How to put probabilities on homographies

We present a family of "normal" distributions over a matrix group together with a simple method for estimating its parameters. In particular, the mean of a set of elements can be calculated. The approach is applied to planar projective homographies, showing that using priors defined in this way improves object recognition.     

Augmented reality camera tracking with homographies

To realistically integrate 3D graphics into an unprepared environment, camera position must be estimated by tracking natural image features. We apply our technique to cases where feature positions in adjacent frames of an image sequence are related by a homography, or projective transformation. We describe this transformation's computation and demonstrate several applications. First, we use an augmented notice board to explain how a homography, between two images of a planar scene, completely determines the relative camera positions. Second, we show that the homography can also recover pure camera rotations, and we use this to develop an outdoor AR tracking system. Third, we use the system to measure head rotation and form a simple low-cost virtual reality (VR) tracking solution.     

Multiview photometric stereo

This paper addresses the problem of obtaining complete, detailed reconstructions of textureless shiny objects. We present an algorithm which uses silhouettes of the object, as well as images obtained under changing illumination conditions. In contrast with previous photometric stereo techniques, ours is not limited to a single viewpoint but produces accurate reconstructions in full 3D. A number of images of the object are obtained from multiple viewpoints, under varying lighting conditions. Starting from the silhouettes, the algorithm recovers camera motion and constructs the object's visual hull. This is then used to recover the illumination and initialise a multi-view photometric stereo scheme to obtain a closed surface reconstruction. There are two main contributions in this paper: Firstly we describe a robust technique to estimate light directions and intensities and secondly, we introduce a novel formulation of photometric stereo which combines multiple viewpoints and hence allows closed surface reconstructions. The algorithm has been implemented as a practical model acquisition system. Here, a quantitative evaluation of the algorithm on synthetic data is presented together with complete reconstructions of challenging real objects. Finally, we show experimentally how even in the case of highly textured objects, this technique can greatly improve on correspondence-based multi-view stereo results.     

Visual map‐less navigation based on homographies

We introduce a method for autonomous robot navigation based on homographies computed between the current image and images taken in a previous teaching phase with a monocular vision system. The features used to estimate the homography are vertical lines automatically extracted and matched. From homography, the underlying motion correction between the reference path and the current robot location is computed. The proposed method, which uses a sole calibration parameter, has turned out to be especially useful to correct heading and lateral displacement, which are critical in systems based on odometry. We have tested the proposal in simulation, and with real images. Besides, the visual system has been integrated into an autonomous wheelchair for handicapped, working in real time with robustness. © 2005 Wiley Periodicals, Inc.     

Multiple homographies with omnidirectional vision for robot homing

Two relevant issues in vision-based navigation are the field-of-view constraints of conventional cameras and the model and structure dependency of standard approaches. A good solution of these problems is the use of the homography model with omnidirectional vision. However, a plane of the scene will cover only a small part of the omnidirectional image, missing relevant information across the wide range field of view, which is the main advantage of omnidirectional sensors. The interest of this paper is in a new approach for computing multiple homographies from virtual planes using omnidirectional images and its application in an omnidirectional vision-based homing control scheme. The multiple homographies are robustly computed, from a set of point matches across two omnidirectional views, using a method that relies on virtual planes independently of the structure of the scene. The method takes advantage of the planar motion constraint of the platform and computes virtual vertical planes from the scene. The family of homographies is also constrained to be embedded in a three-dimensional linear subspace to improve numerical consistency. Simulations and real experiments are provided to evaluate our approach.     

Hierarchical Multiview Rigid Registration

Registration is a key step in the 3D reconstruction of real‐world objects. In this paper, we propose a hierarchical method for the rigid registration of multiple views. The multiview registration problem is solved via hierarchical optimization defined on an undirected graph. Each node or edge in this graph represents a single view or a connection between two overlapped views, respectively. The optimizations are performed hierarchically on the edges, the loops, and the entire graph. First, each overlapped pair of views is locally aligned. Then, a loop‐based incremental registration algorithm is introduced to refine the initial pairwise alignments. After a loop is registered, the views in the loop are merged into a metaview in the graph. Finally, global error diffusion is applied to the entire graph to evenly distribute the accumulated errors to all views. In addition, a new objective function is defined to describe the loop closure problem; it improves the accuracy and robustness of registration by simultaneously considering transformation and registration errors. The experimental results show that the proposed hierarchical approach is accurate, efficient and robust for initial view states that are not well posed.     

基于多样性的多视图低秩稀疏子空间聚类算法

本文主要研究如何通过挖掘多视图特征的多样性信息来促进多视图聚类,提出了基于多样性的多视图低秩稀疏子空间聚类算法。该方法直接将视图多样性概念应用于多视图低秩稀疏子空间聚类算法框架中,确保不同视图的子空间表示矩阵的多样性;为了实现多个视图聚类一致性同时达到提高聚类性能的目标,在该框架中引入谱聚类算法共同优化求解。通过对3个图像数据集的实验验证了该算法的有效性,同时其聚类的性能优于已有的单视图及多视图算法。     

多视点视频编码混合快速搜索算法

EPZS是联合多视点视频编码(JMVC,Joint Multi-view Video Coding)运动估计中采用的一种预测搜索算法,其搜索速度慢.针对EPZS算法的性能不足,我们在预测矢量集合、搜索模型、阈值设置和搜索策略四个方面进行改进,提出了一种混合快速搜索算法.在联合多视点视频编码测试平台JMVC8.3中,对三个由平行摄像机采集的多视点视频测试序列BallRoom、Exit和Vassar进行测试.实验结果表明:在保证视频重建质量和码率的前提下,与Jmvc中的EPZS算法相比,编码速度平均提高了55.66％ ～69.62％,改进算法的效果明显,编码效率得以提高.     

基于正交基的多视图迁移谱聚类

挖掘多视图一致性是提升多视图聚类性能的关键,为更好地从多视图数据中学习一致性表示,提出一种新的多视图聚类算法OMTSC。OMTSC算法同时学习每个视图的聚类分配矩阵和特征嵌入,并将聚类分配矩阵分解为共享正交基矩阵和聚类编码矩阵。正交基矩阵可捕获并储存多视图一致性信息形成潜在聚类中心,经过加权融合的多视图聚类编码矩阵可更好地平衡不同视图的质量差异。引入基于二部图的协同聚类,实现正交基、聚类编码和特征嵌入3个矩阵的知识相互迁移,以提升多视图数据一致性和多样性,并利用特征嵌入的多样性最大化多视图一致性学习最优的潜在聚类中心,从而提高多视图聚类的性能。此外,基于群稀疏约束的特征嵌入可有效消除多视图数据中的噪声,提升算法的鲁棒性。在WikipediaArticles、COIL20和ORL数据集上的实验结果表明,与SC-Best、Co-Reg等先进的多视图聚类算法相比,OMTSC算法在ACC、NMI、ARI 3个评价指标上整体取得最优值,其中在COIL20和ORL数据集中的NMI评价指标均高于0.9。     

基于多视图边界判别投影的高光谱图像分类

高光谱图像分类是遥感领域研究的热点问题,其关键在于利用高光谱图谱合一的 优势,同时融合高光谱图像中各个像元位置的光谱信息和空间信息,提高光谱图像分类精度。 针对高光谱图像特征维数高和冗余信息多等问题,采用多视图子空间学习方法进行特征降维, 提出了图正则化的多视图边界判别投影算法。将每个像元处的光谱特征看作一个视图,该像元 处的空间特征看作另一个视图,通过同时优化每个视图上的投影方向来寻找最优判别公共子空 间。公开测试数据集上的分类实验表明,多视图学习在高光谱图像空谱融合分类方面具有显著 的优越性,在多视图降维算法中,该算法具有最高的分类准确性。     

基于视差估计算法的多视点视频预测方案

多视点视频编码是立体视频的关键技术,视差估计是目前多视点视频编码中常用的方法之一.探讨了多视点视频编码中的视差估计算法原理,对当前应用视差估计算法的几种典型预测结构进行了深入分析,提出一种结合分级B图与视点相关性的多视点编码方案,该方案在H.264/AVC的编码模型JM下实现.实验表明,该方案在兼顾随机访问性能的同时,实现了较高的编码效率,尤其适合视点间相关性较高的运动图像序列.     

Multiview Visibility Estimation for Image-Based Modeling

In this paper, we investigate the problem of determining regions in 3D scene visible to some given viewpoints when obstacles are present in the scene. We assume that the obstacles are composed of some opaque objects with closed surfaces. The problem is formulated in an implicit framework where the obstacles are represented by a level set function. The visible and invisible regions of the given viewpoints are determined through an efficient implicit ray tracing technique. As an extension of our approach, we apply the multiview visibility estimation to an image-based modeling technique. The unknown scene geometry and multiview visibility information are incorporated into a variational energy functional. By minimizing the energy functional, the true scene geometry as well as the accurate visibility information of the multiple views can be recovered from a number of scene images. This makes it feasible to handle the visibility problem of multiple views by our approach when the true scene geometry is unknown.     

Dense mirroring surface recovery from 1D homographies and sparse correspondences

In this work, we recover the 3D shape of mirrors, sunglasses, and stainless steel implements. A computer monitor displays several images of parallel stripes, each image at a different angle. Reflections of these stripes in a mirroring surface are captured by the camera. For every image point, the direction of the displayed stripes and their reflections in the image are related by a 1D homography matrix, computed with a robust version of the statistically accurate heteroscedastic approach. By focusing on a sparse set of image points for which monitor-image correspondence is computed, the depth and the local shape may be estimated from these homographies. The depth estimation relies on statistically correct minimization and provides accurate, reliable results. Even for the image points where the depth estimation process is inherently unstable, we are able to characterize this instability and develop an algorithm to detect and correct it. After correcting the instability, dense surface recovery of mirroring objects is performed using constrained interpolation, which does not simply interpolate the surface depth values but also uses the locally computed 1D homographies to solve for the depth, the correspondence, and the local surface shape. The method was implemented and the shape of several objects was densely recovered at submillimeter accuracy.     

Practical Global Optimization for Multiview Geometry

This paper presents a practical method for finding the provably globally optimal solution to numerous problems in projective geometry including multiview triangulation, camera resectioning and homography estimation. Unlike traditional methods which may get trapped in local minima due to the non-convex nature of these problems, this approach provides a theoretical guarantee of global optimality. The formulation relies on recent developments in fractional programming and the theory of convex underestimators and allows a unified framework for minimizing the standard L ₂-norm of reprojection errors which is optimal under Gaussian noise as well as the more robust L ₁-norm which is less sensitive to outliers. Even though the worst case complexity of our algorithm is exponential, the practical efficacy is empirically demonstrated by good performance on experiments for both synthetic and real data. An open source MATLAB toolbox that implements the algorithm is also made available to facilitate further research.     

图的多视角一致性稀疏聚类

提出了一种新的面向图的一致性多视角稀疏聚类框架,该方法先将多视角数据分解为一致性与不一致性部分;然后采用相似性度量方法与KNN(K-nearest neighbor)算法对多视角数据进行分解与融合;再运用稀疏表示学习多视角图的一致性相似矩阵,进而通过谱聚类获取聚类结果.最后,设计并实现了一种交替迭代优化算法求解目标函数,并在八个多视角数据集上通过对比实验验证了该方法的有效性.