3-D object recognition using 2-D views

We consider the problem of recognizing 3-D objects from 2-D images using geometric models and assuming different viewing angles and positions. Our goal is to recognize and localize instances of specific objects (i.e., model-based) in a scene. This is in contrast to category-based object recognition methods where the goal is to search for instances of objects that belong to a certain visual category (e.g., faces or cars). The key contribution of our work is improving 3-D object recognition by integrating Algebraic Functions of Views (AFoVs), a powerful framework for predicting the geometric appearance of an object due to viewpoint changes, with indexing and learning. During training, we compute the space of views that groups of object features can produce under the assumption of 3-D linear transformations, by combining a small number of reference views that contain the object features using AFoVs. Unrealistic views (e.g., due to the assumption of 3-D linear transformations) are eliminated by imposing a pair of rigidity constraints based on knowledge of the transformation between the reference views of the object. To represent the space of views that an object can produce compactly while allowing efficient hypothesis generation during recognition, we propose combining indexing with learning in two stages. In the first stage, we sample the space of views of an object sparsely and represent information about the samples using indexing. In the second stage, we build probabilistic models of shape appearance by sampling the space of views of the object densely and learning the manifold formed by the samples. Learning employs the Expectation-Maximization (EM) algorithm and takes place in a "universal," lower-dimensional, space computed through Random Projection (RP). During recognition, we extract groups of point features from the scene and we use indexing to retrieve the most feasible model groups that might have produced them (i.e., hypothesis generation). The likelihood of each hypothesis is then computed using the probabilistic models of shape appearance. Only hypotheses ranked high enough are considered for further verification with the most likely hypotheses verified first. The proposed approach has been evaluated using both artificial and real data, illustrating promising performance. We also present preliminary results illustrating extensions of the AFoVs framework to predict the intensity appearance of an object. In this context, we have built a hybrid recognition framework that exploits geometric knowledge to hypothesize the location of an object in the scene and both geometrical and intesnity information to verify the hypotheses.     

3-d object retrieval and recognition with hypergraph analysis

View-based 3-D object retrieval and recognition has become popular in practice, e.g., in computer aided design. It is difficult to precisely estimate the distance between two objects represented by multiple views. Thus, current view-based 3-D object retrieval and recognition methods may not perform well. In this paper, we propose a hypergraph analysis approach to address this problem by avoiding the estimation of the distance between objects. In particular, we construct multiple hypergraphs for a set of 3-D objects based on their 2-D views. In these hypergraphs, each vertex is an object, and each edge is a cluster of views. Therefore, an edge connects multiple vertices. We define the weight of each edge based on the similarities between any two views within the cluster. Retrieval and recognition are performed based on the hypergraphs. Therefore, our method can explore the higher order relationship among objects and does not use the distance between objects. We conduct experiments on the National Taiwan University 3-D model dataset and the ETH 3-D object collection. Experimental results demonstrate the effectiveness of the proposed method by comparing with the state-of-the-art methods.     

Principal axes estimation using the vibration modes of physics-based deformable models.

This paper addresses the issue of accurate, effective, computationally efficient, fast, and fully automated 2-D object orientation and scaling factor estimation. The object orientation is calculated using object principal axes estimation. The approach relies on the object's frequency-based features. The frequency-based features used by the proposed technique are extracted by a 2-D physics-based deformable model that parameterizes the objects shape. The method was evaluated on synthetic and real images. The experimental results demonstrate the accuracy of the method, both in orientation and the scaling estimations.     

一种视频监控中基于航迹的运动小目标检测算法

针对视频监控中运动小目标难以检测的问题,该文提出一种基于航迹的检测算法。首先,为了降低检测漏警率,提出区域纹理特征与差值概率融合的自适应前景提取方法;其次,为了降低检测虚警率,设计航迹关联的概率计算模型以建立疑似目标在视频帧间的关联,并设置双门限以区分疑似目标中的真实目标与虚假目标。实验结果表明,与多种经典算法相比,该算法能对定量范围内的运动小目标以更低的漏警率和虚警率实施准确检测。     

应用图像融合与多样性的舰船显著性检测

基于单源的图像显著性检测存在较大的虚警或漏检,文章提出了利用约简后的特征点和CPD算法对海面实拍船只图像进行多源图像匹配,获得图像间的变换投影方程并利用投影方程对单源图像的显著性检测结果进行叠加与虚警控制器分类,从而达到提高检测率与控制虚警的目的。显著性检测方面,文章分析了基于图等级多样性的显著性检测方法的不足和优点,引入了最大稳定区域检测方法对图像做前期处理,并对获得区域进行联合获得新区域,使得新区域能够最大限度地满足基于图的等级多样性显著性检测最优条件。对于检测获得的联合区域目标显著性不完整的情况,利用了区域的叠加性进行加权求和,最终获得了具有较好联通性的多舰船目标图像显著性检测结果。对于显著性检测结果中存在较大虚警的情况,文章进一步提出计算船只与浪花的多尺度分形维数,并结合Adaboost算法训练浪花虚警控制器。实验结果显示控制器能够消除一部分浪花带来的虚警,但是对于灰度与舰船极为相似的虚警无法消除。     

Detection filters and algorithm fusion for ATR.

Detection involves locating all candidate regions of interest (objects) in a scene independent of the object class with object distortions and contrast differences, etc., present. It is one of the most formidable problems in automatic target recognition, since it involves analysis of every local scene region. We consider new detection algorithms and the fusion of their outputs to reduce the probability of false alarm P(FA) while maintaining high probability of detection P(D). Emphasis is given to detecting obscured targets in infrared imagery.     

Three-dimensional reconstruction of live embryos using roboticmacroscope images

To determine the three-dimensional (3-D) shape of a live embryo is a technically challenging task. The authors show that reconstructions of live embryos can be done by collecting images from different viewing angles using a robotic macroscope, establishing point correspondences between these views by block matching, and using a new 3-D reconstruction algorithm that accommodates camera positioning errors. The algorithm assumes that the images are orthographic projections of the object and that the camera scaling factors are known. Point positions and camera errors are found simultaneously. Reconstructions of test objects and embryos show that meaningful reconstructions are possible only when camera positioning and alignment errors are accommodated since these errors can be substantial. Reconstructions of early-stage axolotl embryos were made from sets of 33 images. In a typical reconstruction, 781 points, each visible in at least three different views, were used to form 1511 triangles to represent the embryo surface. The resulting reconstruction had a mean radius of error of 0.27 pixels (1.1 μm). Mathematical properties of the reconstruction algorithm are identified and discussed     

Validation of 3-D curved objects: CAD model and fabricatedworkpiece

This paper proposes a new method to describe and identify a 3-D curved object for the purpose of validating a fabricated object to the design specification. Curved 3-D objects are, in general, difficult to represent and identify because they lack distinct properties such as edges, planes, or cylindrical surfaces which are the building blocks in representing objects. In this paper, the authors propose to use principal axes of a 3-D object to establish a reference for the representation. A method of obtaining an inertia matrix from a 3-D range image is developed. The unique set of principal axes is obtained from the inertia matrix of an object with an arbitrary 3-D position and orientation, and the object can be described uniquely on these principal axes. On the principal axes, an object is described by a set of features describing the shape of the object such as spine, section size, section orientation, and section contraction. The features are used for comparing two objects for the validation purpose. The authors also propose a direct measure of similarity between two objects as a mean-squared difference of radii. As an experiment, two 3-D object models are designed through a CAD package, and fabricated objects are compared with the designed models for validation purposes     

Multimedia ambiance communication

The photo-realistic 3-D image space of multimedia ambiance communication offers enhanced interpersonal communication. Formed by taking the laws of perspective and the characteristics of human visual perception into account, the space provides a natural environment that users can feel to be a part of. It is based on the concept of a three-layer structure, with long-, mid-, and short-range views. We constructed a testbed for multimedia ambiance communication consisting of a high-speed graphics computer and a curved screen onto which images are stereoscopically projected from the rear, and developed a three-camera system for capturing environment images. In addition, we developed the two-plane expression for processing backdrop views and highly efficient mid-range views. Finally, we constructed a photo-realistic 3-D image space using these image processing techniques     

Registration of image sets using silhouette consistency

A new algorithm is described for estimating the change in orientation and position of an object in two sets of images. The images within each set are calibrated but the exact geometrical relationship between the two sets of views is unknown. Variations in the two-dimensional silhouette of a fixed and rigid three-dimensional object, as the viewpoint is changed, are analysed to estimate the relative position and orientation of the object in the two different image sets. The main advantage of this method is that no explicit point, or line, correspondences need be identified; the only requirement is for reliable segmentation of the object from the background. It is shown that an incorrect estimate of the relative object pose gives rise to silhouettes which are inconsistent in that they violate a certain geometrical constraint. The extent to which the images are consistent is quantified using a certain consistency metric. Standard minimisation techniques are then used to obtain accurate estimates for both rotational and translational parameters. Results are presented for the registration of synthetic images, with added noise, and for the registration of real image data. For small test objects the relative orientation estimates are consistent to within ±6 degrees and the relative translation estimates to ±1.8 mm     

Tag surface reconstruction and tracking of myocardial beads from SPAMM-MRI with parametric B-spline surfaces

Magnetic resonance imaging (MRI) is unique in its ability to noninvasively and selectively alter tissue magnetization, and create tag planes intersecting image slices. The resulting grid of signal voids allows for tracking deformations of tissues in otherwise homogeneous-signal myocardial regions. In this paper, we propose a specific spatial modulation of magnetization (SPAMM) imaging protocol together with efficient techniques for measurement of three-dimensional (3-D) motion of material points of the human heart (referred to as myocardial beads) from images collected with the SPAMM method. The techniques make use of tagged images in orthogonal views by explicitly reconstructing 3-D B-spline surface representation of tag planes (tag planes in two orthogonal orientations intersecting the short-axis (SA) image slices and tag planes in an orientation orthogonal to the short-axis tag planes intersecting long-axis (LA) image slices). The developed methods allow for viewing deformations of 3-D tag surfaces, spatial correspondence of long-axis and short-axis image slice and tag positions, as well as nonrigid movement of myocardial beads as a function of time.     

基于多向背景预测的红外弱小目标检测

杂波背景中的弱小目标检测是红外图像处理中的一个重要问题。普通的二维滤波背景预测方法可以用来检测图像中的小目标,但是也存在对复杂场景的适应性差,杂波边缘虚警高的问题。通过分析二维最小均方滤波背景预测算法的方向特性,在对图像四邻域滤波残差进行像素级加权融合后,得到了一种基于多方向融合自适应滤波背景预测的弱小目标检测方法。对构造图像和实际红外云杂波场景中的小目标检测仿真表明,该方法对不同背景适应性较强,在保持目标检测概率的同时显著抑制了杂波边缘虚警,有效提高了杂波背景中小目标的检测性能。      

A statistical approach to landmine detection using broadbandelectromagnetic induction data

The response of time-domain electromagnetic induction (EMI) sensors, which have been used almost exclusively for landmine detection, is related to the amount of metal present in the object and its distance from the sensor. Unluckily, there is often a significant amount of metallic clutter in the environment that also induces an EMI response. Consequently, EMI sensors employing detection, algorithms based solely on metal content suffer from large false alarm rates. To mitigate this false alarm problem for mines with substantial metal content, statistical algorithms have been developed that exploit models of the underlying physics. In such models it is commonly assumed that the soil has a negligible effect on the sensor response, thus the object is modeled in "free space." We report on studies that were performed to test, the hypotheses that for broadband EMI sensors: 1) soil cannot be modeled as free space when the buried object has low metal content and 2) advanced signal processing algorithms can be applied to reduce the false alarm rates. Our results show that soil cannot be modeled as free space and that when modeling soil correctly our advanced algorithms reduced the false alarm probability by up to a factor of 10 in blind tests     

基于时空域的暗弱空间运动点目标检测算法

为了对空间目标进行精确定位与跟踪,建立目标运动轨迹,该文对基于运动信息的星图暗弱空间运动点目标检测算法进行研究。首先建立一种新的空间运动点目标描述模型,然后提出基于相关系数矩阵的运动点目标检测算法,最后提取目标运动轨迹,并给出了点目标运动速度的估计模型。根据实测数据和硬件平台,提出了检测概率和虚警率相结合的评价方法对算法进行验证。试验结果表明,所提方法能够在保持较低的虚警概率下获得较高的检测概率,优于参与比较的其它目标检测方法。与单纯扩大望远镜口径相比,该方法为提高空间暗弱目标识别能力提供了具有更高性价比的有效途径。     

Image super-resolution by curve fitting in the threshold decomposition domain

A new curve-fitting scheme is proposed in this paper to produce super-resolution images from a single low-resolution source image. The most unique feature of this method is that the threshold decomposition is performed on the given source image to obtain multiple binary images so that the curve-fitting applied on each resulted binary image can be made very efficient and accurate, thus allowing us to focus on tiny objects and thin structures so as to achieve rather nice visual results even when a large up-scaling factor is used. Two novel techniques are further proposed to improve the visual quality: (1) a spreading technique (applied on some significant pixels detected in each threshold decomposed binary image) is used to remove ladder-like false edges that often appear visually in super-resolution images, and (2) an edge correction (guided by the edge information extracted from the original source image) is used to sharpen all inherent edges. Our results are compared with those achieved by using the state-of-arts techniques, showing the ability of our algorithm to achieve a better visual quality in smooth areas as well as for sharp edges and small objects.     

微透镜阵列实现3维物体旋转不变实时识别

为了实现3维物体旋转不变实时识别,应用微透镜阵列的多视角成像特点,利用透射像阵列的高关联性,实现3维物体信息与2维透射像阵列信息之间的转换,从而可以利用光学2维图像识别技术实现3维物体的识别。对转换和识别过程进行了理论分析,用匹配滤波的方法进行了实验验证,实现了3维物体旋转不变实时识别。得到了良好的识别效果,并实现了旋转方向的准确定位和旋转角度大小的比较判别。结果表明,应用微透镜阵列可以实现旋转3维物体旋转不变实时识别。     

均匀分布地杂波中检测目标的统计分析

简要叙述了常规雷达在高斯噪声环境下检测目标时的发现概率、虚警概率和信噪比的关系，并在此基础上，结合目前很多雷达采用杂波单元平均法进行目标检测的情况，分析了均匀分布杂渡的统计特性，得出了在杂波分量远大于噪声分量的检测过程中发现概率、虚警概率和信杂比三者的关系。对于常规雷达的检测理论，这是一个新的补充。     

Determination of optimal angiographic viewing angles: basic principles and evaluation study

Foreshortening of vessel segments in angiographic (biplane) projection images may cause misinterpretation of the extent and degree of coronary artery disease. The views in which the object of interest are visualized with minimum foreshortening are called optimal views. The authors present a complete approach to obtain such views with computer-assisted techniques. The object of interest is first visualized in two arbitrary views. Two landmarks of the object are manually defined in the two projection images. With complete information of the projection geometry, the vector representation of the object in the three-dimensional space is computed. This vector is perpendicular to a plane in which the views are called optimal. The user has one degree of freedom to define a set of optimal biplane views. The angle between the central beams of the imaging systems can be chosen freely. The computation of the orientation of the object and of corresponding optimal biplane views have been evaluated with a simple hardware phantom. The mean and the standard deviation of the overall errors in the calculation of the optimal angulation angles were 1.8 degrees and 1.3 degrees , respectively, when the user defined a rotation angle.