图像拼接技术

Image mosaics have been an active area of research in the fields of computer vision,image processing and computer graphics in recent years.The automatic fast construction of unlimited field of view,high-resolution image mosaics is a main research task of this area.According to the procedure of image mosaics,the paper introduces and discusses image acquisition,geometric corrections,image register and image blending in detail.In the last part of the paper,we make a discussion on some problems of research and point out the future research directiions.     

Experimental evaluation of a real-time GPU-based pose estimation system for autonomous landing of rotary wings UAVs

This paper proposes a real-time system for pose estimation of an unmanned aerial vehicle (UAV) using parallel image processing and a fiducial marker. The system exploits the capabilities of a high-performance CPU/GPU embedded system in order to provide on-board high-frequency pose estimation enabling autonomous takeoff and landing. The system is evaluated extensively with lab and field tests using a custom quadrotor. The autonomous landing is successfully demonstrated, through experimental tests, using the proposed algorithm. The results show that the system is able to provide precise pose estimation with a framerate of at least 30\,fps and an image resolution of 640?480 pixels. The main advantage of the proposed approach is in the use of the GPU for image filtering and marker detection. The GPU provides an upper bound on the required computation time regardless of the complexity of the image thereby allowing for robust marker detection even in cluttered environments.     

Directional EMD and its application to texture segmentation

Image processing has been a subject with systematic theory and extensive applica-tions including video processing, medical image processing, remote sensing image processing and the techniques attracting attention recently such as biometrics and visual surveillance, etc. Since multi-scale is one of the main features of natural images, there have been a series of methods for representing the quality of images such as multi-scale technique based on diffusion equation[1], that based on morphologica…     

Memristive crossbar array with applications in image processing

A memristor is a kind of nonlinear resistor with memory capacity.Its resistance changes with the amount of charge or flux passing through it.As the fourth fundamental circuit element,it has huge potential applications in many fields,and has been expected to drive a revolution in circuit theory.Through numerical simulations and circuitry modeling,the basic theory and properties of memristors are analyzed,and a memristor-based crossbar array is then proposed.The array can realize storage and output for binary,grayscale and color images.A series of computer simulations demonstrates the effectiveness of the proposed scheme.Owing to the advantage of the memristive crossbar array in parallel information processing,the proposed method is expected to be used in high-speed image processing.     

QSobel:A novel quantum image edge extraction algorithm

Edge extraction is an indispensable task in digital image processing. With the sharp increase in the image data, real-time problem has become a limitation of the state of the art of edge extraction algorithms.In this paper, QSobel, a novel quantum image edge extraction algorithm is designed based on the flexible representation of quantum image(FRQI) and the famous edge extraction algorithm Sobel. Because FRQI utilizes the superposition state of qubit sequence to store all the pixels of an image, QSobel can calculate the Sobel gradients of the image intensity of all the pixels simultaneously. It is the main reason that QSobel can extract edges quite fast. Through designing and analyzing the quantum circuit of QSobel, we demonstrate that QSobel can extract edges in the computational complexity of O(n2) for a FRQI quantum image with a size of2 n × 2n. Compared with all the classical edge extraction algorithms and the existing quantum edge extraction algorithms, QSobel can utilize quantum parallel computation to reach a significant and exponential speedup.Hence, QSobel would resolve the real-time problem of image edge extraction.     

A memristor-based architecture combining memory and image processing

Image processing is a type of memory-access-intensive application and is applied in many fields.Logic operations are very simple ones in image processing.During these operations,memory access takes a majority of the total time consumed,which puts a great pressure on memory access speed and bandwidth.However,in traditional von Neumann architecture,memory access is the inherent bottleneck of the system;that is,the speed of memory’s data supply is far lower than the data request of processor.Memristor is considered to be the fourth circuit element after resistor,capacitor and inductor.It has the capacity of both processing and memory,which supplies a new idea for solving the"memory wall"problem.In this paper,memristor is used to build an architecture combining computing and memory,where the memory has the ability to handle some simple image processing operations.This architecture can reduce readings and writings of memory effectively,which saves memory bandwidth thus improving the efficiency of the system.Logic operations of images are considered in this paper to validate the architecture.The experimental results and theoretical analysis indicate that the architecture can reduce memory access effectively.     

Filtering images contaminated with pep and salt type noise with pulse-coupled neural networks

As a typical type of noise in many image related applications, pep and salt (PAS) type noise reduces the quality of the image seriously. Median filter and its variations[1—3] are the earliest filtering algorithms for filtering this type of noise, with the drawback that filtering is performed to all of the pixels in the image, which leads to a severe blur of the filtered image. To tackle this problem, Sun and Neuval[4], and Florencio et al.[5] pre-sented a switch median filtering method whic…     

Multi-toning Image Adjustment

Due to the different lighting environments or other reasons,the pixel colors may be quite different in one image which causes distinct visual discontinuities.It makes the analysis and processing of such an image more difficult and sometime impossible.In this paper,a unified multi-toning image adjustment method is proposed to solve this problem.First,a novel unsupervised clustering method was proposed to partition the source and the target image into a certain number of subsets with similar color statistics.By matching the texture characteristics and luminance distribution between the blocks,it can create optimized correspondence.Then,the color information was transferred from the matched pixels in the source blocks to the target ones.Graph cut method was used to optimize the seams between different subsets in the final step.This method can automatically perform color adjustment of a multi-toning image.It is simple and efficient.Various results show the validity of this method.     

Dynamic Fractal Transform with Applications to Image Data Compression

A recent trend in computer graphics and image processing is to use Iterated Function System(IFS)to generate and describe both man-made graphics and natural images.Jacquin was the first to propose a fully automation gray scale image compression algorithm which is referred to as a typical static fractal transform based algorithm in this paper.By using this algorithm,an image can be condensely described as a fractal transform operator which is the combination of a set of reactal mappings.When the fractal transform operator is iteratedly applied to any initial image,a unique attractro(reconstructed image)can be achieved.In this paper,a dynamic fractal transform is presented which is a modification of the static transform.Instea of being fixed,the dynamic transform operator varies in each decoder iteration,thus differs from static transform operators.The new transform has advantages in improving coding efficiency and shows better convergence for the deocder.     

Multi-polarimetric SAR image compression based on sparse representation

The use of sparse representation in signal and image processing has gradually increased over the past few years.Obtaining an over-complete dictionary from a set of signals allows us to represent these signals as a sparse linear combination of dictionary atoms.By considering the relativity among the multi-polarimetric synthetic aperture radar(SAR)images,a new compression scheme for multi-polarimetric SAR image based sparse representation is proposed.The multilevel dictionary is learned iteratively in the 9/7 wavelet domain using a single channel SAR image,and the other channels are compressed by sparse approximation,also in the 9/7 wavelet domain,followed by entropy coding of the sparse coefficients.The experimental results are compared with two state-of-the-art compression methods:SPIHT(set partitioning in hierarchical trees)and JPEG2000.Because of the efficiency of the coding scheme,our method outperforms both SPIHT and JPEG2000 in terms of peak signal-to-noise ratio(PSNR)and edge preservation index(EPI).     

自动检测图像目标的形态滤波遗传算法

提出了一种实现形态滤波器参数优化设计的贵传学习算法（Genetic Training Algorithm for Morphologi-cal Fitters,GTAMF）。采用新的交叉与变异算子－曲面体交叉与主从式变异,通过优化搜索全局以获得滤波性和时效性兼优的形态滤波器参数。实验结果表明该方法设计方便,实用性强且易于推广,对提高形态滤波性能效果明显,分析表明,形态滤波器可分解为形态学运算和结构元选择两个基本问题,形态学运算的规则已由定义本身而确定,于是形态滤波器的最终滤波性能就仅仅取决于结构元的选择。通过自适应优化训练使结构元具有图像目标的形态结构特征,从而赋予结构元特定的知识,使形态滤波过程融入特有的智能,以实现对复杂变化的图像具有良好的滤波性能和稳健的适应能力。     

Automatic target detection by optimal morphological filters

It is widely accepted that the design of morphological filters,which are optimal in some sense,is a difficult task.In this paper a novel method for optimal learning of morphological filtering parameters(Genetic training algorithm for morphological filters,GTAMF)is presented.GTAMF adopts new crossover and mutation operators called the curved cylinder crossover and master-slave mutaition to achieve optimal filtering parameters in a global searching,Experimental results show that this method is practical,easy to extend,and markedly improves the performances of morphoological filters.The operation of a morphological filter can be divided into two basic problems including morphological operation and structuring element (SE)Selection.The rules for morphological operations are predefined so that the filter‘s properties depend merely on the selection of SE.By means of adaptive optimization training,structureing elements possess the shape and structural characteristics of image targets,and give specific information to SE.Morphological filters formed in this way become certainly intelligent and can provide good filtering results and robust adaptability to image targets with clutter background.     

基于小波边缘提取的混合运动目标检测算法

常用的运动目标检测算法易受到噪声、阴影等因素的影响,检测出来的运动目标边缘比较模糊,本文因此提出 一种基于小波边缘提取的运动目标检测算法,将小波边缘检测与帧间差分法和背景差分法相结合来检测运动目标,采用 形态学滤波和连通性分析得到准确的运动目标。实验表明,该算法可以准确的将运动目标从视频图像序列中检测出来。     

基于超宽带技术的运动目标跟踪高精度定位系统设计

为克服运动目标不断变化导致跟踪定位精度较低的问题,设计基于超宽带技术的运动目标跟踪高精度定位系统。图像采集模块由FPGA单元、VGA显示单元、帧缓存单元以及图像采集单元构成,以此实现运动目标跟踪与定位中的图像采集,在超宽带技术模块中,设计超宽带运动目标定位所需的天线、定位基站、移动节点,完成超宽带动态组网,实现硬件系统的设计。基于硬件系统采集到的图像,实施图像灰度化处理、形态学滤波处理,以增强图像中有用的信息,设计TLD运动目标跟踪算法,随着运动目标开始运动,TLD模型会不断学习跟踪的运动目标,获取目标在距离、景深、角度等层面的改变,并不断学习、识别,达到良好的跟踪效果,基于超宽带技术设计运动目标动态定位算法,依据跟踪结果实现运动目标的高精度定位,完成软件系统的设计。实验测试结果表明,该系统在中、远距离目标跟踪与定位实验中跟踪错误率低于0.60%、2.4%,沿着S 型运动时,路线弯折处的定位误差较低,与实验运动目标的飞行路线相贴合,具有良好的定位能力。     

三维运动目标的多尺度智能递推识别新方法

在实际成像条件下,运动中的三维目标,其投影形状(Silhouette)是变化的,因而其可识别性也处于变动中．为了应对这类困难情况,本文定义了模式的动态特征空间和模式的动态可识别性等概念．讨论了建立多尺度三维目标特性视图特征模型的必要性,以及将目标运动特性一般约束用于目标序列图像识别的合理性．据此,提出了处理三维目标运动图像序列的多尺度智能递推识别方法(MUSIRR)．构造了一种混合神经网络和逻辑决策模块的智能识别器,BP神经网和RBF网用作识别器的基本构成单元．在训练阶段,该识别器使用目标的多尺度二值特性视图模型的规则矩不变量为样本特征向量．在识别阶段,算法在递推识别序列目标图像过程中,充分利用了目标姿态不会突变以及有关成像过程的合理约束,达到了提高识别率目的．与文献中的基于单尺度特性视图的三维目标识别方法相比,本文的方法训练过程简单,只需较少的目标特性视图模型样本,不仅能处理单帧图像,更能有效处理序列图像．对几类飞机目标的大规模模拟实验结果证实了本文方法的合理性和有效性．     

带非线性约束的自适应高斯和卡尔曼滤波目标跟踪算法

无线传感网络中运动目标状态通常满足某种非线性状态约束,为了提高对传感网络中运动目标的跟踪精度,降低非高斯噪声对状态估计的影响,避免高斯项数在迭代过程中的冗余累积,提出一种带非线性约束的权值自适应高斯和卡尔曼滤波算法.算法在每个时刻计算目标当前状态的高斯子项集合,并对每个高斯子项分别以无迹卡尔曼滤波进行状态估计.设计了一种高斯子项权值自适应策略动态调节子项权值,以实现无约束状态下的全局估计.将目标的非线性状态约束引入滤波器结构中时,考虑将其看作一类无约束状态估计的约束投影问题,通过状态约束信息先验来修正运动目标的状态估计.仿真结果表明,该算法与目前的非线性约束卡尔曼滤波相比具有更高的跟踪精度.     

基于改进Camshift的穿墙雷达运动人体目标成像跟踪算法

针对穿墙雷达运动人体目标图像"闪烁"与"抖动"的特点,提出基于改进Camshift的穿墙雷达运动人体目标成像跟踪算法。首先,针对形成的连续多帧穿墙雷达图像以及对应的颜色概率分布图,引入目标预测过程以确定图像中运动目标搜索波门,消除波门外的杂波干扰;然后,利用颜色概率分布图,在波门内自适应迭代调整目标搜索窗尺度,匹配形状与大小变化的目标图像以提取目标位置;最后,对提取的目标位置进行α-β滤波,形成连续平滑的目标运动跟踪航迹,实现基于穿墙雷达成像的建筑物内运动人体稳定航迹跟踪。多输入多输出（MIMO）穿墙雷达实验结果显示,与传统Camshift和Meanshift算法相比,改进后算法的跟踪航迹误差分别降低了40.99%和43.09%,获得了更加准确和平滑的目标运动航迹。     

基于Vibe背景建模的运动目标检测算法

在运动目标检测的过程中，传统算法基于对单一特征背景进行建模，对背景描述不够准确，针对这个问题，本文提出融入颜色和边缘特征的Vibe背景建模.解决了三帧差分法在运动目标检测结果中出现噪声、断点与内部空洞等问题，并采用基于形态学处理方法对图像处理的结果进行补偿.为了保证运动目标检测的准确性，加快消除Vibe算法中第一帧出现“鬼影”现象，本文结合了Vibe算法和改进的三帧差分法对运动目标实现实时检测.通过研究分析与计算推导，实验中运动目标的检测结果表明，基于Vibe背景建模的改进三帧差分法检测效果明显优于三帧差分法.     

六足机器人动态目标检测与跟踪系统研究

动态目标检测与目标跟踪是图像领域的热点研究问题,为研究其在移动机器人领域的应用价值,设计了六足机器人动态目标检测与跟踪系统。针对非刚体运动目标容易被检测为多个分散区域的问题提出区域合并算法,并通过对称匹配、自适应外点滤除对运动背景进行精确补偿,最终基于背景补偿法实现对运动目标的精确检测。研究了基于KCF（Kernel Correlation Filter）的目标跟踪算法在六足机器人平台上的应用,设计了自适应跟踪算法实现六足机器人对运动目标的角度跟踪。将运动目标检测及跟踪算法应用于六足机器人系统。实验表明,在六足机器人移动过程中,系统可对运动目标进行精确检测与跟踪。     

基于顺序形态滤波的外运动小目标检测

针对约外图像中运动弱小目标的检测问题,本文提出了基于顺序形态滤波的小目标检测方法,并给出了具体算法。目标检测分两步进行,首先利用顺序形态滤波抑制背景,检测出候选目标的位置,并对候选目标进行区域分割,最后利用序列图像中目标运动的连续性和轨迹的一致性筛选出真正的目标,作者通过实验比较了该方法与传统高通滤波方法在抗噪声性能,背景抑制性能以及抑制虚警目标性能的差异,实验结果表明,顺序形态滤波法在这三个方面都优于高通滤波法,它能够快速、可靠检测出低信噪比的运动小目标。