一种室外非理想光照条件下的立体匹配算法

针对室外非理想光照条件和图像低纹理、低对比度造成立体匹配效果较差的问题,提出一种HSL(色相-饱和度-亮度)颜色空间下基于边缘图分割的立体匹配算法.区别于传统的RGB颜色空间下基于像素强度的度量方式,该算法采用一种HSL颜色空间下的像素非相似性度量公式来获得匹配代价,然后基于左右输入图像的边缘检测结果进行图像区域分割和立体匹配.在实验中采用一系列不同光照条件的图片集和具有明显低纹理区域的图片集,对本文算法与现有算法进行对比验证.实验结果证明,该算法能够得到比较理想的视差图,对非理想的光照条件和低纹理图像具有很好的鲁棒性,并且基本达到实时性要求.     

基于多邻域支持技术的迭代式角点匹配算法

角点匹配是立体视觉研究中的一个重要问题,文中针对该问题提出一种基于多邻域支持技术的迭代式角点匹配算法.该算法首先使用Marr和Frisby提出的立体匹配的五大约束限定搜索区域,然后使用了多邻域支持技术对点特征相似性的评价方法进行了改进,最后引入了左/右以及上/下两种对称性测试过程和迭代技术以提高匹配的精度.这些技术解决了传统匹配算法实时性差、精确度低的问题.仿真实验表明,该算法是一种快速、稳定并且实用的角点匹配算法.     

An intensity-based cooperative bidirectional stereo matching with simultaneous detection of discontinuities and occlusions

This paper presents a new intensity-based stereo algorithm using cooperative bidirectional matching with a hierarchical multilevel structure. Based on a new model of piecewise smooth depth fields and the consistency constraint, the algorithm is able to estimate the 3-D structure and detect its discontinuities and the occlusion reliably with low computational costs. In order to find the global optimal estimates, we utilize a multiresolution two-stage algorithm minimizing nonconvex cost functions, which is equivalent to the MAP estimation. This basic framework computing the 3-D structure from binocular stereo images has been extended to the trinocular stereo vision for a further improvement of the performance. A few examples for the binocular and trinocular stereo problems are given to illustrate the performance of the new algorithms.     

An Intensity-Based,Coarse-to-Fine Approach to Reliably Measure Binocular Disparity

Disparity estimation is an ill-conditioned problem: at certain locations, the disparity vectors cannot be estimated solely using local intensity patterns. According to the strategy they use to solve this problem, the algorithms to estimate disparity vectors can be divided into two classes: the feature-based and intensity-based algorithms. In this paper, a new strategy is proposed. First, the disparity vectors are estimated, and then the unreliable and unfeasible vectors are eliminated. The method bears some resemblance with methods of both classes. In principle, the new approach is intensity-based, but it will be proved that because of the elimination process it determines the features on a binocular basis: the binocular raw primal sketch is constructed. A computational technique is developed for this new strategy. This technique is based on the simplex algorithm and its associated sensitivity analysis. Methods to reduce the required storage space and computation time are discussed. Numerical results are given for a random dot stereogram and an artificially generated stereo pair. Qualitative results are given for natural stereo pairs.     

立体视频编码中的目标分割与立体匹配算法

视频目标分割与立体匹配是目标基立体视频编码中的核心技术.首先在单通道视频目标分割的基础上提出一种轮廓跟踪匹配算法,以提取立体视频目标对,然后提出一种基于目标的视差估计算法.它以具有特征信息的像素为匹配基元,结合视差匹配约束进行视差估计,克服了传统块匹配算法视差场不连续、视差精度差的缺点,可以获得较为精确和平滑的视差场.     

A wavelet-based multiresolution approach to solve the stereo correspondence problem using mutual information.

In this correspondence, we propose a wavelet-based hierarchical approach using mutual information (MI) to solve the correspondence problem in stereo vision. The correspondence problem involves identifying corresponding pixels between images of a given stereo pair. This results in a disparity map, which is required to extract depth information of the relevant scene. Until recently, mostly correlation-based methods have been used to solve the correspondence problem. However, the performance of correlation-based methods degrades significantly when there is a change in illumination between the two images of the stereo pair. Recent studies indicate MI to be a more robust stereo matching metric for images affected by such radiometric distortions. In this short correspondence paper, we compare the performances of MI and correlation-based metrics for different types of illumination changes between stereo images. MI, as a statistical metric, is computationally more expensive. We propose a wavelet-based hierarchical technique to counter the increase in computational cost and show its effectiveness in stereo matching.     

Semisupervised Clustering with Metric Learning using Relative Comparisons

Semisupervised clustering algorithms partition a given data set using limited supervision from the user. The success of these algorithms depends on the type of supervision and also on the kind of dissimilarity measure used while creating partitions of the space. This paper proposes a clustering algorithm that uses supervision in terms of relative comparisons, viz., x is closer to y than to z. The proposed clustering algorithm simultaneously learns the underlying dissimilarity measure while finding compact clusters in the given data set using relative comparisons. Through our experimental studies on high-dimensional textual data sets, we demonstrate that the proposed algorithm achieves higher accuracy and is more robust than similar algorithms using pairwise constraints for supervision.     

基于自适应迭代松弛的立体点对匹配鲁棒算法

图像匹配是立体视觉的重要部分,也是双目立体测量系统必须解决和最难解决的问题。为了对图像进行鲁棒性匹配,提出了一种基于自适应迭代松弛的立体点对匹配方法。该方法首先利用视差梯度约束来构造匹配支持度函数;然后通过松弛方法优化该函数来完成立体点对的匹配。由于利用了动态更新松弛匹配过程参数的方法,因此有效地降低了误匹配率和误剔除率。在此基础上还提出了对松弛过程结束后的匹配结果,再次使用视差梯度约束来进行进一步检验的策略,该策略能够以一定幅度的误剔除率提升为代价,大幅度降低了误匹配率,从而可满足许多要求严格限制误匹配率的应用。实验结果证明,该新算法是有效的,并已经用于一个双目立体测量原型系统当中。     

一种鲁棒的基于互信息的实时立体匹配算法

立体匹配算法依然是目前计算机视觉领域中的一个重要的研究热点.现有的绝大多数匹配算法都假定已满足相似性约束条件.然而在野外环境下,光照不均、场景为非朗伯表面、像机间差异都会使该约束条件无法满足,从而导致匹配失败.本文针对这种情况,并从实时应用的角度出发,提出一种鲁棒的基于互信息的实时立体匹配算法.该方法在相关匹配算法中引入互信息概念,并将其转换为相关算法可用的求和形式,通过迭代方法修正互信息值.然后,建立了三种亮度变化模型来验证该算法的有效性.实验结果表明,该算法能很好地抑制立体图像对间的亮度差异,具有很好的实时性与鲁棒性.     

一种对光照条件不敏感而快速的局部立体匹配

针对绝大多数立体匹配算法的相似性测度过分依赖于图像灰度统计特性的问题,提出了一种对光照变化不敏感的立体匹配算法.首先,研究了Census非参数变换并分析了其局限性;其次,为了在立体匹配时能够考虑像素的空间位置信息,对于变换窗口内与中心像素的相对位置大于一个单位的各邻域像素,将其灰度值通过周围4个像素的灰度值插值获得:最...     

Adaptive spatial information-theoretic clustering for image segmentation

The incorporation of spatial context into clustering algorithms for image segmentation has recently received a significant amount of attention. Many modified clustering algorithms have been proposed and proven to be effective for image segmentation. In this paper, we propose a different framework for incorporating spatial information with the aim of achieving robust and accurate segmentation in case of mixed noise without using experimentally set parameters based on the original robust information clustering (RIC) algorithm, called adaptive spatial information-theoretic clustering (ASIC) algorithm. The proposed objective function has a new dissimilarity measure, and the weighting factor for neighborhood effect is fully adaptive to the image content. It enhances the smoothness towards piecewise-homogeneous segmentation and reduces the edge blurring effect. Furthermore, a unique characteristic of the new information segmentation algorithm is that it has the capabilities to eliminate outliers at different stages of the ASIC algorithm. These result in improved segmentation result by identifying and relabeling the outliers in a relatively stronger noisy environment. Comprehensive experiments and a new information-theoretic proof are carried out to illustrate that our new algorithm can consistently improve the segmentation result while effectively handles the edge blurring effect. The experimental results with both synthetic and real images demonstrate that the proposed method is effective and robust to mixed noise and the algorithm outperforms other popular spatial clustering variants.     

Hybrid image matching combining Hausdorff distance with normalized gradient matching

Image matching has been a central problem in computer vision and image processing for decades. Most of the previous approaches to image matching can be categorized into the intensity-based and edge-based comparison. Hausdorff distance has been widely used for comparing point sets or edge maps since it does not require point correspondences. In this paper, we propose a new image similarity measure combining the Hausdorff distance with a normalized gradient consistency score for image matching. The normalized gradient consistency score is designed to compare the normalized image gradient fields between two images to alleviate the illumination variation problem in image matching. By combining the edge-based and intensity-based information for image matching, we are able to achieve robust image matching under different lighting conditions. We show the superior robustness property of the proposed image matching technique through experiments on face recognition under different lighting conditions.     

Multiflash stereopsis: depth-edge-preserving stereo with small baseline illumination

Traditional stereo matching algorithms are limited in their ability to produce accurate results near depth discontinuities, due to partial occlusions and violation of smoothness constraints. In this paper, we use small baseline multi-flash illumination to produce a rich set of feature maps that enable acquisition of discontinuity preserving point correspondences. First, from a single multi-flash camera, we formulate a qualitative depth map using a gradient domain method that encodes object relative distances. Then, in a multiview setup, we exploit shadows created by light sources to compute an occlusion map. Finally, we demonstrate the usefulness of these feature maps by incorporating them into two different dense stereo correspondence algorithms, the first based on local search and the second based on belief propagation. Experimental results show that our enhanced stereo algorithms are able to extract high quality, discontinuity preserving correspondence maps from scenes that are extremely challenging for conventional stereo methods. We also demonstrate that small baseline illumination can be useful to handle specular reflections in stereo imagery. Different from most existing active illumination techniques, our method is simple, inexpensive, compact, and requires no calibration of light sources.     

基于相异性度量选取初始聚类中心改进的K-means聚类算法

选取合理的初始聚类中心是正确聚类的前提,针对现有的K-means算法随机选取聚类中心和无法处理离群点等问题,提出一种基于相异性度量选取初始聚类中心改进的K-means聚类算法.算法根据各数据对象之间的相异性构造相异性矩阵,定义了均值相异性和总体相异性两种度量准则;然后据此准则来确定初始聚类中心,并利用各簇中数据点的中位数代替均值以进行后续聚类中心的迭代,消除离群点对聚类准确率的影响.此外,所提出的算法每次运行结果保持一致,在初始化和处理离群点方面具有较好的鲁棒性.最后,在人工合成数据集和UCI数据集上进行实验,与3种经典聚类算法和两种优化初始聚类中心改进的K-means算法相比,所提出的算法具有较好的聚类性能.     

Robust Hausdorff distance measure for face recognition

Face is considered to be one of the biometrics in automatic person identification. The non-intrusive nature of face recognition makes it an attractive choice. For face recognition system to be practical, it should be robust to variations in illumination, pose and expression as humans recognize faces irrespective of all these variations. In this paper, an attempt to address these issues is made using a new Hausdorff distance-based measure. The proposed measure represent the gray values of pixels in face images as vectors giving the neighborhood intensity distribution of the pixels. The transformation is expected to be less sensitive to illumination variations besides preserving the appearance of face embedded in the original gray image. While the existing Hausdorff distance-based measures are defined between the binary edge images of faces which contains primarily structural information, the proposed measure gives the dissimilarity between the appearance of faces. An efficient method to compute the proposed measure is presented. The performance of the method on bench mark face databases shows that it is robust to considerable variations in pose, expression and illumination. Comparison with some of the existing Hausdorff distance-based methods shows that the proposed method performs better in many cases.     

Generalised residual images’ effect on illumination artifact removal for correspondence algorithms

The intensity (grey value) consistency of image pixels in a sequence or stereo camera setup is of central importance to numerous computer vision applications. Most stereo matching and optical flow algorithms minimise an energy function composed of a data term and a regularity or smoothing term. To date, well performing methods rely on the intensity consistency of the image pixel values to model the data term. Such a simple model fails if the illumination is (even slightly) different between the input images. Amongst other situations, this may happen due to background illumination change over the sequence, different reflectivity of a surface, vignetting, or shading effects.In this paper, we investigate the removal of illumination artifacts and show that generalised residual images substantially improve the accuracy of correspondence algorithms. In particular, we motivate the concept of residual images and show two evaluation approaches using either ground truth correspondence fields (for stereo matching and optical flow algorithms) or errors based on a predicted view (for stereo matching algorithms).     

A multimedia stereo calibration algorithm based on rectangular pyramidal method used to aid visual navigation of ALVs under low illumination

In order to measure and reconstruct accurate three-dimension (3D) data for visual aided navigation of autonomous land vehicles (ALVs), a multimedia stereo calibration algorithm which is suitable for normal scene and especially for low illumination scene is proposed. Firstly, an expression of object-point re-projection errors is derived by the collinear equation model, and the non-linear least square algorithm (NLS) is introduced to iteratively optimize external parameters for individual camera. A rectangular pyramidal method enforcing the rectangular geometric constraint is presented, to produce more stable initial parameter values. Then, according to imaging-point correspondences between the left and right camera, a re-projection error model is constructed for this stereo calibration system, of which all parameters are further optimized and calculated through the calibrated results of two separate cameras. Experimental results show that the proposed algorithm can achieve re-projection errors of no more than 0.5 pixels and converge fast usually with less than 10 interation times, whether under normal illumination or low illumination, so it can get better performance and realize a rapid re-calibration.

     

基于改进流形距离K-medoids算法

针对空间分布复杂的数据以及空间分布未知的现实数据聚类问题,设计了一种改进流形距离作为不相似测度。该不相似测度可有效利用所有数据点之间的全局一致性,挖掘无类属数据集的空间分布信息。通过使用该不相似测度,提出了基于改进流形距离K-medoids算法。将新算法与基于已有的流形距离和基于欧氏距离的K-medoids算法进行性能比较,对八个人工数据集以及USPS手写体数字识别问题的实验结果表明:新算法针对不同结构的测试数据集,在聚类性能上均优于或接近于另外两种K-medoids算法,并且对于各种分布的,无论简单或复杂,凸或者非凸的数据都可以进行聚类。     

基于粗糙集的改进K—Modes聚类算法

传统的K-Modes算法采用简单匹配的方法来计算对象之间的距离,并没有充分考虑同一属性下的两个不同值之间的相似性.基于粗糙集中的上、下近似,提出了一种新的距离度量,并重新定义了类中心,对传统K-Modes算法进行了改进.与其他改进K-Modes算法进行了比较,实验结果表明,基于粗糙集的改进K-Modes算法有效地提高了聚类精度.     

Real-Time Correlation-Based Stereo Vision with Reduced Border Errors

This paper describes a real-time stereo vision system that is required to support high-level object based tasks in a tele-operated environment. Stereo vision is computationally expensive, due to having to find corresponding pixels. Correlation is a fast, standard way to solve the correspondence problem. This paper analyses the behaviour of correlation based stereo to find ways to improve its quality while maintaining its real-time suitability. Three methods are suggested. Two of them aim to improve the disparity image especially at depth discontinuities, while one targets the identification of possible errors in general. Results are given on real stereo images with ground truth. A comparison with five standard correlation methods is provided. All proposed algorithms are described in detail and performance issues and optimisation are discussed. Finally, performance results of individual parts of the stereo algorithm are shown, including rectification, filtering andcorrelation using all proposed methods. The implemented system shows that errors of simple stereo correlation, especially in object border regions, can be reduced in real-time using non-specialised computer hardware.