具有容错能力的L1最优化半自动2D转3D

半自动2D转3D的关键是将用户分配的稀疏深度转换为稠密深度.现有方法没有充分考虑纹理图像和深度图之间的结构差异,以及2D转3D对用户误标注的容错性.针对上述问题,借助L₁范数对异常数据的抵制,在一个统一框架下实现结构相关具有容错能力的稀疏深度稠密插值.首先,利用L₁范数表示估计深度和用户分配深度在标注位置的差异,建立数据项;其次,根据特征的相似性用L₁范数计算局部相邻像素点之间的深度差异,建立局部正则项;再次,对图像进行超像素分割,根据不同超像素内代表性像素点之间深度差异的L₁测度,建立全局正则项;最后,用上述数据项和正则项构建能量函数,并通过分裂Bregman算法予以求解.无误差和有误差情况下的实验结果表明,与边缘保持的最优化插值、随机游走、混合图割与随机游走、软分割约束的最优化插值和非局部化随机游走相比,本文估计深度图绘制的虚拟视点图像空洞和伪影损伤更小.在误操作情况下,本文比上述方法PSNR改善了0.9dB以上,且在视觉上屏蔽了用户误操作的影响.     

对象引导的单幅散焦图像深度提取方法

2D图像转3D图像是解决3D影视内容缺乏的主要手段之一,而深度提取是其中的关键步骤.考虑到影视作品中存在大量散焦图像,提出单幅散焦图像深度估计的方法:首先通过高斯卷积将散焦图像转换成两幅模糊程度不同的图像;其次计算这两幅图像在边缘处的梯度幅值比例,进而根据阶跃信号与镜头的卷积模型得到边缘处的模糊度;再次将边缘处的模糊度转换成图像的稀疏深度并利用拉普拉斯矩阵插值得到稠密深度图;最后通过图像的视觉显著度提取前景对象,建立对象引导的深度图优化能量模型,使前景的深度趋于一致并平滑梯度较小区域的深度.该方法利用对象引导的深度优化,剔除了拉普拉斯矩阵插值引入深度图的纹理信息.模拟图像的峰值信噪比和真实图像的视觉对比均表明该算法比现有方法有较大改善.     

加权SIFT流深度迁移的单幅图像2D转3D

2D视频转3D视频是解决3D片源不足的主要手段,而单幅图像的深度估计是其中的关键步骤.提出基于加权SIFT流深度迁移和能量模型优化的单幅图像深度提取方法.首先利用图像的全局描述符从深度图数据库中检索出近邻图像;其次通过SIFT流建立输入图像和近邻图像之间像素级稠密对应关系;再次由SIFT流误差计算迁移权重,将近邻图像对应像素点的深度乘以权重后迁移到输入图像上;然后利用均值滤波对迁移后的近邻图像深度进行融合;最后建立深度图优化能量模型,在尽量接近迁移后近邻图像深度的前提下,平滑梯度较小区域的深度.实验结果表明,该方法降低了估计深度图的平均相对误差,增强了深度图的均匀性.     

基于超像素和低秩的协同稀疏高光谱解混

为了克服经典协同稀疏解混算法的不足以及全变差正则项引起的边缘模糊问题,同时考虑到稀疏性和空间信息对解混精度提高的重要性,采用结合超像素和低秩的协同稀疏高光谱解混算法,进行了理论分析和实验验证.该算法对高光谱图像进行超像素分割,并对每个超像素施加协同稀疏性约束.此外使用低秩正则项代替传统的全变差正则项来利用空间信息,选取...     

基于两重误差重构的显著性区域检测算法

通过SLIC分割算法将图像分成多个超像素区域后,利用重构误差进行视觉显著性检测。首先提取图像边缘的超像素区域作为背景模板,然后利用这些模板构建两重外观模型:稀疏外观模型及稠密外观模型。对于每一块图像区域,首先计算稠密重构误差及稀疏重构误差,然后利用K均值聚类方法得到的上下文对重构误差进行传播,再利用贝叶斯准则融合稀疏型检测结果及稠密型检测结果,最后通过综合多尺度重构误差信息及修正的目标基高斯模型信息实现像素级显著性检测。     

基于视差约束的3D立体视频重新定位研究

文中提出了一种视差约束的3D立体视频重新定位方法,该方法同时将双目视频调整为新的纵横比,并将深度感知进行重新映射。建立畸变能量建模来防止视频内的目标区域形变,通过模拟视差变化能量来约束空间域和时间域中的视差范围,实现了深度映射的稳定性。运用原始立体视频生成不同显示分辨率的高感知质量的图像版本,克服了能量模型中目标分辨率的非均匀性和像素形变的干扰。最后通过实验分析验证了所提方法的有效性。     

基于颜色三角形的彩色图像边缘检测

利用像素点的颜色坐标RGB构建像素的颜色三角形,计算该三角形的周长和内角.将周长和内角作为像素点的信息量的度量.通过像素点在相关邻域上的信息量的计算,确定该像素点是否为彩色图像的边缘点.这种边缘检测方法,在一定程度上合理地考虑了个各颜色分量的相关性,将向量空间的计算以自然的方式转换成了标量的计算,在思想上是一种不同于其他算法新的算法.实验结果表明,与传统方法相比,该方法能检测出更多的边缘,并且算法实现简单,检测出的边缘清晰.     

基于语义分割的双目场景流估计

针对现有场景流计算方法在复杂场景、大位移和运动遮挡等情况下易产生运动边缘模糊的问题,提出一种基于语义分割的双目场景流估计方法.首先,根据图像中的语义信息类别,通过深度学习的卷积神经网络模型将图像划分为带有语义标签的区域;针对不同语义类别的图像区域分别进行运动建模,利用语义知识计算光流信息并通过双目立体匹配的半全局匹配方法计算图像视差信息.然后,对输入图像进行超像素分割,通过最小二乘法耦合光流和视差信息,分别求解每个超像素块的运动参数.最后,在优化能量函数中添加语义分割边界的约束信息,通过更新像素到超像素块的映射关系和超像素块到移动平面的映射关系得到最终的场景流估计结果.采用KITTI 2015标准测试图像序列对本文方法和代表性的场景流计算方法进行对比分析.实验结果表明,本文方法具有较高的精度和鲁棒性,尤其对于复杂场景、运动遮挡和运动边缘模糊的图像具有较好的边缘保护作用.     

双层约束下基于局部和全局信息的图像插值新模型

该文提出一种双层约束的图像插值模型,模型在原始未插值图像梯度模约束下同时基于局部和全局信息处理。使用偏微分方程处理边缘像素,锐化边缘同时平滑边缘块状效应;平滑区域像素点的插值操作使用非局部均值模型,非局部均值模型通过对原始图像全局信息加权平均得到待处理图像像素值,图像平滑。使用双层约束模型处理纹理图像可以保持纹理特征,平滑纹理部分线形特征位置的块状效应。最后理论和实验结果证明使用双层控制模型可以直接将噪声图像插值放大。     

采用温控镂空发热网的热像仪与3D激光雷达配准

在热像仪与3D 激光雷达组合感知系统上,对基于特征点的配准问题进行了研究遥结合热像仪与3D 激光雷达的工作特性,设计制作了温控镂空发热网配准靶,可同时为热像仪与3D 激光雷达提供特征点遥红外图像特征点使用Harris 角点探测器进行采集曰为减小混合像素和激光点稀疏的影响,对配准靶平面进行了拟合并对点云进行了配准平面符合度检查,确定了深度图边缘曰使用计算角点附近深度边缘均值的方法提取深度特征点坐标,并对坐标进行了修正曰最后使用NMSM-EM 优化方法对配准结果进行了优化遥基于以上研究成果,使组合感知系统能够在微光条件下完成对移动机器人行驶环境的感知遥     

动态背景下融合运动线索和颜色信息的视频目标分割算法

针对现有动态背景下目标分割算法存在的局限性,提出了一种融合运动线索和颜色信息的视频序列目标分割算法。首先,设计了一种新的运动轨迹分类方法,利用背景运动的低秩特性,结合累积确认的策略,可以获得准确的运动轨迹分类结果;然后,通过过分割算法获取视频序列的超像素集合,并计算超像素之间颜色信息的相似度;最后,以超像素为节点建立马尔可夫随机场模型,将运动轨迹分类信息以及超像素之间颜色信息统一建模在马尔可夫随机场的能量函数中,并通过能量函数最小化获得每个超像素的最优分类。在多组公开发布的视频序列中进行测试与对比,结果表明,本文方法可以准确分割出动态背景下的运动目标,并且较传统方法具有更高的分割准确率。     

基于自适应区域限制FCM的图像分割方法

提出一种基于自适应区域限制FCM（Fuzzy C-Means）的彩色图像分割方法,结合隐马尔科夫模型,把超像素具有区域一致性作为先验知识自适应融入到聚类过程中,以提升聚类性能.算法首先生成图像的超像素,计算像素对该超像素的贡献度,以此计算该超像素的区域隶属度函数;然后根据像素所属超像素是否具有主标签,选择像素级隶属度函数或区域级隶属度函数计算该像素的点对先验概率,以加强分割结果的区域一致性;其中,使用区域隶属度函数将引导聚类优化的方向,因此在迭代过程中去除未被使用的标签;最后迭代终止获得图像的分割结果.实验结果表明,相对于比较算法,本文算法的分割性能有显著提升.     

Superpixels extracted via region fusion with boundary constraint

In this paper, we present an accurate superpixel algorithm by region fusion with boundary constraint (RFBC). Superpixels with regular shape and high boundary adherence can be generated in weak boundary and complex texture regions through our algorithm. RFBC includes two steps which are initial segmentation and region fusion respectively. In initial segmentation, broken Canny edges are connected through edge closing algorithm. Subsequently, the closed Canny edges and SLIC superpixel edges are combined together to form the incipient superpixels. In region fusion, gray Gaussian distribution and adjacent relation are used as priori to compute the degree of similarity across incipient superpixels in GBP algorithm. For concreteness, the information of similarity is propagated between regions and the most similar regions are fused, which are accomplished alternatingly to preserve accurate boundaries. Extensive experiments on the Berkeley segmentation benchmark show that the proposed algorithm outperforms the most state-of-the-art algorithms.     

Depth map misalignment correction and dilation for DIBR view synthesis

The quality of the synthesized views by Depth Image Based Rendering (DIBR) highly depends on the accuracy of the depth map, especially the alignment of object boundaries of texture image. In practice, the misalignment of sharp depth map edges is the major cause of the annoying artifacts at the disoccluded regions of the synthesized views. Conventional smooth filter approach blurs the depth map to reduce the disoccluded regions. The drawbacks are the degradation of 3D perception of the reconstructed 3D videos and the destruction of the texture in background regions. Conventional edge preserving filter utilizes the color image information in order to align the depth edges with color edges. Unfortunately, the characteristics of color edges and depth edges are very different which causes annoying boundaries artifacts in the synthesized virtual views. Recent solution of reliability-based approach uses reliable warping information from other views to fill the holes. However, it is not suitable for the view synthesis in video-plus-depth based DIBR applications. In this paper, a new depth map preprocessing approach is proposed. It utilizes Watershed color segmentation method to correct the depth map misalignment and then the depth map object boundaries are extended to cover the transitional edge regions of color image. This approach can handle the sharp depth map edges lying inside or outside the object boundaries in 2D sense. The quality of the disoccluded regions of the synthesized views can be significantly improved and unknown depth values can also be estimated. Experimental results show that the proposed method achieves superior performance for view synthesis by DIBR especially for generating large baseline virtual views.     

Semi-automatic 2D-to-3D video conversion based on background sprite generation

This paper presents a technique for semi-automatic 2D-to-3D stereo video conversion, which is known to provide user intervention in assigning foreground/background depths for key frames and then get depth maps for non-key frames via automatic depth propagation. Our algorithm treats foreground and background separately. For foregrounds, kernel pixels are identified and then used as the seeds for graph-cut segmentation for each non-key frame independently, resulting in results not limited by objects’ motion activity. For backgrounds, all video frames, after foregrounds being removed, are integrated into a common background sprite model (BSM) based on a relay-frame-based image registration algorithm. Users can then draw background depths for BSM in an integrated manner, thus reducing human efforts significantly. Experimental results show that our method is capable of retaining more faithful foreground depth boundaries (by 1.6–2.7 dB) and smoother background depths than prior works. This advantage is helpful for 3D display and 3D perception.     

Stereo matching based on multi-direction polynomial model

This paper presents a segmentation based stereo matching algorithm. For the purposes of both preserving the shape of object surfaces and being robust to under segmentations, we introduce a new scene formulation where the reference image is divided into overlapping lines. The disparity value and the index of pixels on lines are modeled by polynomial functions. Polynomial functions are propagated among lines to obtain smooth surfaces via solving energy minimizing problems. Finally, the disparity of pixels is estimated from the disparity fields provided by lines. Because lines in multiple directions implicitly segment different objects in an under segmentation region, our method is robust for under segmented regions where it is usually difficult for conventional region based methods to produce satisfactory results. Experimental results demonstrate that the proposed method has an outstanding performance compared with the current state-of-the-art methods. The scene representation method in this work is also a powerful approach to surface based scene representations.     

Automatic image segmentation by integrating color-edge extractionand seeded region growing

We propose a new automatic image segmentation method. Color edges in an image are first obtained automatically by combining an improved isotropic edge detector and a fast entropic thresholding technique. After the obtained color edges have provided the major geometric structures in an image, the centroids between these adjacent edge regions are taken as the initial seeds for seeded region growing (SRG). These seeds are then replaced by the centroids of the generated homogeneous image regions by incorporating the required additional pixels step by step. Moreover, the results of color-edge extraction and SRG are integrated to provide homogeneous image regions with accurate and closed boundaries. We also discuss the application of our image segmentation method to automatic face detection. Furthermore, semantic human objects are generated by a seeded region aggregation procedure which takes the detected faces as object seeds.     

High-dimensional features of adaptive superpixels for visually degraded images

This study presents a novel and highly efficient superpixel algorithm, namely, depth-fused adaptive superpixel (DFASP), which can generate accurate superpixels in a degraded image. In many applications, particularly in actual scenes, vision degradation, such as motion blur, overexposure, and underexposure, often occurs. Well-known color-based superpixel algorithms are incapable of producing accurate superpixels in degraded images because of the ambiguity of color information caused by vision degradation. To eliminate this ambiguity, we use depth and color information to generate superpixels. We map the depth and color information to a high-dimensional feature space. Then, we develop a fast multilevel clustering algorithm to produce superpixels. Furthermore, we design an adaptive mechanism to adjust the color and depth information automatically during pixel clustering. Experimental results demonstrate that regardless of boundary recall, under segmentation error, run time, or achievable segmentation accuracy, DFASP is better than state-of-the-art superpixel methods.     

Convexity constrained efficient superpixel and supervoxel extraction

This paper presents an efficient superpixel (SP) and supervoxel (SV) extraction method that aims improvements over the state-of-the-art in terms of both accuracy and computational complexity. Segmentation performance is improved through convexity constrained distance utilization, whereas computational efficiency is achieved by replacing complete region processing by a boundary adaptation technique. Starting from the uniformly distributed, rectangular (cubical) equal size (volume) superpixels (supervoxels), region boundaries are iteratively adapted towards object edges. Adaptation is performed by assigning the boundary pixels to the most similar neighboring SPs (SVs). At each iteration, SP (SV) regions are updated; hence, progressively converging to compact pixel groups. Detailed experimental comparisons against the state-of-the-art competing methods validate the performance of the proposed technique considering both accuracy and speed.     

Interactive image segmentation based on samples reconstruction and FLDA

Existing interactive image segmentation methods heavily rely on manual input, i.e. a sufficient quantity and correct locations of labels. In this paper, we propose a new interactive segmentation algorithm which aims to reduce human intervention and to generate high-quality segmentation results. In contrast to most energy minimizing based segmentation methods, the segmentation is cast as multi-classification in our proposed method. First, the input image is segmented into superpixels by using different methods. Then we build a dictionary consisting of all obtained superpixels and reconstruct samples represented by certain labeled superpixels. Finally, we learn a discriminative projection matrix through Fishers linear discriminant analysis (FLDA) algorithm, which learns a discriminative subspace for classification. The unlabeled superpixels are grouped into foreground or background, via calculating their minimal norm. Our method can capture long range grouping cues and reduce the sensitivity with respect to input label quantity and location of labels, by the combination of superpixels and discriminative dictionary. Extensive experiments are conducted both on MSRC and another challenging database in order to demonstrate the effectiveness of the proposed method. Quantitative and qualitative results show that our method is competitive to the state-of-the-art performance.