一种立体景象匹配技术及其应用

景象匹配是航天武器精确制导的一种重要方法,大多采用二维图像进行匹配,其效率较低。文中提出一种立体景象匹配技术及相应的算法,在实验中得到了应用。主要做法是将三维图像离散成二维图像序列,而后与基准图进行比较。分析证明,大大提高了精度和效率。为此,文中还涉及了相应算法,易于编码和应用。应用表明,该算法的实时性和适应性较好,匹配时间能达到0．14s,正确匹配率达到92．5％。有待研究的图像立体匹配方法很多,诸如多基准图对离散化的系列实时图进行匹配,以及定义、构造立体图像的数学模型并进行匹配等。     

一种立体景象匹配技术及其应用

景象匹配是航天武器精确制导的一种重要方法,大多采用二维图像进行匹配,其效率较低。文中提出一种立体景象匹配技术及相应的算法,在实验中得到了应用。主要做法是将三维图像离散成二维图像序列,而后与基准图进行比较。分析证明,大大提高了精度和效率。为此,文中还涉及了相应算法,易于编码和应用。应用表明,该算法的实时性和适应性较好,匹配时间能达到0．14s,正确匹配率达到92．5％。有待研究的图像立体匹配方法很多,诸如多基准图对离散化的系列实时图进行匹配,以及定义、构造立体图像的数学模型并进行匹配等。     

用于行人头部特征提取的目标区域匹配方法

为了准确地定位与跟踪序列图像中的运动行人以获取精确的客流量信息,提出了一种基于目标区域匹配的行人头部特征提取新方法。与常用的基于致密视差图的头部区域视差获取方法不同,该方法基于“先分割后匹配”的思想,即首先借助单目图像处理方法对基准图进行分割,获取候选头部区域;然后直接将这些候选头部区域作为目标区域,在匹配图中搜索其匹配对应区域以获取候选头部区域的视差;再借助候选头部区域的视差提取出候选头部区域的深度与透视特征,用于去除虚假头部区域以获取最终的头部检测结果。性能测试与实验结果表明,该方法不仅视差提取精度高、实时性好,并且借助该方法获取的头部特征具有较高的区分度,可以有效去除候选头部区域中的虚假头部区域,使客流量检测的准确率达到90%以上。     

基于相关系数符号的快速匹配算法*

针对经典灰度相关匹配算法耗时多的缺点,提出一种减少计算次数、提高匹配效率的新方法.该方法是先构造一幅相关图像,然后计算它与基准子图像的互相关数据并利用其符号分离候选匹配点,最后在匹配过程中,根据实时图像与相关图像的相关系数符号来选定匹配点区域,从而减少匹配计算次数,提高匹配速度.理论分析和实验表明,该方法不但能够保持经典灰度相关匹配算法具有较高的匹配精度和较强的抗噪能力的特点,而且大大缩短了匹配时间,使得经典灰度相关算法能够在实际中得以应用.     

复杂地面目标前视红外景象匹配算法*

针对复杂地面目标前视红外图像边缘模糊、背景杂乱无章,无直接可用的同源基准图的情况,研究了一种灰度与形状特征相结合的由粗到精景象匹配算法。在粗匹配阶段,将积分图像引入归一化积相关算法中,并对其计算公式进行了近似,使运算速度大大加快;精匹配阶段,利用实时图与所制备基准图形状相似的特点,采用形状上下文进行匹配。实验结果显示,该算法匹配精度高、速度快,对于复杂地面目标前视红外图像的匹配识别具有一定的应用价值。     

张量分析在视差图生成中的应用

针对当前视差图生成算法中常用的匹配代价对光晕等复杂光学畸变比较敏感的问题,在对相机成像模型进行分析的基础上提出了一种基于张量分析的匹配代价。和目前常用的匹配代价相比,该匹配代价不但对光晕效应具有更强的鲁棒性而且能够更加准确的反映图像的局部结构信息,有效的降低了匹配的歧义性。在本文中,张量在积分图像上构造,张量间的距离在黎曼流形上测量;此外,提出了一种简单有效的视差图后续处理方法进一步修正了初始视差图中的不可信视差。在标准测试集和人工图像上的实验结果验证了该方法的有效性。     

影像匹配定位中的直线倾角直方图不变矩法

针对现有的基于图像直方图不变矩的匹配方法大多不能适应图像存在较大旋转变换的问题,提出直线倾角直方图不变矩的概念,并将其应用到影像的匹配与定位中.该方法采用直线段拟合表示图像边缘,利用直线倾角在基准图与待匹配图上的一致性进行影像匹配.实验结果证明,倾角直方图不变矩可以作为影像特征的描述形式,利用其进行影像匹配与定位是可行的.     

基于图分割与Hausdorff距离的多分辨率影像匹配

针对具有复杂场景的航拍图像提出了一种基于图分割理论与Hausdorff距离的多分辨率影像匹配方法。在高斯金字塔图像模型中,低分辨率的图像通过图分割方法,充分考虑图像中的局部和全局的信息,提取到稳定和完整的图像区域边界,并以区域边界作为待匹配的曲线。再通过计算曲线的统计特性作为图像间待匹配特征,并由信号相关的度量方法粗估计出图像间全局仿射变换参数。利用粗估计的参数在高分辨率层次上进一步通过基于Hausdorff距离的匹配方法搜索到精确的变换参数。实验结果表明,该方法在较大变形和强噪音干扰的情况下对复杂场景的图像也能有效地完成匹配。     

一种基于DCT系数分布特性的块匹配准则

视频编码通过运动估计消除时间冗余信息，块匹配方法是目前所有视频编码标准采用的运动估计方法。根据运动估计的残差图像的DCT变换后交流系数的统计分布规律，推导出了一种块匹配运动估计的匹配准则．这种匹配准则在对有亮度变化的帧进行运动估计时特别有效．实验结果表明该匹配准则可以取得比SAD匹配准则更好的效果．     

一种结合互信息和模板匹配的配准方法

传统的互信息法直接对大图进行互信息配准,容易出现局部极值并产生误匹配现象,针对该问题,提出一种将互信息与模板匹配相结合的配准方法,采用互信息为相似度准则进行图像的模板匹配,得到候选的匹配子图,通过待配准大图其余部分与模板和子图的空间关系,得到配准后的大图,分别计算按照各个候选子图配准情况下的待配准图的互信息,得到最大的互信息所对应的子图,确定最终的配准结果。实验结果表明,该方法在对灰度差较大的图像进行配准时,能够获得良好的效果。     

Ranking with uncertain labels and its applications

The techniques for image analysis and classification generally consider the image sample labels fixed and without uncertainties. The rank regression problem studied in this paper is based on the training samples with uncertain labels, which often is the case for the manual estimated image labels. A core ranking model is designed first as the bilinear fusing of multiple candidate kernels. Then, the parameters for feature selection and kernel selection are learned simultaneously by maximum a posteriori for given samples and uncertain labels. The provable convergency Expectation Maximization (EM) method is used for inferring these parameters in an iterative manner. The effectiveness of the proposed algorithm is finally validated by the extensive experiments on age ranking task and human tracking task. The popular FG-NET and the large scale Yamaha aging database are used for the age estimation experiments, and our algorithm outperforms those state-of-the-art algorithms ever reported by other interrelated literatures significantly. The experiment result of human tracking task also validates its advantage over conventional linear regression algorithm. A short version of this paper appeared in ICME07.     

面向惯性约束聚变实验靶图像的快速椭圆检测

目的：针对惯性约束核聚变实验中靶图像轮廓模糊、亮度不均匀等问题,并从提高图像处理实时性角度出发,提出了一种高可靠性和高精度的快速椭圆检测方法。方法：首先利用椭圆边缘点在它与圆心相连方向上具有较大灰度变化率这一特点,以预估中心点为极点建立极坐标系,通过从极点出发的射线上灰度变化率极值点搜索实现椭圆边缘点检测,极值点搜索在图像局部范围进行保证边缘点检测的有效性和实时性;其次利用基于RANSAC的自适应椭圆参数提取算法得到最终椭圆参数,该方法利用椭圆参数空间聚类分析选取最优椭圆参数,从而实现了一致样本集的自适应选择,保证了椭圆参数拟合精度的同时提高了算法的适应性和鲁棒性。结果：采用本文算法检测一幅图像的平均时间约为110ms,与常用椭圆检测方法相比检测速度有显著提高。结论：对比实验表明,本文提出的椭圆检测方法与其他方法相比具有更高的精度、更快的实时性和更强的鲁棒性。     

A new gravitational image edge detection method using edge explorer agents

In this paper, a new algorithm for image edge detection based on the theory of universal gravity is proposed. The problem is represented by a discrete space in which each image pixel is considered as a celestial body and its mass is considered to be corresponding to the pixel’s grayscale intensity. To find the edgy pixels a number of moving agents are randomly generated and initialized through the image space. Artificial agents move through the space via the forces of celestial bodies that are located in their neighborhood and in this way they can find the promising edge pixels. A large number of experiments are employed to determine suitable algorithm parameters and confirm the legitimacy of the proposed algorithm. Also, the results are compared with conventional and soft computing based methods like Sobel, Canny and ant-based edge detector. As compared to other standard techniques, our algorithm provides more accurate results over 11 test images via Baddeley’s error metric. The visual and quantitative comparisons reveal the effectiveness and robustness of the proposed algorithm.     

基于图像变形技术的平行坐标可视化

针对传统的平行坐标可视化方法不适于处理大量高维数据等不足,将基于控制点的图像变形技术引入到可视化中,首先利用学习集中的数据建立控制点到目标点的变形函数,求出方程的参数,再将测试集中的数据通过变形函数映射到平行坐标系中,实验结果表明,通过图像变形原理能较好地实现高维数据的分类和可视化效果,优于传统的平行坐标方法。     

Edge detection using ant algorithms

In this paper a new algorithm for edge detection using ant colony search is proposed. The problem is represented by a directed graph in which nodes are the pixels of an image. To adapt the problem, some modifications on original ant colony search algorithm (ACSA) are applied. A large number of experiments are employed to determine suitable algorithm parameters. We drive an experimental relationship between the size of the image to be analyzed and algorithm parameters. Several experiments are made and the results suggest the effectiveness of the proposed algorithm.     

Medical image registration based on self-adapting pulse-coupled neural networks and mutual information

Medical image registration plays a dominant role in medical image analysis and clinical research. In this paper, we present a new coarse-to-fine method based on pulse-coupled neural networks (PCNNs) and mutual information (MI). In the coarse-registration process, we use the PCNN-clusters’ invariant characteristics of translation, rotation and distortion to get the coarse parameters. And the parameters of the PCNN model are optimized by ant colony optimization algorithm. In the fine-registration process, the coarse parameters provide a near-optimal initial solution. Based on this, the fine-tuning process is implemented by mutual information using the particle swarm optimization algorithm to search the optimal parameters. For the purpose of proving the proposed method can deal with medical image registration automatically, the experiments are carried out on MR and CT images. The comparative experiments on MI-based and SIFT-based methods for medical image registration show that the proposed method achieves higher performance in accuracy.     

A robust projection plane selection strategy for UAV image stitching

Unmanned Aerial Vehicles (UAVs) are the most popular way to collect ground data today, thanks to their low cost and matchless convenience. However, UAVs are prone to unstable flight poses because they are so light in weight, which has resulted in a new challenge for UAV image stitching. In this paper, we propose a robust approach to stitch UAV images captured from approximately planar scenes without pose parameters assistance. The key idea of the proposed framework lies in an effective projection plane selection strategy, which is capable of resisting the perspective distortion from existing pose-perturbed images. To select a reasonable reference image as the projection plane, we first divide all the images into two groups (stable group and unstable group) according to their registration error under the affine model. Then, a specifically designed approach is used to define a weighted topological graph, which guarantees that the reference image is selected from the stable group while maintaining a global minimum accumulated registration error. Based on our cost topological graph, each unstable group image is locally attached to a stable group image via a homography. Finally, alignment parameters of all the stable group images are solved using affine model, after which global optimization is performed on the model of both groups. Comparing our results to those of the conventional approaches indicates that our proposed approach produced superior results in several challenging experiments involving both qualitative and quantitative evaluation.     

复杂背景运动模糊图像的盲复原算法研究

为了有效恢复具有复杂背景的运动模糊图像，提出一种基于正则化策略和共轭梯度优化迭代复原算法；同时为了辨识运动模糊图像的参数，又提出一种基于模糊图像做分自相关函数的点扩展函数辨识算法。为验证算法的有效性，在微机上对提出的算法与现有算法进行了对比实验，结果表明十分有效，也具有较强的鲁棒性。     

基于量子行为粒子群优化算法的图像插值方法

传统图像插值方法简单,容易实现,但经过插值后的图像会增加一定的虚假内容，导致图像模糊。为提高插值图像的质量和图像的分辨率，提出一种基于量子行为粒子群优化（QPSO）算法的图像插值方法。该方法利用QPSO算法在以传统插值图像为基础形成的解空间中，寻找符合目标函数的最优高分辨率图像。实验证明，该方法实用、可行，且能得到质量较好的插值图像。     

一种基于遗传算法的图像配准算法研究

针对图像位置配准问题,提出了一种基于遗传算法的图像配准算法。选择合适的相似性参数来表征两图像的配准参数,引用遗传算法实现对相似性参数的优化,通过对比实验得到的种群大小、遗传代数和运算时间,最终用MATLAB编写程序对本算法进行实验。实验结果表明该算法相对传统算法具有较好的收敛性和运算速度,同时也具有较好的精确度和实用性。