基于双视线特征感知编组的多目标跟踪方法

为实现精准的图像多目标捕获与跟踪,提出基于双视线特征感知编组的多目标跟踪方法.利用自由形状线特征涵盖的丰富信息,使用双视线特征感知编组方法将线特征匹配结果当作计算条件,推算已匹配的每对线特征左右视差均值,将方位相近、左右视差均值接近的线特征视作一组,明确各组线特征作用窗口,代人时差收敛均值,实现多目标特征匹配;代入联合概率数据关联算法,构建改进粒子滤波模型,让粒子权值呈现出测量值与目标轨迹的关联概率,确保各目标跟踪轨迹持续性,并完善轨迹初始点与终点,增强跟踪时效性.仿真结果表明,所提方法能很好地处理车辆交叉引发的错误匹配问题,在交叉或遮挡等复杂情况下,依旧可以快速准确地同时对多个目标车辆进行跟踪.     

基于序列影像的城市三维建模

提出了一种从序列图像建立城市三维模型的算法框架。该方法使用三条序列影像和匹配生成的数字表面模型，结合几何约束的多视特征匹配，从图像获取三维点、线信息。同时讨论了基于感知编组的几何模型生成算法，以及纹理优选与自动映射。实验结果证明该方法是有效的。     

面向组特征的航空影像直线匹配方法

针对直线匹配结果存在"一对多""多对一""多对多"的问题,提出一种基于组特征的航空影像直线匹配方法。该方法在直线提取结果的基础上,首先通过区域和角度双重约束对左、右影像上提取的直线分别进行编组,然后采用核线约束、单应矩阵约束、相似性约束对组直线特征进行匹配及分裂,最终确定同名直线。采用某城区的数字航空影像进行直线匹配实验,取得可靠的匹配结果,验证该方法的有效性及可行性。     

基于感知编组的高层建筑物立面提取方法

将感知编组理论引入到遥感影像上高层建筑物立面的提取中,依据感知编组的邻近性、连接性和封闭性等规则,提出了一种基于感知编组的遥感影像上高层建筑物立面的提取算法,该算法包括边缘提取、边缘数据分块、块内感知编组提取建筑物立面、建筑物立面提取结果融合等步骤.实验验证了该方法的有效性.     

直线对几何特征约束的近景影像特征匹配

针对直线匹配过程中线特征提取不完整以及缺乏考虑邻近直线相关性,提出一种直线对几何特征约束的近景影像特征匹配方法:首先,利用直线检测算法(line segment detector,LSD)对参考影像和搜索影像进行直线提取,并对提取的直线进行特征编组获得特征直线对;然后,将特征直线对作为匹配基元,依次运用双重核线约束、仿射变换约束、最优相似性原则确定同名直线对;最后,根据同名直线对中2条直线端点与其邻域内同名点的距离关系拆分同名直线对,利用仿射变换约束整合拆分过程中对应不一致的单直线,得到最终匹配的同名单直线。为了验证该算法的有效性与可靠性,选取4组人工建筑物特征变换近景影像进行实验,验证了该算法在直线匹配过程中具有一定的稳健性和普适性。     

仿真图像作为模板的遥感影像小目标检测方法

随着传感器技术和航空遥感技术的不断进步,遥感影像的质量和数量也得到了极大的提高,而遥感影像中的目标检测是理解和分析遥感影像所面临的一个基本问题。针对神经网络在遥感影像小目标检测任务中难以提取足够多的有效特征、遥感小目标易受云雾遮挡等问题,提出了一种基于仿真图像模板匹配的方法,通过特征融合的方式成功地将该方法应用于遥感影像小目标检测任务。成像仿真技术生成的仿真图像包含了更多的遥感小目标特征,如几何形状、材质等。在与深度学习结合之后,更多的特征可以提升神经网络检测遥感影像小目标的准确率。实验结果表明将基于仿真图像的模板匹配方法应用于深度学习之后,对于遥感影像小目标检测取得了较好的效果,尤其是针对受到云雾等天气干扰的小目标。     

多重约束下的近景影像线特征匹配方法

目的 针对影像匹配时提取特征线断裂而影响匹配结果及可靠性的问题,提出多重约束条件下的近景影像线特征匹配方法。方法 首先,采用SIFT算法获取同名点,并使用RANSAC算法进行优化,通过同名点计算仿射变换矩阵;建立格网点,利用仿射变换、Harris兴趣值及最小二乘法提高密集匹配结果的精度;其次,采取Freeman链码优先级算法提取直线,根据搜索区域内密集匹配点与直线位置关系完成特征线的初始匹配;最后通过线段重合度对初始匹配结果进行优化,并利用核线约束确定同名直线端点。结果 选取存在旋转、尺度、遮挡的近景影像进行线特征匹配实验,结果表明,与其他直线匹配方法相比,本文方法不仅在直线匹配成功数目上约为经典算法的1.07~4.1倍,而且直线匹配正确率也提升0.6%~53.3%,具有较好的准确性和鲁棒性。结论 通过多重约束有效地减小了立体影像中线特征匹配时的搜索范围,提高了直线匹配速率,且该方法适用于不同类型几何变化下的近景影像数据,并能较好地改善直线断裂及遮挡问题。     

仿射变换下基于凸包和多尺度积分特征的形状匹配方法

针对在仿射变换下的形状匹配问题,提出基于凸包的特征点提取方法、基于各向异性高斯核的多尺度积分特征和基于两者的匹配方法.首先提取形状的凸包,根据最大面积原则对凸包相邻顶点之间的曲线进行演化,获取的点和凸包顶点形成仿射不变的特征点;其次对特征点按顺序编组,根据特征点之间的仿射变换关系构造多尺度积分特征向量;最后使用动态规划算法计算形状之间的相似度.实验结果表明,该方法对局部形变和噪声敏感度小,并适用于复杂形状的匹配.此外,特征点提取方法和多尺度积分特征也可与其他方法结合进行形状分析.     

基于空间约束的正则化流形学习影像匹配方法

针对大数据量的影像匹配问题,提出了一种基于正则化流形学习的影像匹配方法。该方法利用曼哈顿距离方法计算特征点SIFT描述符的相似性,并在此基础上增加同一幅影像中特征点之间的空间结构关系作为正则化项,采用流形学习方法将两幅影像中的特征点共同映射到同一流形空间;根据最小距离方法进行特征点的匹配。通过选取四种不同来源的影像对进行实验,与SVD-SIFT方法、LE-SIFT方法进行综合分析,结果表明该方法在匹配性能上优于现有方法,而且该方法具有线性复杂度,适用于处理特征点数量较大的影像匹配。     

自由特征模型参数化研究

为了更高效直观地对自由特征形状进行建模,对自由特征形体及自由特征定义点进行参数化,提出了一种通过封装参数和约束创建自由特征体特征的方法。在自由特征形状的定义中,建立数值参数和最终特征形状几何属性的映射关系。在轨迹线上提取特征定义点,在各点处建立横截面,对横截面进行蒙皮和扫掠运算,生成和基曲面无缝连接的自由形状体特征。     

基于感性意象的高速列车座椅设计及美学规律研究

针对现有高速列车座椅普遍存在设计同质化、体验感不良等问题,将高速列车座 椅美学规律研究与感性意象方法相结合,探讨高速列车二等座椅的设计研究方法及应用路径, 为设计实践及行业发展提供借鉴与指导。通过对高速列车座椅典型样本和感性意象词汇的搜集 与筛选,结合语义差异法和拉依达准则构建得出感性意象数据库;然后将其导入 SPSS 软件进 行主成分分析,依据成分矩阵和样本评价散点图提取主成分中载荷较大意象词汇及对应的代表 样本,并进一步明确意象词汇在代表样本中的高匹配度区域,得出设计要素及优先级顺序;最 后进行实践设计及可行性评估,并将研究过程中所适用的主要美学规律进行阐述。研究结果赋 予高速列车领域美学规律研究更为科学的方法路径,同时也拓展了感性意象研究新的应用空间, 为设计出更加迎合乘客感性意象的高速列车座椅提供了有效的借鉴方法及操作路径。     

Automatic layout of 2D free-form shapes based on geometric similarity feature searching and fuzzy matching

Two-dimensional (2D) irregular layout is widely applied in various manufacturing processes, such as sheet metal cutting, shipbuilding, and electronic component placement. An efficient layout algorithm can effectively improve the material utilization, thereby reducing manufacturing cost. But the free-form shape layout problem is very challenge as it is difficult to exactly represent a free-form shape. There is not an efficient method currently available for the 2D free-form shape layout. This paper proposes a method based on the geometric similarity feature searching and fuzzy matching for the 2D free-form shape layout. The freeman chain code is developed to describe the contour information of shapes and forward-lines to form the basis of the layout strategy. A strategy based on fuzzy matching is proposed for the layout, which includes searching geometric similarity features using the longest common subsequence and the proposed placement algorithm to complete the collision. Three computational experiments are conducted to analyze the performance of the proposed method. Experimental results show that the proposed method is feasible and effective with the good applicability to achieve a high filling rate in reduced time.     

轮廓组织研究进展

轮廓提取是图像信息处理、机器视觉等领域中的经典难题之一。轮廓组织,即基于感知组织的轮廓提取技术为解决这一经典难题注入了新的活力。从轮廓提取与感知组织之间结合点出发,按照时间顺序对轮廓组织的研究现状进行比较,全面总结并分析现有方法的特点和不足,最后指出了进一步研究的发展方向。     

基于曲率特征的自由曲面匹配算法

针对无任何预知联系下的自由曲面匹配问题,提出了一种简捷、快速的匹配方法.该方法以曲面的曲率为联系特征,在测量数据与模型曲面之间建立起满足角度、距离约束的对应关系,利用三点旋转平移变换法生成旋转平移变换列表;然后通过最小距离目标函数选取正确的三维坐标变换,实现测量数据与模型曲面之间的准确匹配.实验结果表明:该方法简捷、可靠且容易实现,特别适用于工件的测量定位和多视数据的融合.     

Stereo using monocular cues within the tensor voting framework

We address the fundamental problem of matching in two static images. The remaining challenges are related to occlusion and lack of texture. Our approach addresses these difficulties within a perceptual organization framework, considering both binocular and monocular cues. Initially, matching candidates for all pixels are generated by a combination of matching techniques. The matching candidates are then embedded in disparity space, where perceptual organization takes place in 3D neighborhoods and, thus, does not suffer from problems associated with scanline or image neighborhoods. The assumption is that correct matches produce salient, coherent surfaces, while wrong ones do not. Matching candidates that are consistent with the surfaces are kept and grouped into smooth layers. Thus, we achieve surface segmentation based on geometric and not photometric properties. Surface overextensions, which are due to occlusion, can be corrected by removing matches whose projections are not consistent in color with their neighbors of the same surface in both images. Finally, the projections of the refined surfaces on both images are used to obtain disparity hypotheses for unmatched pixels. The final disparities are selected after a second tensor voting stage, during which information is propagated from more reliable pixels to less reliable ones. We present results on widely used benchmark stereo pairs.     

Optimal shape error analysis of the matching image for a free-form surface

When using an optical non-contact scanning system to measure an object that has a large surface, large curvature, or a full 360° profile, one can acquire only one set of sectional measurement points each time. For reconstructing the entire object, every set of sectional measurement points acquired at different positions must match. Therefore, the optimal shape error analysis for the matching image of two or more sets of sectional measurement points is desired. This paper presents a measurement system that combines two CCD cameras, one line laser and a three-axis motion stage. It forms an optical non-contact scanning system in association with the mathematical method of direct shape error analysis for the use in reverse engineering. This analysis and measurement system can be used for the profile measurements of free-form objects. It analyzes the matching image of a free-form surface with high efficiency and accuracy. The validity and applicability of this system are demonstrated by two practical examples.     

The Earth Mover's Distance as a Metric for Image Retrieval

We investigate the properties of a metric between two distributions, the Earth Mover's Distance (EMD), for content-based image retrieval. The EMD is based on the minimal cost that must be paid to transform one distribution into the other, in a precise sense, and was first proposed for certain vision problems by Peleg, Werman, and Rom. For image retrieval, we combine this idea with a representation scheme for distributions that is based on vector quantization. This combination leads to an image comparison framework that often accounts for perceptual similarity better than other previously proposed methods. The EMD is based on a solution to the transportation problem from linear optimization, for which efficient algorithms are available, and also allows naturally for partial matching. It is more robust than histogram matching techniques, in that it can operate on variable-length representations of the distributions that avoid quantization and other binning problems typical of histograms. When used to compare distributions with the same overall mass, the EMD is a true metric. In this paper we focus on applications to color and texture, and we compare the retrieval performance of the EMD with that of other distances.