Approximation of waveforms and contours by one-dimensional pyramid linking

A method of segmenting an image was recently developed based on constructing links between the pixels at consecutive levels in a “pyramid” of successively reduced-resolution versions of the image. We develop here an analgous method of piecewise approximating a waveform or a closed curve by linking nodes in a one-dimensional “pyramid” of reduced-resolution versions of the curve. The method can be efficiently implemented in parallel on a one-dimensional cellular array or cellular “pyramid”.     

不产生精度截断及数据膨胀的图像金字塔

图像金字塔是处理和分析数字图像的重要工具。以图像金字塔为研究对象,旨在减小图像金字塔的存储量,同时解决恢复数据时的精度截断问题。从同一思想出发,提出了两种新的金字塔结构：类均值金字塔与类高斯金字塔;它们都是通过对子像素的简单运算来求得父像素,而这种运算不存在精度截断问题,也不需要额外的比特来保存小数。由于从父像素能够反推出它的子像素之一,所以,在存储金字塔时可以舍弃这部分子像素,从而使所需存储的像素数仅与原始图像相同。对精度、存储量以及构建速度的理论分析与实验结果表明,该金字塔结构具有优良的总体性能。     

Voronoi Pyramids Controlled by Hopfield Neural Networks

We present a novel method for irregular pyramid construction. The contributions of this paper are twofold: (1) Instead of starting with the original regular pixel grid, we first apply an adaptive Voronoi tessellation to the image. This provides the advantage that the number of cells at the bottom level of the pyramid is already reduced as compared to the number of pixels of the original image. (2) For the construction of the irregular pyramid, we present a Hopfield neural network which controls the decimation process. The decimation by Hopfield networks includes naturally the concept of the adaptive pyramid. The validity of our approach is demonstrated by several examples in image segmentation.     

Extracting compact objects using linked pyramids

This correspondence describes a method of extracting compact regions from images using three multiresolution (``pyramid') representations of image features. The method makes use of a gray-level pyramid in which linking of similar nodes at successive levels smooths the image into uniform regions; an edge pyramid in which linking of similarly oriented edge elements serves to delineate the boundaries of the detected regions; and a ``surroundedness' pyramid in which pixels surrounded by edges are detected.     

Heuristic Linking Models in Multiscale Image Segmentation

This paper presents a novel approach to multiscale image segmentation. It addresses the linking of pixels at adjacent levels in scale-space and the labeling of roots representing segments in the original image. In previous multiscale segmentation approaches, linking and root labeling were based on intensity proximity only. The approach proposed here contains multiple heuristic mechanisms that result in a single criterion for linking (affection) and root labeling (adultness). The segmentations are validated by measuring the amount of postprocessing that is needed to reach an objectively defined accuracy of segmentation. The evaluation is performed using three artificial 2D images with different characteristics, and two 2D magnetic resonance brain images. A comparison is made with a pyramid segmentation method. It is found that several of the proposed heuristic link and root mechanisms improve the performance of multiscale segmentation. A very satisfactory segmentation of all images could be obtained by using a fixed set of compromised weight settings of the most effective mechanisms.     

一种高光皮肤多分辨率融合新方法

提出了一种新的皮肤图像融合方法,该方法在对色度-亮度平面内高光和非高光区域像素进行融合时,充分考虑了皮肤像素在此平面内呈现Γ形分布的特点,使像素的插值结果仍然呈现Γ分布。文章最后提供了该方法结合了多分辨率融合算法的实验结果。     

Image filtering using multiresolution representations

It is shown how multiresolution representations can be used for filter design and implementation. These representations provide a coarse frequency decomposition of the image, which forms the basis for two filtering techniques. The first method, based on image pyramids, is used for approximating the convolution of an image with a given mask. In this technique, a filter is designed using a least-squares procedure based on filters synthesized from the basic pyramid equivalent filters. The second method is an adaptive noise reduction algorithm. An optimally filtered image is synthesized from the multiresolution levels, which in this case are maintained at the original sampling density. Individual pixels of the image representation are linearly combined under a minimum mean square error criterion. This uses a local signal-to-noise ratio estimate to provide the best compromise between noise removal and resolution loss     

机载SAR图像的动态金字塔实时显示技术

目的 随着机载SAR（合成孔径雷达）图像分辨率越来越高,幅宽越来越大,传统雷达显控系统将整幅图像放入内存、抽样显示的现有方法存在内存资源紧张、显示图像的等待时间过长等问题,为解决此类问题,提出一种动态金字塔实时显示技术。方法 机载SAR图像实时显示软件包括动态金字塔构建和显示技术。动态金字塔构建技术包括：当接收到一个瓦片的图像数据时,输出第0层级的金字塔瓦片;分6种情况,生成高层级瓦片,随着接收数据不断增多,逐步补全金字塔文件。动态金字塔显示技术是指在瓦片数据不全的情况下,采用递归算法,读取较低层级瓦片,合成、显示当前显示层级图像的技术。这两种技术分属两个独立线程,以硬盘文件（瓦片）为接口,实时交互,协同工作。结果 机载SAR图像实时显示软件仅仅占用30 MB内存,且与图像大小无关;显示第1块SAR图像瓦片的时延小于1 s,与传统显控系统对比,减少约一帧图像的传输时延;显示整帧图像的时延因存储介质读写文件的速率存在差异较大,固态硬盘的时延比较稳定,显示1 GB图像的时延为12.55 s;机械盘的时延受读写速度的影响,当发送时间间隔大于6 ms时,显示1 GB图像的时延仅比传输时延多1.47 s。结论 机载SAR图像实时显示软件能实时向用户呈现接收中的SAR图像,提高了机载SAR图像的显示时效性,降低了机载雷达显控终端的内存需求,改善了机载雷达显控终端的用户体验。     

Pyramid Multi‐View Stereo with Local Consistency

In this paper, we propose a PatchMatch‐based Multi‐View Stereo (MVS) algorithm which can efficiently estimate geometry for the textureless area. Conventional PatchMatch‐based MVS algorithms estimate depth and normal hypotheses mainly by optimizing photometric consistency metrics between patch in the reference image and its projection on other images. The photometric consistency works well in textured regions but can not discriminate textureless regions, which makes geometry estimation for textureless regions hard work. To address this issue, we introduce the local consistency. Based on the assumption that neighboring pixels with similar colors likely belong to the same surface and share approximate depth‐normal values, local consistency guides the depth and normal estimation with geometry from neighboring pixels with similar colors. To fasten the convergence of pixelwise local consistency across the image, we further introduce a pyramid architecture similar to previous work which can also provide coarse estimation at upper levels. We validate the effectiveness of our method on the ETH3D benchmark and Tanks and Temples benchmark. Results show that our method outperforms the state‐of‐the‐art.     

基于双模式联合三边滤波器的深度图像超分辨率方法

彩色图像引导的深度图像超分辨率方法通过利用高分辨率彩色图像的高频信息来重建深度图像,取得了不错的重建效果,但当深度图像和彩色图像边缘不(完全)一致或彩色区域纹理丰富时,重建图像普遍存在边缘模糊和纹理拷贝问题.针对这一问题,提出一种边缘图像引导的双模式联合三边滤波器(DMJTF)方法.该方法利用单幅低分辨率深度图像构建了一个边缘图像金字塔字典,然后利用MRF模型构建了一个高分辨率边缘图像,该图像确定了滤波器的两种模式,分别用于重构深度图像的边缘和平滑区域.实验结果表明DMJTF算法有效地避免了纹理拷贝异常,降低了边缘模糊现象,在定性和定量两个方面都优于其他算法,取得了较好的超分效果.     

基于改进拉普拉斯金字塔的图像融合方法

提出了一种新的基于改进拉普拉斯金字塔变换的图像融合算法。传统拉普拉斯金字塔变换的重构算法在图像在融合过程中会引入噪声,而改进的重构算法能有效抑制融合噪声。首先将图像进行拉普拉斯金字塔分解,得到各层拉普拉斯金字塔图像,针对不同的分解层图像,采用不同的方法进行融合,最后采用改进的拉普拉斯金字塔重构算法进行重构,得到最终的融合图像。通过仿真实验验证了算法的有效性。     

基于多尺度LBP金字塔特征的分类算法

为有效解决旋转变化、光照变化和尺度变化等图像的分类问题,提出一种基于多尺度局部二元模式(LBP)金字塔特征的图像分类算法。通过多尺度LBP金字塔提取各尺度的图像纹理特征,建立图像的多尺度LBP金字塔直方图,并将其作为图像特征向量,采用K-means方法对该特征向量进行降维,以用于图像分类。同时,针对传统二进制权值分布方法对噪声敏感的缺点,提出一种多端权值分布方法。实验结果表明,多尺度LBP金字塔方法具有较好的可鉴别性及图像描述能力,而多端权值分布法也能提高图像的分类精度。     

基于空间金字塔的镜头检测

提出一种HSV颜色直方图与像素的位置空间金字塔结合的方法,该方法既考虑像素的信息,又考虑了像素的位置信息,来进行视频镜头分割。将图像进行一次亚采样,对得到的第一层亚采样图像进行均匀的四分割;对得到的四块小区域分别计算其颜色直方图,获得四个特征向量;将第一层亚采样的图像再进行一次亚采样,得到第二层亚采样图像,并计算其颜色特征向量;将五个特征向量级联,作为图像帧的特征,并计算相邻两个帧的相似度。该算法不仅考虑了像素信息,还考虑了像素位置信息,而且考虑的是全局位置信息和局部位置信息。实验结果显示,该方法较好地权衡了查全率和查准率。     

基于FFT与互信息准则的分层遥感图像配准

提出了一种基于傅立叶变换和互信息准则的分层遥感图像自动配准方法。通过小波变换构造图像金字塔;在小波分解的最顶层,采用基于傅立叶变换的方法确定图像间的变换参数,并作为下一层搜索的粗略位置;然后根据互信息最大的原则逐层细化,直到最底层。试验结果表明:采用所提的方法,克服了基于互信息准则的分层配准方法耗时长的缺点,且利用分层细化的搜索策略增加了基于傅立叶变换的误差修正过程,提高了配准精度。     

一种快速全局运动估计算法

为了对全局运动进行准确快速的估计,在对全局运动估计算法进行研究的基础上,提出了一种快速全局运动估计算法。该算法基于非线性密度估计,采用了六参数的仿射模型。为了提高计算速度,采用了3层金字塔进行多分辨率计算,而且在每层迭代计算中,将基于块的外点去除算法与特征点提取算法相结合,这样既加快了算法的速度,又提高了计算结果的准确性。全局运动估计的实验结果表明,该算法在速度和准确性上具有一定的优势。     

基于融合及数学形态学的遥感图像目标检测

提出了一种基于融合及数学形念学的遥感图像目标检测的新方法。在分析了steerable金字塔变换特性的基础上,采用合理的融合规则将两幅遥感图像进行融合,得到了目标更为清晰的增强图像,有利于进一步的目标检测。然后再利用数学形态学方法及目标的特征对融合后的目标进行检测,得到了满意的检测效果,实验结果表明了本文所提方法的有效性。     

采用LBP金字塔的人脸描述与识别

为了有效地提取人脸图像的全局和局部特征以提高人脸识别的性能,提出一种基于LBP金字塔特征的人脸描述与识别算法.首先通过多尺度分析构建人脸图像金字塔;然后采用LBP算子提取各层图像的LBP特征谱,建立图像的LBP金字塔;最后对LBP金字塔各层特征谱进行分块统计,并将各层的统计直方图序列连接起来作为人脸的鉴别特征用于分类识别.该算法在ORL和FERET人脸数据库上取得了较高的人脸识别率.实验分析表明,LBP金字塔特征具有较强的人脸描述能力和可鉴别性,且对光照、人脸表情及位置的变化具有较高的鲁棒性.     

六边形正交影像金字塔图像压缩算法研究

六边形正交变换由对人眼视觉传输机制的模拟过程所推导,具有仿生、自我类似、高效能等特性,可直接建立相应的影像金字塔。其变换的基函数具有正交性,自我类似性,并与频率域、空间域和方向相关等特性。论文以六边形图像采样技术为基础,结合小波零树压缩的基本思路,提出了一种基于六边形正交影像金字塔的影像压缩算法。该算法具有运算速度快、编码效率高的优点,在保证精度的条件下取得了比传统的基于矩形机制的压缩方法更好的压缩效果。     

稀疏光流快速计算的动态目标检测与跟踪

动态目标的检测与跟踪作为图像处理和计算机视觉学科的重要分支,广泛应用于军事和民用等各个领域。文中提出一种基于稀疏光流快速计算的目标检测和跟踪新方法,该方法通过计算能反映图像特征的特定像素点光流矢量来实现目标检测和跟踪,同时结合图像金字塔技术,可以检测和跟踪运动速度更快、运动尺度更大的目标。文中将该方法分别与稠密光流方法和基于颜色特征方法作对比,结果表明该方法有计算量小、能很好应对目标遮挡情况和能检测和跟踪运动速度较快的目标等诸多优点。实验在多种条件下对该方法进行了验证,跟踪准确率都能达到80%以上,且基本能符合实时性的要求,说明该方法具有可行性和实用价值。     

Variable pyramid structures for image segmentation

Linked pyramid structures have proved to be a useful tool in digital image processing for many applicatins because of their ability to face problems at different levels of detail. Some variations suggested by usage to existent pyramid algorithms have been investigated for the segmentation of compact objects in noisy IR images. In particular, the efficacy of increasing the span at the very last iterations in order to correct the link deficiency of the boundary nodes is reported. We also report about a method which separate segment roots at any level in the pyramid and mergess the segments under the constraint of the maximum number of regions to be distinguished. The method is applied to IR image segmentation and comparative results are given.