance modalities. To analyze our trained deep networks, we visualize the learned features.     

Digital image registration by sequential analysis

This paper proposes a new approach to translational image registration problems, based on the theory of sequential tests of hypotheses (S.T.H.). This leads to the development of two different methods: the first one is based on the Gaussian assumption and uses the fact that the variance of the error between two images to be registered tends to be low on the registration point. The second method uses binary images derived from the original ones. The statistical model for the resulting accumulated error is a binomial distribution and the registration position is characterized by a low probability of the binary error being one. In both methods two sequences of thresholds are employed: one leading to the rejection of the point and the other one to the eventual acceptance of it. Experimental results with both methods are presented. They include registration of a LANDSAT image against noisy versions of it, matching of different channels of the same multispectral image as well as matching of segments of two images taken at different dates. Successful registration was achieved in most cases even in low signal to noise ratio conditions, with a modest amount of computational effort.