Improved block matching approach to fast disparity estimation

An improved block matching approach to fast disparity estimation in machine vision applications is proposed, where the matching criterion is the sum of the absolute difference (SAD). By evaluating the lower bounds, which become increasingly tighter for the matching criteria, the method tries to successively terminate unnecessary computations of the matching criteria between the reference block in one image and the ineligible candidate blocks in another image. It also eliminates the ineligible blocks as early as possible, while ensuring the optimal disparity of each pixel. Also, the proposed method can further speed up the elimination of ineligible candidate blocks by efficiently using the continuous constraint of disparity to predict the initial disparity of each pixel. The performance of the new algorithm is evaluated by carrying out a theoretical analysis, and by comparing its performance with the disparity estimation method based on the standard block matching. Simulated results demonstrate that the proposed algorithm achieves a computational cost reduction of over 50.5% in comparision with the standard block matching method.     

Directionality based fast fractional pel motion estimation for H.264

Motion estimation is an important and intensive task in video coding applications. Since the complex-ity of integer pixel search has been greatly reduced by the numerous fast ME algorithm, the computation overhead required by fractional pixel ME has become relatively significant. To reduce the complexity of the fractional pixel ME algorithm, a directionality-based fractional pixel ME algorithm is proposed. The proposed algorithm efficiently explores the neighborhood positions which with high probability to be the best matching around the minimum one and skips over other unlikely ones. Thus, the proposed algorithm can complete the search by examining only 3 points on appropriate condition instead of 17 search points in the search algorithm of reference software. The simulation results show that the proposed algorithm successfully optimizes the fractional-pixel motion search on both half and quarter-pixel accuracy and improves the processing speed with low PSNR penalty.     

基于HEVC的亚像素运动估计快速算法

利用在亚像素搜索区域内误差匹配函数以单峰曲面分布的特点,提出了一种改进的亚像素的快速搜索算法。根据整像素搜索的结果建立5点的误差曲面模型,估计1/2像素最佳点的位置,并确定1/2像素点搜索范围和搜索模板;再根据1/2像素搜索结果确定1/4像素点的搜索方式,完成亚像素搜索。实验表明,算法在峰值信噪比平均下降0.043 dB的条件下,减少了亚像素搜索部分近60%的计算量,在保证重建图像的主观质量和客观质量的同时,提高了编码效率。     

Fast M-fold matching pursuit algorithm for image approximation

A simple and effective greedy algorithm for image approximation is proposed. Based on the matching pursuit approach, it is characterized by a reduced computational complexity benefiting from two major modifications. First, it iteratively finds an approximation by selecting M atoms instead of one at a time. Second, the inner product computations are confined within only a fraction of dictionary atoms at each iteration. The modifications are implemented very efficiently due to the spatial incoherence of the dictionary. Experimental results show that compared with full search matching pursuit, the proposed algorithm achieves a speed-up gain of 14.4∼36.7 times while maintaining the approximation quality.     

序列图像的运动补偿编码技术

本文系统地研究了运动补偿编码技术的基本原理和运动矢量检测的基本方法,包括像素递归法、块匹配法和块递归匹配法。     

一种基于正交矩的立体匹配方法

通过引入Tchebichef离散正交矩提出了一种新的基于双目立体匹配的方法，该方法利用了Tchebichef离散正交矩在图像空间中的正交性来描述图像的灰度分布特征，然后根据该分布特征对图像对进逐行逐像素匹配，视差计算通过逆变换或者通过比较重建图像的灰度值进行估计，从而得到视差图。给出了利用正交矩处理图像对的重建结果和立体匹配结果。试验结果表明，该方法是可行和有效的。     

基于FFT的海底地形二维匹配技术

海底地图匹配技术是水下地形辅助导航的核心技术之一,它主要用来提高水下载体(AUV3的定位精度,提出了基于付立叶变换的海底地形二维匹配算法(FFT算法),通过FFT变换将频域中幅值引入匹配,设计了位置匹配圆板进行实时图位置匹配与方向搜索模板进行方向搜索.应用实际海图原始数据进行仿真,结果表明,该算法能够同时匹配出位置信息和方向信息,具有较高的匹配精度和抗差特性.     

A rough set approach to feature selection based on scatter search metaheuristic

Rough set theory is an effective method to feature selection, which has recently fascinated many researchers. The essence of rough set approach to feature selection is to find a subset of the original features. It is, however, an NP-hard problem finding a minimal subset of the features, and it is necessary to investigate effective and efficient heuristic algorithms. This paper presents a novel rough set approach to feature selection based on scatter search metaheuristic. The proposed method, called scatter search rough set attribute reduction （SSAR）, is illustrated by 13 well known datasets from UCI machine learning repository. The proposed heuristic strategy is compared with typical attribute reduction methods including genetic algorithm, ant colony, simulated annealing, and Tabu search. Computational results demonstrate that our algorithm can provide efficient solution to find a minimal subset of the features and show promising and competitive performance on the considered datasets.     

基于多参量模型的全局运动估计算法

提出了一种基于特征点匹配的视频序列多参量运动估计算法,即将初始特征点域,进行梯度方向上的极坐标变换,并依据正交特征,作方向轴上的一维投影,构建出新的特征曲线,从而将孤立的特征点匹配转化成特征曲线相关.依据曲线的相关性,完成特征点对的匹配,最后使用最小二乘解算平移、旋转、缩放等变换参量.实验结果表明:算法的特征点误匹配率<5%,缩放误差<0.1%,平移误差<0.1像素;各参量估计范围:缩放因子s:0.7130°,平移参量|d|>35.算法在保证了高精度的同时,具有更为宽松的使用条件及适用性.     

基于非局部分类处理的SAR图像降斑

针对合成孔径雷达(synthetic aperture radar, SAR)图像不同内容间的统计特性差距较大以及采用非局部降斑方法处理SAR图像时会产生图像细节丢失及伪影等现象,提出了一种基于非局部分类处理的SAR图像降斑方法。首先对相似块方差系数的均值采用阈值比较的方法将图像分为同质区和异质区,在寻找目标块对应的相似块时,根据图像块中心像素点所属的类别选择合适的参数进行块匹配,并在获得相似块后分别使用加权平均的方法处理同质区目标块和3D变换域硬阈值收缩方法处理异质区目标块。该方法不仅能在块匹配过程中选择不同的块尺寸和搜索范围以提高块匹配的精度,而且使用不同方法处理同质区和异质区时能够在图像降斑与细节保持的权衡中达到更好的平衡。实验结果表明,该方法充分利用同质区和异质区的特点,结合不同的方法进行分类处理可有效提高图像降斑性能,在SAR图像降斑性能指标和视觉效果方面均达到了较高水平。     

强化结构的数字壁画病害修复算法研究

针对北京地区法海寺壁画块状缺失,且缺失区域结构信息丰富的特点,提出了一种强化结构的数字图像修复算法,解决了Criminisi算法修复时对图像结构信息考虑不足的问题。首先在计算填充块的优先权函数时,将线性卷积的曲率计算融入数据项中,同时增加结构信息的权重,实现了优先修复结构信息丰富区域的目的;其次在搜索匹配块的相似度计算中引入区域协方差方法,确保修复后图像结构的一致性,减少了匹配错误率。实验结果表明：该算法较好地解决了结构性较强的壁画块状信息缺失填充错位问题。     

基于相邻像素统计特性的LSB隐写分析技术

基于对图像相邻像素灰度值的奇偶性及其大小关系的统计分析,提出了一种新的可靠检测空域LSB隐写的隐写分析算法。该算法通过统计相邻像素对中奇像素大于偶像素的相邻像素对数与偶像素大于奇像素的相邻像素对数,然后根据其比值来判断图像中隐秘信息的有无,并从理论上给予了证明。这一算法不仅可以实现对空域LSB隐写的可靠检测,还可以准确估计图像中隐密信息数据量的大小。算法实现简单、计算量小、检测速度快。实验结果表明,该方法可以获得优于GPC等隐写分析方法的检测性能,且适用于彩色图像。     

一种融合运动和立体的视差与运动估计算法

本文提出融合运动和立体的视差与运动估计算法。算法首先通过计算瞬时ＦＯＥ，实现对每个像素处位移的ＭＡＰ估计，计算关联置信度测量，然后利用位移估计从两图像序列之一计算相对深度图并导出能用于匹配两立体对图像序列的视差先验概率分布，使立体对的两图像序列匹配，确定３－Ｄ景物深度。算法可独立估计每个像素处的视差，不需关联的平滑假设。     

基于自适应非局部均值的SAR图像相干斑抑制

针对在利用非局部均值方法对合成孔径雷达(synthetic aperture radar, SAR)图像降斑时,存在的图像块相似性度量不准确、鲁棒性不高等问题,提出了一种基于自适应非局部均值的SAR图像相干斑抑制方法。首先,定义平滑度以刻画图像不同区域的纹理复杂程度,并设计自适应匹配函数,自适应地确定图像块和搜索窗口的大小,以提高块相似性度量的准确性,并在此基础上提出了自适应非局部均值算法框架。然后,利用Gabor滤波器对图像块的相似性进行度量,以增强块相似性度量的鲁棒性,并以所提框架为依据,设计了基于Gabor滤波器的自适应非局部均值算法。实验结果表明,所提算法不仅能够有效去除相干斑噪声,而且较好地保持了图像的纹理、边缘、点目标等信息,为后期SAR图像的理解与解译奠定了良好的基础。     

基于最大梯度和灰度相关的两步全景图拼接算法

提出一种基于最大梯度和灰度相关的两步全景图拼接算法。该算法综合了基于灰度相关和特征相关算法的优点，首先通过匹配梯度最大值点位置的梯度值缩小搜索范围，再利用最大灰度相关匹配两幅待拼接图像。实验表明，算法原理简单、拼接速度快，同时消除了对有重复纹理特征图像的伪拼接现象，对图像亮度差异具有很强的抗干扰能力，鲁棒性好。     

基于遗传算法的轮廓模糊匹配问题研究

在由序列的二维轮廓线重构出面模型来表示三维形体的面绘制方式中,首先要解决相邻两层切片上的轮廓线之间的匹配连接关系。针对目前的轮廓线匹配算法容易导致错误匹配的问题,提出一种基于遗传算法的轮廓模糊匹配算法。模糊性为轮廓匹配问题本身所具有,借鉴遗传算法这一种全局优化自适应概率搜索算法,可以准确表达轮廓匹配中的约束,有效地减少错误匹配的发生。在肝脏的CT数据三维重建中应用该算法取得了比较理想的效果。     

Integration of spatial attractions between and within pixels for sub-pixel mapping

As a promising technique to enhance the spatial resolution of remote sensing imagery,sub-pixel mapping is processed based on the spatial dependence theory with the assumption that the land cover is spatially dependent both within pixels and between them.The spatial attraction is used as a tool to describe the dependence.First,the spatial attractions between pixels,subpixel/pixel spatial attraction model (SPSAM),are described by the modified SPSAM (MSPSAM) that estimates the attractions according to the distribution of sub-pixels within neighboring pixels.Then a mixed spatial attraction model (MSAM) for sub-pixel mapping is proposed that integrates the spatial attractions both within pixels and between them.According to the expression of the MSAM maximumising the spatial attraction,the genetic algorithm is employed to search the optimum solution and generate the sub-pixel mapping results.Experiments show that compared with SPSAM,MSPSAM and pixel swapping algorithm modified by initialization from SPSAM (MPS),MSAM can provide higher accuracy and more rational sub-pixel mapping results.     

Learning Bayesian networks using genetic algorithm

A new method to evaluate the fitness of the Bayesian networks according to the observed data is provided. The main advantage of this criterion is that it is suitable for both the complete and incomplete cases while the others not. Moreover it facilitates the computation greatly. In order to reduce the search space, the notation of equivalent class proposed by David Chickering is adopted. Instead of using the method directly, the novel criterion, variable ordering, and equivalent class are combined,moreover the proposed mthod avoids some problems caused by the previous one. Later, the genetic algorithm which allows global convergence, lack in the most of the methods searching for Bayesian network is applied to search for a good model in this space. To speed up the convergence, the genetic algorithm is combined with the greedy algorithm. Finally, the simulation shows the validity of the proposed approach.     

无人机视觉着舰导航鲁棒角点精确检测算法

针对舰载无人直升机着舰时拍摄的图像存在大尺度、角度畸变,使得合作目标角点难以检测的问题,提出一种鲁棒角点精确检测算法。设计了一种彩色非对称合作目标,通过计算合作目标的最小周长多边形（minimum perimeter polygon,MPP）来获取轮廓上的角点。针对这些角点存在伪角点及未排序问题,给出了斜率约束、距离约束和方向约束策略。最后,针对亚像素Harris角点检测算法精度高但未排序、三重约束的MPP角点检测精度低但已排序的问题,制定了这两种角点检测方法的融合策略。实验表明,所提算法可以有效解决合作目标图像发生大角度畸变以及一定尺度畸变范围内的角点检测。     

多状态网络系统d-最小割集的边合并算法

为更有效的获取多状态网络系统d-最小割集（d-mincuts，d-MCs），提出一种边合并算法。算法用容量未取最大容量的边及对应取值组成的集合对表示网络状态，基于网络分割的思想，不以最小割集为基础，通过边合并、状态继承求取可行解，通过集合对的比较得到d-MCs。同时提出一个引理，更高效的求取容量下界，缩小状态空间。算法复杂度对比分析证明算法有效，且通过定义带权值的广义联络矩阵实现算法，便于编程计算。最后，通过实例分析验证了算法的有效性。