视图插补与透视同伦变换

基于未标定图像序列实现任意视点插补,是目前视点插补技术研究中的热点.本文首次将同伦变换引入视点插补问题研究中,提出并证明了基于透视同伦变换的视图插补定理,并针对可忽略遮挡关系的简单场景给出了基于未标定图像序列的透视同伦变换.算法实现的关键在于对摄像机内外参数的估计,同时对实验结果作了详细分析,指出实验结果的优劣(算法实现瓶颈)在于对应关系的建立.     

柱面全景图像视图合成中的关键问题研究

图像校正和插值是基于柱面全景图像视图合成中的关键问题。首先分析了极线采样方法在柱面图像校正像素保持率和像素有效率上的优势,通过计算极线的数量、范围及起止位置,有效保留了源图像的信息,减少了以往算法中由于使用单应性映射而导致的弱采样和过采样效应;其次,在新视点插值上,根据柱面全景图像的成像模型,推导了合成视图上像素点的位置和颜色计算公式。最后给出了基于仿真图像和实际图像的视图合成结果。      

Hybrid dual stream blender for wide baseline view synthesis

Free navigation of a scene requires warping some reference views to some desired target viewpoint and blending them to synthesize a virtual view. Convolutional Neural Networks (ConvNets) based methods can learn both the warping and blending tasks jointly. Such methods are often designed for moderate inter-camera baseline distance and larger kernels are required for warping if the baseline distance increases. Algorithmic methods can in principle deal with large baselines, however the synthesized view suffers from artifacts near disoccluded pixels. We present a hybrid approach where first, reference views are algorithmically warped to the target position and then are blended via a ConvNet. Preliminary view warping allows reducing the size of the convolutional kernels and thus the learnable parameters count. We propose a residual encoder–decoder for image blending with a Siamese encoder to further keep the parameters count low. We also contribute a hole inpainting algorithm to fill the disocclusions in the warped views. Our view synthesis experiments on real multiview sequences show better objective image quality than state-of-the-art methods due to fewer artifacts in the synthesized images.     

三维重构系统的极线矫正算法研究

在设计三维重构系统的过程中发现,极线矫正算法的优劣将直接关系到三维重构结果的准确性和精确度。因此,文中采用了先进行控制点变换再进行灰度值插值的算法来达到极线矫正的目的。该方法通过控制点变换来定义空间变换本身,用其来描述每个像素如何从初始位置"移动"到终止位置,再利用灰度值插值算法产生一个光滑映射,并将像素点的灰度值改变,从而达到矫正的目的。文中不仅对矫正前后左右目摄像头采集到的图像进行了对比,还对右图矫正前后的灰度波形进行了对比,矫正后的图像整体向左平移了150个像素点。     

基于即时稠密三维重构的无人机视觉定位

传统景象匹配定位方法在用于低空无人机定位时,易因低空航拍图像视场小,且与卫星图像（带有地理信息）的拍摄角度差异大而失败.本文提出了一种基于即时稠密三维重构的无人机视觉定位方法,通过将稠密三维点云与卫星图像匹配以实现无人机定位.首先根据图像序列快速估计摄像机位姿,而后使用多深度图协同去噪与优化算法生成稠密三维点云,随后通过变换观察视角由稠密三维点云生成与卫星图像拍摄视角相近的虚拟视图,最后将虚拟视图与卫星图像匹配并得到无人机的地理坐标.由于稠密三维点云包含多张图像的信息,覆盖面积大,且可变化观察视角,因此能够有效克服上述两个问题.实验证明了本文方法的有效性.     

多光学传感器的图像拼接系统的设计

当要求的场景尺寸超出一个光学传感器的范围时,同时取得一个完整的场景就成为难点。针对这一问题,提出一套小型的视场拼接系统。采用多个光学传感器同时对场景进行采集,得到几幅互相有一定重叠的图像。然后进行图像配准和图像融合,实现无缝大视场的拼接。     

基于逆向映射的空洞填补方法

为了有效填补虚拟视点图像中的公共空洞,提出 了一种基于逆向映射的空洞填补方法。 首先利用深度图像绘制(DIBR)技术将左、右参考视点映射到虚拟视点位置,利用图像膨胀方 法将映射的虚拟视图中的空 洞区域进行扩大,以消除虚拟视点图像中的伪影瑕疵;然后,提取出膨胀后空洞区域的边界 ,并将其逆映 射到原始的参考图像中,根据空洞与边界的相对位置,选取原始图像中相对位置上的像素来 填充虚拟视图 中的空洞区域;最后,将空洞填补之后的左、右视点映射的虚拟视图进行融合获得最终的虚 拟视图。实验 证明,本文方法有效解决了传统空洞填补方法容易将前景像素填充到背景区域的问题,能 够获得较好的视觉观看效果和较高的客观峰值信噪比(PSNR)值。     

3D modeling and rendering from multiple wide-baseline images by match propagation

In this paper, we present a method for modeling a complex scene from a small set of input images taken from widely separated viewpoints and then synthesizing novel views. First, we find sparse correspondences across multiple input images and calibrate these input images taken with unknown cameras. Then one of the input images is chosen as the reference image for modeling by match propagation. A sparse set of reliably matched pixels in the reference image is initially selected and then propagated to neighboring pixels based on both the clustering-based light invariant photoconsistency constraint and the data-driven depth smoothness constraint, which are integrated into a pixel matching quality function to efficiently deal with occlusions, light changes and depth discontinuity. Finally, a novel view rendering algorithm is developed to fast synthesize a novel view by match propagation again. Experimental results show that the proposed method can produce good scene models from a small set of widely separated images and synthesize novel views in good quality.     

Image interpolation by adaptive 2-D autoregressive modeling and soft-decision estimation.

The challenge of image interpolation is to preserve spatial details. We propose a soft-decision interpolation technique that estimates missing pixels in groups rather than one at a time. The new technique learns and adapts to varying scene structures using a 2-D piecewise autoregressive model. The model parameters are estimated in a moving window in the input low-resolution image. The pixel structure dictated by the learnt model is enforced by the soft-decision estimation process onto a block of pixels, including both observed and estimated. The result is equivalent to that of a high-order adaptive nonseparable 2-D interpolation filter. This new image interpolation approach preserves spatial coherence of interpolated images better than the existing methods, and it produces the best results so far over a wide range of scenes in both PSNR measure and subjective visual quality. Edges and textures are well preserved, and common interpolation artifacts (blurring, ringing, jaggies, zippering, etc.) are greatly reduced.     

基于色差空间的Bayer 图像的迭代插值算法

单CCD/CMOS 传感器相机捕捉图像信息靠在传感器表面覆盖一层颜色滤波阵列(CFA),经过CFA 后每个像素点只能获得物理三基色(红,绿,蓝)其中一种分量。另外缺少的两种颜色分量,需要通过周围像素的值来估算。首先利用55 模板内的像素来估计插值的方向并用最优的权重系数来插值G 分量。其次利用了基于有理函数的二维插值算子在色差空间插值R(B)处缺少的B(R)分量。再次利用色差插值G 处缺少的R 和B 分量。最后,使用方差约束条件,迭代插值过程被重复多次直到达到了最优的插值结果。通过在24 幅柯达图片以及笔者相机拍摄的图片上的Matlab 仿真实验,结果显示,被提出的算法无论是在视觉方面还是在量化的数据方面都表现出了优势。     

Image change detection using Gaussian mixture model and genetic algorithm

In this paper, we propose a novel method for unsupervised change detection in multi-temporal satellite images of the same scene using Gaussian mixture model (GMM) and genetic algorithm (GA). The difference image data computed from multi-temporal satellite images of the same scene is modelled by using N components GMM. GA is used to estimate the parameters of the GMM. Then, the GMM of the difference image data is partitioned into two sets of distributions representing data distributions of “changed” and “unchanged” pixels by minimizing a cost function using GA. Bayesian inference is exploited together with the estimated data distributions of “changed” and “unchanged” pixels to achieve the final change detection result. The proposed method does not need any parameter tuning process, and is completely automatic. As a case study for the unsupervised change detection, multi-temporal advanced synthetic aperture radar (ASAR) images acquired by ESA Envisat on the recent flooding area in Bangladesh and parts of India brought on by two weeks of persistent rain and multi-temporal optical images acquired by Landsat 5 TM on a part of Alaska are considered. Change detection results are shown on real data and comparisons with the state-of-the-art techniques are provided.     

Edge-directed interpolation based on shifted-linear image model

This paper presents a hybrid image interpolation algorithm to keep details and edges simultaneously. The basic idea is to separate the unknown pixels into two classes and estimate them in different way. One class of unknown pixels is obtained via shifted linear interpolation and the other class through statistical signal processing method. The merit of this hybrid algorithm is that each unknown pixel can be estimated through original pixels simultaneously. Simulation results demonstrate that this hybrid interpolation algorithm improves the quality of the interpolated images over conventional interpolation methods.     

探测器阵列靶的激光光斑图像复原方法研究

为了准确地测量激光远场光斑参数,使得阵列探测法的研究逐渐成为热点。而阵列式靶板仪靶面探测器受空间物理限制和研发成本等因素影响均不能均匀紧密的排布,这将造成采样光斑失真。利用已知采样点参数对光斑图像实现高精度复原是利用阵列探测法测量光斑参数必须要解决的问题。因此,提出采用改进型的双三次插值算法对光斑图像进行复原。仿真分析并对比改进型双三次插值算法和其他插值算法,结果表明:运用改进型插值算法计算得到光斑总能量误差为1.7 %,光斑质心坐标偏移量在x轴方向和y轴方向较最邻近插值算法和双线性插值算法相比均能降低7.8 %和3.3 %,处理时间较双三次插值算法至少缩短35 %。该研究为提高阵列探测法测量远场光斑参数精度积累了一定的理论基础和实验数据。     

模拟驾驶器山区道路虚拟驾驶研究

针对山区道路模拟驾驶体验的特点,提出了模拟驾驶场景中预定义和路面感应计算相结合的实时控制虚拟车辆运行方法。在虚拟场景中预定义自走车辆运动轨迹,通过时间控制位置和方位的线性插补方法使其运行。对于驾驶车辆模型,文中用方向盘信号和车辆轮胎在路面的空间位置坐标实时计算车辆的位置和方位姿态,使车辆行驶与山区路面的坡度、弯道倾斜、粗糙度等状况等相吻合,增强了山区道路安全驾驶的真实体验感。     

一种改进的双线性插值图像放大算法

针对传统的双线性插值图像放大算法存在的边缘模糊问题,提出一种改进算法：先计算插值点的双线性插值和最近邻点插值,然后以4个邻点的灰度方差构造权重,将二种插值进行加权融合获得最终插值结果。该算法既考虑到插值点与邻点之间距离关系,又考虑到邻点的灰度分布特性,有效地提高了放大图像的质量。实验结果验证了算法的有效性。     

基于精确模型和逆投影的超大视场红外图像畸变校正

针对超大视场红外图像畸变大、与人眼视觉差异明显的问题,提出了一种基于精确模型和逆投影的超大视场红外图像畸变校正算法以改善其视觉效果.该算法首先利用精确模型对超大视场红外相机成像中的物、像关系进行描述;然后,针对红外图像像素采样率不高的缺点,利用较为精确的三次卷积插值法对图像进行插值来补全成像信息;最后,根据校正图像上的待赋值像点的坐标,结合校正模型和超大视场红外相机精确模型,计算该像点逆投影到插值图像时的对应坐标,并以最近邻像点像素值作为校正后图像像点的赋值.车载道路场景下的超大视场红外图像畸变校正实验结果显示,所提出的算法图像校正结果边界清晰、无锯齿效应,对场景中的直线平均还原偏差小于0.35 pixels,表明该算法对超大视场红外图像畸变校正具有较好的适用性.     

基于最优斜面参数估计的局部立体匹配算法

针对传统局部匹配算法在斜面场景匹配中所表现出的阶梯效应,提出了一种基于最优斜面参数估计的局部立体匹配算法。该算法首先为每一个像素随机地分配一组斜面参数,然后以新的斜面参数所定义的支撑域下当前像素的匹配代价是否减小为准则,迭代地进行斜面参数的邻域传播-单点优化过程,并最终使得计算结果收敛到最优斜面,同时估计得到稠密的亚像素级视差。通过对典型斜面场景图像和Middlebury 标准测试图像对的匹配实验表明,文中算法在将对普通场景的匹配效果保持在当前先进水平的同时,对斜面场景的匹配消除了阶梯效应,且匹配率代表了局部匹配的先进水平。     

Interactive Natural Image Segmentation via Spline Regression

This paper presents an interactive algorithm for segmentation of natural images. The task is formulated as a problem of spline regression, in which the spline is derived in Sobolev space and has a form of a combination of linear and Green's functions. Besides its nonlinear representation capability, one advantage of this spline in usage is that, once it has been constructed, no parameters need to be tuned to data. We define this spline on the user specified foreground and background pixels, and solve its parameters (the combination coefficients of functions) from a group of linear equations. To speed up spline construction, K-means clustering algorithm is employed to cluster the user specified pixels. By taking the cluster centers as representatives, this spline can be easily constructed. The foreground object is finally cut out from its background via spline interpolation. The computational complexity of the proposed algorithm is linear in the number of the pixels to be segmented. Experiments on diverse natural images, with comparison to existing algorithms, illustrate the validity of our method.     

High efficiency depth image-based rendering with simplified inpainting-based hole filling

Hole and crack filling is the most important issue in depth-image-based rendering (DIBR) algorithms for generating virtual view images when only one view image and one depth map are available. This paper proposes a priority patch inpainting algorithm for hole filling in DIBR algorithms by generating multiple virtual views. A texture-based interpolation method is applied for crack filling. Then, an inpainting-based algorithm is applied patch by patch for hole filling. A prioritized method for selecting the critical patch is also proposed to reduce computation time. Finally, the proposed method is realized on the compute unified device architecture parallel computing platform which runs on a graphics processing unit. Simulation results show that the proposed algorithm is 51-fold faster for virtual view synthesis and achieves better virtual view quality compared to the traditional DIBR algorithm which contains depth preprocessing, warping, and hole filling.     

基于小波的双线性插值误差补偿算法的图像放大

为了尽可能地保持低分辨率图像的基本信息,提高图像的视觉效果和空间分辨率,本文提出一种基于小波的双线性插值误差补偿算法。该算法增加双线性插值的误差补偿项,利用Sobel算子设定插值点的边缘方向,得到初始放大图像。利用小波提取高频成分,原始图像幅值增强充当低频部分,再经过小波逆变换得到高分辨率图像。实验结果表明,相对于传统的图像放大算法,该算法考虑到全局相关性,得到更加清晰的边缘信息。