基于改进Census变换与梯度融合的立体匹配算法

双目立体匹配根据视差原理将平面视觉转化到三维立体视觉,是三维重建的核心步骤之一。针对局部立体匹配算法在深度不连续、弱纹理区域匹配精度低且易受光照、噪声等因素干扰的问题,提出了一种改进的立体匹配算法。首先,在代价计算阶段将改进的Census代价与梯度代价进行融合,并采用引导滤波算法对图像进行多尺度代价聚合;然后,采用赢家通吃算法计算初始视差;最后,采用左右一致性检测、中值滤波进行视差后处理,得到最终的视差图。实验结果表明,本算法在Middlebury2.0测试平台上的平均误匹配率为5.11%,且具有很好的稳健性和实用性。     

一种边缘保持立体匹配方法

针对边缘处前景和背景视差易混淆问题,提出一种边缘保持立体匹配方法.在代价匹配阶段,采用级联Census变换增强代价的抗噪特性.在代价聚集阶段,引入SLIC超像素分割信息进行快速边缘保持代价聚集.在视差后处理阶段,通过导向十字滤波器进一步优化边缘视差.实验结果表明,文中提出的立体匹配方法在Middlebury测试集以及实际场景获得高质量视差效果,并在边缘处的视差较以往非局部立体匹配方法有所提升.实验还发现在点云上采样时,引入本文所提的导向十字滤波器,可以解决点云在边缘处的过渡.     

Information permeability for stereo matching

A novel local stereo matching algorithm is introduced to address the fundamental challenge of stereo algorithms, accuracy and computational complexity dilemma. The time consuming intensity dependent aggregation procedure of local methods is improved in terms of both speed and precision. Providing connected 2D support regions, the proposed approach exploits a new paradigm, namely separable successive weighted summation (SWS) among horizontal and vertical directions enabling constant operational complexity. The weights are determined by four-neighborhood intensity similarity of pixels and utilized to model the information transfer rate, permeability, towards the corresponding direction. The same procedure is also utilized to diffuse information through overlapped pixels during occlusion handling after detecting unreliable disparity assignments. Successive weighted summation adaptively cumulates the support data based on local characteristics, enabling disparity maps to preserve object boundaries and depth discontinuities. According to the experimental results on Middlebury stereo benchmark, the proposed method is one of the most effective local stereo algorithm providing high quality disparity models by unifying constant time filtering and weighted aggregation. Hence, the proposed algorithm provides a competitive alternative for various local methods in terms of achieving precise and consistent disparity maps from stereo video within fast execution time.     

Edge-preserving guided filtering based cost aggregation for stereo matching

Stereo matching has been widely used in various computer applications and it is still a challenging problem. In stereo matching, the filter-based stereo matching methods have achieved outstanding performance. A local stereo matching method based on adaptive edge-preserving guided filter is presented in this paper, which can achieve proper cost-volume filtering and keep edges well. We introduce a gradient vector of the enhanced image generated by the proposed filter into the cost computation and the Census transform is adopted in the cost measurement. This cost computation method is robust against radiometric variations and textureless areas. The edge-preserving guided filter approach is proposed to aggregate the cost volume, which further proves the effectiveness of edge-preserving filter for stereo matching. The experiments conducted on Middlebury benchmark and KITTI benchmark demonstrate that the proposed algorithm produces better results compared with other edge-aware filter-based methods.     

Stacking learning with coalesced cost filtering for accurate stereo matching

Deep learning based stereo matching algorithms have produced impressive disparity estimation for recent years; and the success of them has once overshadowed the conventional ones. In this paper, we intend to reverse this inferiority, by leveraging Stacking Learning with Coalesced Cost Filtering to make the conventional algorithms achieve or even surpass the results of deep learning ones. Four classical and Discriminative Dictionary Learning (DDL) algorithms are adopted as base-models for Stacking. For the former ones, four classical stereo matching algorithms are employed and regarded as ‘Coalesced Cost Filtering Module’; for the latter supervised learning one, we utilize the Discriminative Dictionary Learning (DDL) stereo matching algorithm. Then three categories of features are extracted from the predictions of base-models to train the meta-model. For the meta-model (final classifier) of Stacking, the Random Forest (RF) classifier is selected. In addition, we also employ an advanced one-view disparity refinement strategy to compute the final refined results more efficiently. Performance evaluations on Middlebury v.2 and v.3 stereo data sets demonstrate that the proposed algorithm outperforms other four most challenging stereo matching algorithms. Besides, the submitted online results even show better results than deep learning ones.     

二次加权引导滤波融合双色彩空间模型的立体匹配

立体匹配一直以来都是双目视觉领域中研究的重点 和难点。针对现有立体匹配算法边 缘保持性差、匹配精度低等问题,提出了一种二次加权引导滤波融合双色彩空间模型的立体 匹配算法(Secondary Weighted Guided Filtering fusion double color model,SWGF)。首 先在代价计算阶段提出了一种双色彩空间模型,从两个颜色空间进行像素颜色匹配代价计算 ,增强像素在低纹理区域的特征;然后在代价聚合阶段基于HSV颜色空间利用不同窗口中像 素纹理不同加入一个边缘保持项,从而使正则化参数进行自适应调整。在一次引导滤波之后 ,我们使用Census变换得到的汉明距离和初始视差完成一次代价更新,再次对其进行代价聚 合,随后计算视差并对视差进行左右一致性检测、空洞填充和加权中值滤波等优化,最后获 得视差图。本文算法在Middlebury测试平台上测试结果表明SWGF算法误匹配率仅为 4.61%,可以大幅提升立体匹配的精度,同时增强其边缘保持性。     

基于韦伯感知和导引滤波分层聚合快速立体图像匹配

该文利用韦伯定律和导引滤波提出基于代价分层聚合的快速立体匹配方法。首先提取立体图像对各彩色通道Weber描述符并初始化匹配代价。利用导引滤波增强匹配代价并提取视差候选;利用候选子集联合空间离散采样与自适应支持权重实现分层代价聚合;据此快速择优选取初始视差。视差求精中采用改进型双边滤波和对称映射后处理有效改善初始视差图中歧义区域。实验表明,该文方法能有效消除匹配歧义,获得分段平滑、高精度稠密视差;结构简单、快速高效且对光照变化具有鲁棒性。     

Parallel framework for dense disparity map estimation using Hamming distance

A novel framework for sparse and dense disparity estimation was designed, and the proposed framework has been implemented in CPU and GPU for a parallel processing capability. The Census transform is applied in the first stage, and then, the Hamming distance is later used as similarity measure in the stereo matching stage followed by a matching consistency check. Next, a disparity refinement is performed on the sparse disparity map via weighted median filtering and color K-means segmentation, in addition to clustered median filtering to obtain the dense disparity map. The results are compared with state-of-the-art frameworks, demonstrating this process to be competitive and robust. The quality criteria used are structural similarity index measure and percentage of bad pixels (B) for objective results and subjective perception via human visual system demonstrating better performance in maintaining fine features in disparity maps. The comparisons include processing times and running environments, to place each process into context.     

基于引导滤波及视差图融合的立体匹配

立体匹配是双目视觉领域的重要研究方向.为在保证图片纹理区域匹配精度的同时降低弱纹理区域的误匹配率,提出一种基于引导滤波及视差图融合的立体匹配方法.首先,根据图像颜色相似性将图片划分为纹理较丰富区域和弱纹理区域.接着,分别采用不同参数的引导滤波进行代价聚合及视差计算,得到两张视差图.然后依据纹理区域划分的结果对获得的两张视差图进行融合.最后,通过左右一致性检测、加权中值滤波等视差优化步骤得到最终视差图.对Middlebury测试平台上标准图像对的实验结果表明,该方法在6组弱纹理图像上的平均误匹配率为9.67％,较传统引导滤波立体匹配算法具有更高的匹配精度.     

基于改进Census变换的抗噪立体匹配算法

针对传统Census变换在匹配代价计算中易受噪声影响、匹配精度较低的问题,提出一种引入噪声容限的四状态Census变换算法。在匹配代价计算中,首先将改进的Census匹配代价与灰度绝对差值和梯度代价进行融合,并加入相应的截断阈值,以提高初始匹配代价空间的可靠性。然后通过引导图滤波进行代价聚合,并采用赢家通吃策略计算初始视差值。最后通过左右一致性检验、视差填充和加权中值滤波来优化初始视差值,得到最终视差图。实验结果表明,所提算法的噪声鲁棒性优于传统Census变换算法,且立体匹配算法的整体误匹配率降低至5.59%。     

基于改进导向滤波算法的低剂量CT图像处理

导向滤波算法是一种有效的基于边保持的平滑滤波算法.然而,由于算法中的正则化系数和细节层增益是固定的,可能会导致边附近出现光晕以及背景中出现大量噪声,降低图像的质量.在本文中,首先给出了一种改进的基于边的权重系数计算方法,它能够较准确地实现边保持,减少光晕现象.其次,提出了基于梯度导向的细节层增益计算方法,可以有效地增强细节并且抑制噪声.实验表明,对于含有大量噪声和小细节的低剂量CT图像,本文方法可以减少噪声和光晕的影响,显著提高图像的对比度,满足临床诊断的需要.     

基于改进代价计算和视差候选策略的立体匹配

立体匹配算法在图像弱纹理区和重复纹理区存在匹配困难、误差大的问题,为此提出一种基于改进代价计算和视差候选策略的立体匹配算法。首先结合改进的Census变换和自适应加权融合的双向梯度信息来计算初始匹配代价,提高代价计算的可靠性。其中:为传统Census变换增加内圈编码,提高邻域信息利用率,同时降低噪声的影响;利用自适应权重函数融合横向和纵向梯度代价,降低物体边缘区域的误匹配率。其次,采用自适应十字交叉窗口进行代价聚合,并通过建立候选视差集和引入邻域视差信息的方法来获取初始视差。最后通过两轮插值策略优化视差。实验结果表明,所提算法能够提高弱纹理区和重复纹理区的匹配效果,在Middlebury中4幅标准立体图像对的平均误匹配率为5.33%。     

应用分层MRF/GRF模型的立体图像视差估计及分割

视差估计与分割是立体图像编码及立体视觉匹配的核心问题,本文提出一种基于分层MRF/GRF模型和交叠块匹配(HMOM)视差估计算法以及结合主动轮廓模型的视差分割提取算法.该混合视差估计方法,可得到光滑准确,且具有清晰边缘的视差场;并便于用主动轮廓模型提取感兴趣对象(OOI)的视差轮廓.与通常的变尺寸块匹配(VSBM)相比,本算法得到的视差补偿图像的峰值信噪比可提高2.5dB左右.本文得到的视差场及对应的轮廓可进一步用于立体图像编码以及视频对象分割.     

基于改进Census变换的局部立体匹配算法

针对基于传统Census变换的立体匹配算法鲁棒性差和精度不高的问题,提出一种基于改进Census变换的自适应权重立体匹配算法.首先,用Census变换窗口中邻域像素的中值来替换中心像素的灰度值,克服了邻域像素对中心像素的依赖;然后用自适应权重的方法分别计算匹配代价和进行立体匹配,得到初始视差;最后通过左右一致性校验和亚像素提精的方法得到稠密的视差图.实验结果表明,该算法有很强的鲁棒性和很高的匹配精度.     

融合梯度特性与置信度的立体匹配算法

针对现有局部立体匹配算法在计算匹配代价时, 不能很好区分强弱纹理区域,及在视差计算过程 中,不能很好的解决视差歧义问题,提出一种融合梯度特性与置信度的立体匹配算法。首先 计算梯度特 征,并根据梯度特征信息选择匹配代价计算的匹配窗口,针对强弱不同纹理区域选择不同尺 寸的匹配窗 口,有效的提高了立体匹配精度,降低了误匹配率;然后在视差计算中引入置信度约束条件 ,解决了视差 计算中视差歧义的问题,提高了立体匹配算法的稳定性与精度;最后使用水平与垂直方向交 叉区域检测进 行奇异值的修正。实验结果表明,该算法在Middlebury数据集中31对 立体图像对的平均误匹配率为7.96%,有效的提高了立体匹配精度。     

基于Census变换和多扫描线优化的半全局立体匹配算法

为了解决局部匹配算法误匹配率高的问题,提出 一种基于AD-Census变换和多扫描线优化的半全局匹配算 法。首先,通过绝对差AD算法与Census变换相结合作为相似性度量函数计算初始匹配代价, 并构建动态交叉域聚合 匹配代价;然后在代价聚合计算阶段,将一维动态规划的代价聚合推广到多扫描线优化,利 用上下左右四个方向逐 次扫描进行匹配代价聚合的计算,并引入正则化约束以确保匹配代价聚合的一致性,大大减 少初始代价中的匹配异 常点;最后,运用简单高效的胜者为王策略选出像素点在代价聚合最小时对应的视差,并在 视差细化阶段,采用左 右一致性检测和抛物线拟合方法进行后续处理以提高立体匹配的正确率。实验结果证明,该 算法可获得高匹配率的视差图并且耗时较少。     

基于改进双目视觉算法的三维重建研究

为解决现有立体匹配算法在图像弱纹理等区域鲁棒性差以及模型参数较大的问题,对PSMNet立体匹配方法进行改善,通过使用空洞空间卷积池化金字塔结构(atrous spatial pooling pyramid,ASPP)提取图像在不同尺度下的空间特征信息。随后引入通道注意力机制,给予不同尺度的特征信息相应的权重。融合以上信息构建匹配代价卷,利用沙漏形状的编解码网络对其进行规范化操作,从而确定特征点在各种视差情况下的相互对应关系,最后采用线性回归的方法得到相应的视差图。与PSMNet相比,该研究在SceneFlow和KITTI2015数据集里的误差率各自减少了14.6%和11.1%,且计算复杂度下降了55%。相比较于传统算法,可以改善视差图精度,提升三维重建点云数据质量。     

基于多尺度分析的快速相位立体匹配

基于相位的立体匹配是双目投影光栅相位法中的重要步骤,但传统的相位匹配方法在处理高分辨率图像时因存储空间大大增加,难以达到匹配速度与精度的平衡。文章提出了一种基于多尺度分析的快速相位立体匹配算法,采用分层匹配的策略,对预处理后的左右绝对相位图进行降采样以生成图像金字塔,利用低分辨率的视差匹配结果以预测下一层视差,以此降低下层高分辨率图像的视差搜索范围,达到匹配速度与精度的平衡。实验结果表明,所提算法在保证精度的情况下能有效提升相位立体匹配速度,实现高分辨率相位图快速准确的立体匹配。     

Exploiting Walsh-based attributes to stereo vision

This paper presents a new stereo feature matching method that extracts the disparity measure for the recovery of depth information in 2-D stereo images. In this method, a stereo pair of images are transformed row for row into strings carrying spatially varying Walsh coefficients as attributes. The significance of the information carried by the Walsh coefficients is expressed mathematically and through experimental evaluations. The choice of the Walsh coefficients in contrast to other orthogonal transform coefficients is a direct result of their computational simplicity and their interpretative meaning in terms of the information contained in the spatial domain. The string-to-string matching technique used to bring the two strings into correspondence integrates, into a unified process, both the feature detection and the feature matching processes. The uniqueness and the ordering constraints are explicitly integrated into this string-to-string matching technique. Both the issues of Gaussian filtering and the importance of enforcing the epipolar line constraint are addressed in view of the application of the proposed method. Experimental results are given and assessed in terms of both the accuracy in stereo matching and the ensuing computational requirements     

基于改进双向动态规划的立体图像匹配算法

提出一种基于改进双向动态规划的立体图像匹配算法,选用修正后的自适应加权代价函数(Adaptive Support Weight Cost Function,ASCF),然后构建新的全局能量函数,并通过改进双向动态规划来寻径,最后采用简单的滤波方法和遵循3个可靠性准则去除孤立的错误视差点,以获得稠密视差图。实验结果表明,该算法在降低误匹配率和减少"条纹"瑕疵方面有显著的改善效果。