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.     

基于图像分割的深度视频校正算法

在基于深度图的虚拟视点绘制过程中,由于通过深 度估计软件获取的深度视频存在大量的失真,从而导致绘制的虚拟视点中存在纹理失真和缺 失现象。本文围绕深度视频失真类型,提出一种基于分割的深度 视频校正算法。利用彩色深度一致性信息分区域校正深度失真,以解决由于深度块失真造成 的虚拟视点纹理 缺失问题。首先,提取彩色视频运动和边缘区域,得到彩色视频边缘和运动区域掩模图;其 次,在边缘和运 动信息的辅助下,对彩色图像进行Mean Shift聚类,并将不同类别区域赋以不同的标签;最 后,分别统计不 同类别连通区域对应的深度直方图,利用其峰值校正深度视频中深度彩色非一致区域。实验 结果表明,本文提 出的基于分割块的深度视频校正算法优于部分基于像素的滤波算法,可以有效地校正深度视 频块失真,解决 虚拟视点边缘失真和纹理缺失问题,同时虚拟视点质量平均提高了0.20dB。     

RGB空间下结合高斯曼哈顿距离图的彩色图像边缘检测

为了能够更好地利用彩色图像的信息进行边缘检测,提出一种RGB空间下结合高斯曼哈顿距离图的彩色图像边缘检测方法.首先分析了彩色图像到灰度图像转换的信息损失,并给出一种RGB空间下边缘的度量方法.其次,通过引入高斯曼哈顿距离,分别在RGB三个通道进行处理,并通过新的边缘度量法统一获得彩色图像的距离图.最后将距离图映射到0~255的灰度范围内,得到最终的边缘检测结果.实验结果表明,本文方法具有较高的处理速度和较好的处理结果.     

An adaptive color plane interpolation method based on edge detection

In this letter, an adaptive interpolation algorithm based on edge detection is proposed. With this algorithm, all the missing green values can be reconstructed in Bayer pattern image by using edge detection interpolation method. Reconstructed images composed of green pixels are classified according to the high frequency components in image, and the threshold T needed for all kinds of green images in the edge detection is determined through experiments. The edge detection is carried out based on the one Dimensional （1D） gradient operator. If the gradient value is greater than T, this pixel is located on the edge; otherwise the pixel is in the smooth area of the image. Finally, the simple bilinear interpolation is used for the smooth area while the Laplacian interpolation with the second-order correction term is adopted to reconstruct the other red/blue values on the edge. This algorithm resolves effectively the conflicts between reconstructing high quality color image and reducing computational complexity, and thus largely enhances the processing speed for the reconstructed color image.     

Study of single image dehazing algorithm based on propagated filtering and minimum color channels

To solve the challenging problem that the edge regions of image have some remained hazes and blackspots,a novel image dehazing algorithm was proposed based on the minimal color channel and propagated filtering.Firstly,an initial atmospheric transmission map was obtained by double-area filtering,then a minimal channel color was introduced as a reference image,and the propagated filtering was combined to optimize the initial atmospheric transmission map.Optimized transmission have the similar edge characteristics as the referenced image,so the deviation of transmission estimation can be effectively avoided for the edge pixels in the depth mutated regions,and the redundant texture information were removed in the initial transmission map.Finally,L-BFGS was used to restore atmospheric light,and the haze-free image can be recovered based on the atmospheric scattering model.Experimental results show that proposed algorithm has the more accurate transmission estimation for the depth mutated edge regions of image,so the recovered image effectively preserves the edges and details in the depth mutated regions,and has better spatial smoothness in the uniform depth regions.The recovered haze-free image with proposed method has a better sharpness and richer color degree.     

面向虚拟视点图像绘制的深度图编码算法

针对不同区域对绘制虚拟视点图像质量产生不同的影响,以及深度估计不准确导致时域抖动效应影响压缩效率的问题,提出了一种面向虚拟视点图像绘制的深度图压缩算法。通过彩色图像帧差、深度图边缘提取等相关处理过程,提取深度图的静态区域、边缘区域以及动态区域。对深度图边缘区域使用了较低的量化系数,以提高深度图边缘区域编码质量;根据深度图各个区域的编码模式特点,仅对部分编码模式而不是所有模式进行率失真优化搜索,以提高深度图的编码速度;对于深度图P帧的静态区域,合理地采用了SKIP模式,以消除由于深度估计算法的局限性导致时域抖动效应对深度图压缩的影响。实验结果表明,与传统的H.264编码方案相比,本文方案在传输码流大小基本不变的前提下提高了最终虚拟视点图像边缘区域的绘制质量,其余区域主观质量相近,而深度图编码时间则节省了约77～87%。     

An Edge‐Based Adaptive Method for Removing High‐Density Impulsive Noise from an Image While Preserving Edges

This paper presents an algorithm for removing high‐density impulsive noise that generates some serious distortions in edge regions of an image. Although many works have been presented to reduce edge distortions, these existing methods cannot sufficiently restore distorted edges in images with large amounts of impulsive noise. To solve this problem, this paper proposes a method using connected lines extracted from a binarized image, which segments an image into uniform and edge regions. For uniform regions, the existing simple adaptive median filter is applied to remove impulsive noise, and, for edge regions, a prediction filter and a line‐weighted median filter using the connected lines are proposed. Simulation results show that the proposed method provides much better performance in restoring distorted edges than existing methods provide. When noise content is more than 20 percent, existing algorithms result in severe edge distortions, while the proposed algorithm can reconstruct edge regions similar to those of the original image.     

Real-Time Refinement of Kinect Depth Maps using Multi-Resolution Anisotropic Diffusion

In this paper, we present a novel real-time algorithm to refine depth maps generated by low-cost commercial depth sensors like the Microsoft Kinect. The Kinect sensor falls under the category of RGB-D sensors that can generate a high resolution depth map and color image of a scene. They are relatively inexpensive and are commercially available off-the-shelf. However, owing to their low complexity, there are several artifacts that one encounters in the depth map like holes, mis-alignment between the depth map and color image and lack of sharp object boundaries in the depth map. This is a potential problem in applications that require the color image to be projected in 3-D using the depth map. Such applications depend heavily on the depth map and thus the quality of the depth map is of vital importance. In this paper, a novel multi-resolution anisotropic diffusion based algorithm is presented that accepts a Kinect generated depth map and color image and computes a dense depth map in which the holes have been filled and the edges of the objects are sharpened and aligned with the objects in the color image. The proposed algorithm also ensures that regions in the depth map where the depth is properly estimated are not filtered and ensures that the depth values in the final depth map are the same values that existed in the original depth map. Experimental results are provided to demonstrate the improvement in the quality of the depth map and also execution time results are provided to prove that the proposed method can be executed in real-time.     

融合相位一致性与二维主成分分析的视觉显著性预测

为了更加有效地预测图像中吸引视觉注意的关键区域,该文提出一种融合相位一致性与2维主成分分析(2DPCA)的显著性方法。该方法不同于传统的利用相位谱的方式,而是提出采用相位一致性(PC)获取图像中重要的特征点和边缘信息,经快速漂移超像素优化后,融合局部和全局颜色对比度,生成低层特征显著图。接着提出利用2DPCA提取图像块的主成分后,计算主成分空间中图像块的局部和全局可区分性,得到模式显著图。最后,通过空间离散度度量分配合适的权重,使两者融合,提取显著性区域。在两种人眼跟踪数据库上与5种经典算法的实验对比结果表明,该算法能更加准确地预测人眼视觉关注点。     

Salient edge and region aware image retargeting

The purpose of image retargeting is to automatically adapt a given image to fit the size of various displays without introducing severe visual distortions. The seam carving method can effectively achieve this task and it needs to define image importance to detect the salient context of images. In this paper we present a new image importance map and a new seam criterion for image retargeting. We first decompose an image into a cartoon and a texture part. The higher order statistics (HOS) on the cartoon part provide reliable salient edges. We construct a salient object window and a distance dependent weight to modify the HOS. The weighted HOS effectively protects salient objects from distortion by seam carving. We also propose a new seam criterion which tends to spread seam uniformly in nonsallient regions and helps to preserve large scale geometric structures. We call our method salient edge and region aware image retargeting (SERAR). We evaluate our method visually, and compare the results with related methods. Our method performs well in retargeting images with cluttered backgrounds and in preserving large scale structures.     

Color filter array demosaicking: new method and performance measures

Single-sensor digital cameras capture imagery by covering the sensor surface with a color filter array (CFA) such that each sensor pixel only samples one of three primary color values. To render a full-color image, an interpolation process, commonly referred to as CFA demosaicking, is required to estimate the other two missing color values at each pixel. In this paper, we present two contributions to the CFA demosaicking: a new and improved CFA demosaicking method for producing high quality color images and new image measures for quantifying the performance of demosaicking methods. The proposed demosaicking method consists of two successive steps: an interpolation step that estimates missing color values by exploiting spatial and spectral correlations among neighboring pixels, and a post-processing step that suppresses noticeable demosaicking artifacts by adaptive median filtering. Moreover, in recognition of the limitations of current image measures, we propose two types of image measures to quantify the performance of different demosaicking methods; the first type evaluates the fidelity of demosaicked images by computing the peak signal-to-noise ratio and CIELAB /spl utri/E/sup *//sub ab/ for edge and smooth regions separately, and the second type accounts for one major demosaicking artifact-zipper effect. We gauge the proposed demosaicking method and image measures using several existing methods as benchmarks, and demonstrate their efficacy using a variety of test images.     

一种基于线条分类的视频文字检测算法

提出了一种基于边缘的视频文字检测算法.利用Canny算子对图像进行边缘检测,然后根据文字边缘线条的特征,过滤非字符的边缘线条.最后利用文字线条区域的相似性,设置综合阈值,得到最终的文字区域.实验结果表明该算法不仅对规则排列的文字有较高的查全率.对不规则排列及扭曲的文字也能够准确定位.并对光照、阴影等条件不敏感.     

基于无监督栈式降噪自编码网络的显著性检测算法

针对现有的显著性检测算法检测目标类型单一、通用性差的问题,提出一种基于无监督栈式降噪自编码网络的显著性检测算法.该算法利用无监督栈式降噪自编码网络（Stacked Denoising Auto Encoder,SDAE）在多个尺度对原始图像进行稀疏重构,将原始图像与SDAE网络重构图像之间的差作为显著图,二值化后的显著图作为显著性目标检测结果.在SDAE网络训练过程中,将原始图像作为原始数据,网络重构的图像作为观察数据.为了提升网络训练效率,首先利用无监督逐层贪婪方法训练同结构的深度信念网络（Deep Belief Network,DBN）,将训练得到的DBN网络参数设为SDAE网络的初始参数,再计算原始数据与观察数据之间的互信息作为网络收敛代价,利用反向传播进行网络参数微调.实验表明,该网络模型可以完成多类型目标的显著性检测,具有通用性好,准确度高等优点.     

融合颜色特征和对比度特征的图像显著性检测

图像显著性检测能够获取一幅图像的视觉显著性区域,是计算机视觉的研究热点之一。提出一种结合颜色特征和对比度特征的图像显著性检测方法。首先构造图像在HSV空间的颜色函数以获取图像颜色特征;然后使用SLIC超像素分割算法对图像进行预处理,基于超像素块的对比度特征计算图像显著性;最后将融合颜色特征和对比度特征的显著图经过导向滤波优化形成最终的显著图。使用本文算法在公开数据集MSRA-1000上进行图像显著性检测,并与其他6种算法进行比较。实验结果表明本文算法结合了图像像素点和像素块的信息,检测的图像显著性区域轮廓更加完整,优于其他方法。     

Joint-adaptive bilateral depth map upsampling

In this paper, we present a new depth upsampler in which an upsampled depth map is computed at each pixel as the average of neighboring pixels, weighted by color and depth intensity filters. The proposed method features two parameters, an adaptive smoothing parameter and a control parameter. The adaptive smoothing parameter is determined based on the ratio between a depth map and its corresponding color image. The adaptive smoothing parameter is used to control the dynamic range of the color-range filter. The control parameter assigns a larger weighting factor to pixels in the object to which a missing pixel belongs. In a comparison with five existing upsamplers, the proposed method outperforms all five in terms of both objective and subjective quality.     

Similarity relation matrix-based color edge detection

A novel edge detection algorithm for color images was described in this paper. In the proposed method, smoothness of each pixel in color image is firstly calculated by means of similarity relation matrix and is normalized to maximum gray level. In other words, color image in three-dimensional color spaces is mapped into one dimension. Accordingly the edges are performed in such a way that pixels lower than thresholds are assigned to be edge. Thus with proposed method, edge pixels in a color image are detected simultaneously without any complex calculations such as gradient, Laplace and statistical calculations.     

基于半反图像的透射率优化降雾算法

传统的暗原色先验图像降雾算法在处理不满足暗原色先验假设的明亮区域时,估计的透射率不准确。从而导致降雾后的图像色彩出现较大偏差。针对这一不足,本文提出了一种基于半反图像的透射率优化降雾算法。该算法通过明亮区域检测来获取大气光,然后用自定义函数对图像中明亮区域透射率进行修正,最后利用引导滤波器优化初始透射率,恢复出清晰的降雾图像。实验结果表明,该算法可以有效地处理图像中不满足暗原色先验假设的明亮区域,提高了户外视觉系统的鲁棒性。     

基于双引导滤波的红外和可见光图像融合算法

图像融合是将多幅图像中有用或互补信息整合成一幅图像的过程。本文提出了一种基于引导滤波多尺度分解的红外和可见光图像融合算法。在传统的引导滤波图像融合算法的基础之上,利用双引导滤波器代替均值滤波器将源图像分解为小尺度纹理细节、大尺度边缘和基础图像;直接利用纹理细节及边缘层图像构建显著性映射图,用其代替额外的特征提取操作,可很好地突出源图像显著性信息的同时大大降低算法复杂度;利用显著性映射图、Sigmoid函数构造权重图,将源图像中具有视觉意义的信息注入到融合图像中;利用色彩模型转换融合方式,可更好保留图像的色彩信息。定性和定量实验结果证明,相比于传统的基于引导滤波的图像融合算法,本文算法的融合效果得到进一步提升。     

An information fusion method for multispectral image classificationpostprocessing

Remote-sensing image classification is one of the most important techniques in understanding the dynamics of the Earth's ecosystems. Various approaches have been proposed for performing this classification task. Obtained classification results are generally shown as a thematic (or class) map in which each pixel is assigned a class label. Due to sensor noise and algorithm limitations, obtained thematic maps are very noisy. The noise has a “salt-and-pepper” appearance in homogeneous regions and produces weakly defined interregion borders. In this paper, a new postprocessing approach aiming to produce thematic maps with sharp interregion boundaries and homogeneous regions is presented. This approach is conducted in two steps: (1) relevant features derived from the original multispectral image (edge maps) as well as from the thematic map, the Smoothed Thematic Map (STM), are determined and (2) a region-growing algorithm is applied over the thematic map. This algorithm grows until reaching an edge (from the edge maps) or a class change in the STM. The proposed approach fills the requirements of being independent of the used classification algorithm and not knowledge-based (in the sense that no a priori information concerning the contents of the considered image is needed). Tests have been conducted on a Landsat image covering mainly agricultural areas