Epipolar line estimation and rectification for stereo image pairs

The assumption that epipolar lines are parallel to image scan lines is made in many algorithms for stereo analysis. If valid, it enables the search for corresponding image features to be confined to one dimension and, hence, simplified. An algorithm that generates a vertically aligned stereo pair by warped resampling is described. The method uses grey scale image matching between the components of the stereo pair but confined to feature points.     

结合空间域与变换域特征提取的盲立体图像质量评价

针对立体图像质量预测准确性不足的问题,该文提出了一种结合空间域和变换域提取质量感知特征的无参考立体图像质量评价模型。在空间域和变换域分别提取输入的左、右视图的自然场景统计特征,并在变换域提取合成独眼图的自然场景统计特征,然后将其输入到支持向量回归(SVR)中,训练从特征域到质量分数域的预测模型,并以此建立SIQA客观质量评价模型。在4个公开的立体图像数据库上与一些主流的立体图像质量评价算法进行对比,以在LIVE 3D Phase I图像库中的性能测试为例,Spearman秩相关系数、皮尔逊线性相关系数和均方根误差分别达到0.967,0.946和5.603,验证了所提算法的有效性。     

具有良好重复率与信息量的立体影像点特征提取方法

针对立体影像匹配问题,从重复率与信息量两个方面对现有几种主要的立体影像点特征提取算子进行了实验分析比较;根据影像的信息熵对影像特征进行聚类分析,提出了一种与影像特征相关的、基于Harris算子原理改进的点特征提取方法;选取不同特征的实际立体影像进行实验分析,证明本文提出的方法具有更优的重复率与信息量.     

基于立体视觉掩蔽的自恢复非对称立体图像水印

为了认证立体图像的完整性,提出了一种基于立体视觉掩蔽的非对称立体图像水印方法。首先,根据立体视觉特性,建立立体视觉掩蔽计算模型,设计了立体图像左右视点嵌入不同容量的非对称水印;其次,使用小波变换系数计算不同类型的恢复水印,将其分别嵌入2个或3个不同映射块,从而提高篡改恢复质量。仿真实验结果证明,该方法能够有效检测和恢复、拼接、粘贴等不同类型的篡改,并且恢复质量高于现有以及扩展的单图像水印方法。     

基于三维特征和结构相似度的图像质量评价方法

分析了人眼视觉特性、双眼视差异信息等三维特征,将立体视觉与图像的结构相似度(SSIM)相结合,提出了一种新的立体图像质量评价方法。该方法考虑了立体图像的亮度、纹理细节和空间位置等因素对人感知立体效果的影响,利用加权平均结构相似性(WMSS)联合统计学方法得到评价初值,用包含三维景物深度信息的双眼视差信息进行修正,作为立体图像质量的评价结果。实验表明,该方法符合人眼视觉特性,与主观评价(MOS)的一致性较好。     

Stereo image quality assessment considering the difference of statistical feature in early visual pathway

Human visual theory is closely related to stereo image quality assessment (SIQA), which determines whether the evaluation results of SIQA method can keep good consistency with subjective perception. Many SIQA methods are not fully based on human visual theory, so there is still room for improvement. The research on the visual system tends to the dorsal and ventral pathways, which ignores the information differences in the early visual pathways. It is worth noting that the ON and OFF receptive fields in retinal ganglion cells (RGCs) respond asymmetrically to the statistical features of images. Inspired by this, in this paper, we propose an SIQA method based on monocular and binocular visual features, which takes into account the difference of ON and OFF response features in early visual pathways. Moreover, the different information interaction mechanisms of visual cortex are used to fuse the response maps information of left and right images. Final, monocular and binocular features are extracted and sent to support vector regression (SVR) for quality prediction. Experimental results show that the proposed method is superior to several mainstream SIQA metrics on four publicly available stereo image databases.     

DCT transform coding of stereo images for multimedia applications

One form of multimedia finding increasing utility in factory automation is stereo imaging. Its uses include remote operation, telepresence, and object positioning. Stereo imaging, with doubled frames, requires high data-rate collection and transmission. Image compression techniques can be utilized to reduce the transmission bandwidth and/or storage space requirements of the stereo pair. This paper develops image compression techniques specific to stereo imaging and compares the performance with nonstereo methods. Disparity compensated residual image coding exploits the redundancy between the two images in a stereo pair. Stereo residuals possess special features that can be exploited within a discrete cosine transform (DCT) image coding framework. Use of these features results in several decibels of performance enhancement across a range of scene types. This approach provides its best performance below 0.75 b/pixel bitrate for 8-b grayscale imagery and below 2 b/pixel for 24-b color imagery     

Grid coding: A novel technique for image processing

The encoding of information as the modulation of a grid is explored as the means for allowing the extraction of relevant details or features from images. A major aspect of this approach is the replacement of the heuristics in certain image processing tasks by simple Fourier filtering. Specific examples and particular implementations of coding schemes are described in order to show the wide applicability of the concept. The examples chosen fall in the domains of scene analysis, difference extraction from successive images, automatic extraction of range, extraction of features such as planes, recording of three-dimentional imagery, and the processing of a single coded view to give a set of stereo related pairs.     

基于差异的视差估计方法研究

视差估计在立体图像编码、视频检索、立体图像分割等领域有重要的应用,是进行图像、视频分析的基础。首先,基于模糊隶属度提出了一种基于差异的视差估计方法;其次,引入模糊隶属度,把图像灰度转换为差异值;然后,分析了多块匹配的优越性;提出了基于多块匹配的视差估计方法;最后,在Middlebury网站上的测试结果证明了该方法的有效性。     

Look, no glasses [3D display system]

Three-dimensional display systems generally require the user to wear special glasses. The author describes a research programme-aimed at providing a high-quality spectacle-free look into the third dimension. It is based on the Twin-LCD display concept developed by the Imaging Technology Department at Sharp Laboratories of Europe. The author describes how the Twin-LCD system works. It is based on two thin-film transistor (TFT) LCDs whose images are superimposed by a half-mirrored beam-combiner. The input optical arrangement creates two laterally displaced images at the nominal observer position. If an observer places an eye in a window, then an image from one of the LCDs can be seen. Each LCD panel displays one of the stereo pair images and so the observer sees the 3D image without the need for any special glasses     

Opposite side ERS-1 SAR stereo mapping over rolling topography

Opposite-side radar stereo images have been considered unsuitable for stereo viewing due to illumination differences which limit the ability to identify the same features in the image pair. In some contexts, like a rolling topography (slope less than 10°), the shadow, layover, and foreshortening effects, specific to radar images, will not be overwhelming with an opposite-side stereo pair. This paper reports on some issues of stereo viewing and plotting, as well as on quantitative results of mapping and features extraction from ascending and descending orbit ERS-1 SAR stereo images. Planimetric accuracy of 17 m and altimetric accuracy of 23.9 m have been achieved for lake shorelines and DEM extractions, respectively. Impacts of different parameters on the accuracy are also evaluated     

Spotlight mode SAR stereo technique for height computation

This paper examines the feasibility of extracting three-dimensional (3-D) or topographic information in spotlight mode stereo synthetic aperture radar (SAR). A display of a SAR (intensity) image has two axes: range and cross-range. Elevated scatterers appear closer in range; this phenomenon is called radar image layover. How the height of each scatterer can be computed from the difference in its layover between two images is investigated. This is analogous to computing height from disparity distance (triangulation) in optical stereo. The same procedure can be applied on pixel by pixel basis for terrain elevation mapping. A general expression is derived for the accuracy of the height estimate as a function of the range resolution and the angular difference between the image planes. Accuracy increases as the angle between the image planes increases, but the bright scatterers in one image tend to fade in the other image. This limited angular persistence of radar scatterers is also discussed. Trajectories for data collection are examined that provide near-optimal height estimates while eliminating the scatterer persistency problem.     

Shift–Scale Complex Correlation for Wide-Angle Coherent Cross-Track SAR Stereo Processing

Automated synthetic aperture radar (SAR) stereo correspondence becomes increasingly difficult when imaging high-relief terrain utilizing large stereo crossing-angle geometries because high-relief SAR image features can undergo significant spatial distortions, causing a failure of traditional correlation matching. This paper presents eight coherent spotlight-mode cross-track stereo pairs with stereo crossing angles averaging 93.7deg collected over a terrain with slopes greater than 20deg. These stereo pairs suffer from terrain-induced distortions, resulting in a decrease in complex correlation (coherence) when utilizing scanning-window correlation calculations. The search to maximize complex correlation is changed from a shift-only (disparity) search to a shift-and-scale search using the downhill simplex method. This approach is tested against complex imagery with simulated distortions and then employed on the eight wide-angle stereo collects. The resulting digital terrain maps (DTMs) are compared to ground truth. Using a shift-and-scale correlation approach to estimate disparity, the relative height errors decrease, and the number of reliable DTM posts increase     

立体图像生成的视差控制

获取合适的视差信息是立体图像得到舒适观看的重要条件。为达到上述目的,提出了一种立体图像视差检测和控制方案。首先分析2种人眼视觉生理学限制的数学模型,并结合人眼跟踪技术获取生理视差容限。然后使用OpenGL图像绘制引擎获取显示场景的极值深度信息,进而计算出画面视差范围。最终通过比对虚拟场景的视差与观察者的生理视差容限,确定场景视差正确性并加以修正。实验证明,方案可以实时地进行视差控制,为立体图像生成提供了可靠依据。     

基于图割和视域相关性的立体图像分割

立体图像分割是对象基立体图像处理中的关键和难点。基于改进Grabcut图割算法和视域相关性,提出一种新的立体图像分割算法。首先基于改进Slic方法将左图像转换成超像素图像,然后基于Grabcut框架通过重新定义能量函数对其分割以提取出左图像目标。最后,基于左右图像的视域相关性通过融合颜色和纹理特征的轮廓匹配提取右图像目标。实验结果表明,与现有方法相比,所提算法能获得更高的分割效率和更准确的分割结果。     

On the application of a modified self-organizing neural network to estimate stereo disparity.

We propose a modified self-organizing neural network to estimate the disparity map from a stereo pair of images. Novelty consists of the network architecture and of dispensing with the standard assumption of epipolar geometry. Quite distinct from the existing algorithms which, typically, involve area- and/or feature-matching, the network is first initialized to the right image, and then deformed until it is transformed into the left image, or vice versa, this deformation itself being the measure of disparity. Illustrative examples include two classes of stereo pairs: synthetic and natural (including random-dot stereograms and wire frames) and distorted. The latter has one of the following special characteristics: one image is blurred, one image is of a different size, there are salient features like discontinuous depth values at boundaries and surface wrinkles, and there exist occluded and half-occluded regions. While these examples serve, in general, to demonstrate that the technique performs better than many existing algorithms, the above-mentioned stereo pairs (in particular, the last two) bring out some of its limitations, thereby serving as possible motivation for further work.     

改进的双目视觉三维尺寸测量系统

根据双目视觉原理,开发了基于双目视觉的三维尺寸测量系统.利用图像帧差法实现目标物体自动检测;并在此基础上利用立体匹配算法计算出目标物体区域的视差,对生成的初步视差采用基于最小二乘法的视差优化算法,获取目标物体区域的完整视差图;再将三维点云重投影到二维平面,利用最小外接矩形完成目标物体尺寸的自动测量.实验表明,在合适的测量距离下,系统测量精度达到了较好的效果,验证了该系统的可行性.     

Disparity based stereo image retrieval through univariate and bivariate models

The widespread use of stereovision in various application fields has led to the constitution of very huge stereo image databases. Therefore, the design of effective content based image retrieval system devoted to stereo pairs becomes an issue of importance. To this end, we propose in this paper two retrieval methods which combine the visual contents of the stereo images with their corresponding disparity information. After modeling the distribution of their associated wavelet coefficients by the generalized Gaussian statistical model, the resulting distribution parameters are selected as salient features. While the two views are processed separately through a univariate modeling in the first method, the second one exploits the correlation between the views by resorting to a bivariate modeling. Experimental results show the benefits which can be drawn from the proposed retrieval approaches.     

一种基于区域颜色信息的宽基线立体匹配算法

立体匹配技术是立体视觉研究领域的难点,利用图像的特征信息解决对应问题是研究的热点.本文在提取基于边缘仿射不变区域检测器的基础上,设计了基于区域颜色信息和几何信息的彩色图像立体匹配算法.该算法首先对所提取的不变区域进行颜色空间量化,在此基础上根据两种色彩之间的距离进行色彩聚类,然后计算直方图的二次距离,并进行相似性度量,最后根据区域间几何性质进行误匹配剔除.实验证明,该算法能降低解决对应问题的复杂性,提高正确匹配率.该方法对于目标识别、三维重建、非接触测量等研究均具有重要的意义.     

Stereo calibration from correspondences of OTV projections

Stereo images have to be calibrated before stereo vision can recover three-dimensional information of the imaged scene. Position constraints over image point correspondences are traditionally used to solve the calibration problem. A method is described that uses angle constraints over correspondences of a particular type of image features, the projections of orthogonal trihedral vertices (OTV), for calibration. Computations of the rotation matrix and the translation vector are separable and the method has a closed-form solution. It also requires correspondences of only two vertex projections at minimum to recover all the transformation parameters which are recoverable from a stereo image pair. Extensive experimental results, including those on real images, are presented and they show that use of angle constraints is generally more accurate than position constraints alone