多种角度比较SIFT、SURF、BRISK、ORB、FREAK算法

SIFT、SURF、BRISK、ORB、FREAK等图像特征匹配算法具有不同的鲁棒性,本文利用Mikolajczyk和Schmid所提供的数据集,对这几种算法从匹配速度,应对图像旋转变换、模糊变换、光照变换、尺度变换、视角变换时表现出的鲁棒性等角度进行比较。本文采用的评价指标是两幅图像中成功匹配的特征点对数。经比较分析后发现,SURF和FREAK算法表现出的鲁棒性较为全面。     

位置地图情境研究

随着位置服务、位置地图的兴起,情境作为一种研究客观世界与人类之间关系的抽象工具,已被逐渐地引入到移动地图服务中来.鉴于目前情境理论在地图的应用过程中存在基本概念不清、主要研究内容不明确的问题,重点剖析了位置地图情境的内涵,并从情境建模、情境匹配、情境推理和情境表达四方面,开展了位置地图情境的相关技术研究.     

利用方向纹理特征从影像上搜索道路中心线

针对遥感影像道路中心线提取问题,提出利用方向纹理特征辅助道路中心线匹配搜索的思想,以人工给出的道路种子点和初始搜索方向为基础,运用方向纹理特征直接从遥感影像上匹配搜索道路的中心线。算法通过预测道路的宽度、弯曲等情况来自动调整纹理窗口的大小,因而能够很好地搜索到道路中心线,此外算法针对树木遮挡、车辆压盖设计了相应的处理策略。实验表明:该方法对遥感影像上不同类型道路均有很好的提取效果,且提取效率高于现有的道路提取算法。     

基于特征点的影像视差分析

本文介绍了一种基于特征点的数字立体影像匹配方法。该法采用Frstner算子提取特征点,然后应用一种松驰迭代算法,实现了同名特征点之间的立体匹配。为实现立体像对的自动相对定向和数字地形模型自动生成提供了一种切实可行的方法。     

多级SPOT立体影像匹配

立体影像匹配是自动提取SPOT影像高程信息的关键技术。本文根据SPOT影像在几何构像关系和影像质量上的特点,提出了多级匹配的结构策略。实际像对匹配实验表明,多级匹配法具有较好的可靠性和精度水平,而且运算速度快,在快速生成DEM数据辅助遥感信息分析方面,有重要的应用价值。     

A geometric-based approach for road matching on multi-scale datasets using a genetic algorithm

Object matching is used in various applications including conflation, data quality assessment, updating, and multi-scale analysis. The objective of matching is to identify objects referring to the same entity. This article aims to present an optimization-based linear object-matching approach in multi-scale, multi-source datasets. By taking into account geometric criteria, the proposed approach uses real coded genetic algorithm (RCGA) and sensitivity analysis to identify corresponding objects. Moreover, in this approach, any initial dependency on empirical parameters such as buffer distance, threshold of spatial similarity degree, and weights of criteria is eliminated and, instead, the optimal values for these parameters are calculated for each dataset. Volunteered geographical information (VGI) and authoritative data with different scales and sources were used to assess the efficiency of the proposed approach. According to the results, in addition to an efficient performance in various datasets, the proposed approach was able to appropriately identify the corresponding objects in these datasets by achieving higher F-Score.     

Tracking of facial deformations in multi-image sequences with elimination of rigid motion of the head

The paper deals with measurement of human facial deformations from synchronized image sequences taken with multiple calibrated cameras from different viewpoints. SIFT (Scale Invariant Feature Transform) keypoints are utilized as image feature points in the first place to determine spatial and temporal correspondences between images. If no temporal match is found for an image point by keypoint matching, then the tracking of the point is switched to least squares matching provided the point has one or more spatial corresponding points in the other views of the previous frame. For this purpose, a new method based on affine multi-image least squares matching is proposed where multiple spatial and temporal template images are simultaneously matched against each search image and part of the spatial template images also change during adjustment. A new method based on analyzing temporal changes in the image coordinates of the tracked points in multiple views is then presented for detecting the 3-D points which move only rigidly between consecutive frames. These points are used to eliminate the effect of rigid motion of the head and to obtain the changes in the 3-D points and in the corresponding image points due to pure deformation of the face. The methods are thoroughly tested with three multi-image sequences of four cameras including also quite large changes of facial deformations. The test results prove that the proposed affine multi-image least squares matching yields better results than another method using only fixed templates of the previous frame. The elimination of the effect of rigid motion works well and the points where the face is deforming can be correctly detected and the true deformation estimated. A method based on a novel adaptive threshold is also proposed for automated extraction and tracking of circular targets on a moving calibration object.     

基于伪语义相似度模型的中文地址匹配方法

地址匹配中,由于传统相似度模型受字符重叠数影响大,在处理简写、缩写地址要素单元时,错误匹配问题突出;深度学习方法需要大量样本支撑,但庞大的数据量和多样的形式,导致生成样本的成本过高。为解决上述问题,本文首先应用基于条件随机场和双向长短时记忆神经网络的模型,对地址进行分词;然后通过建立一种伪语义相似度,对地址要素进行分级匹配。通过对公安业务中地址数据进行测试,在对缩写、简写等不规范地址描述方面,本文模型能较理想地完成任务,各参考指标均高于0.9。     

面向规划的建筑物屋顶精细纹理快速生成方法

针对三维规划审批对精确的空间关系及逼真的三维可视化效果的综合需求,设计实现了两套针对大规模三维数字城市建筑物模型的屋顶纹理快速生成方案。方案一基于严格投影成像方程建立物方与像方对应关系,并根据视线方向、遮挡关系、成像分辨率等选取最优纹理进行映射。方案二通过建立相应的屋顶纹理库,并利用屋顶纹理智能匹配技术实现大范围屋顶纹理的快速合成。利用常州市三维城市模型数据进行了实验分析,实验表明,这两套纹理生成方案生成的屋顶纹理都满足建筑物纹理重建生产要求,极大地提高了三维建模效率。     

基于码字匹配和引力筛选的半监督协同训练算法

针对传统的Co-training和Tri-training协同训练算法中基分类器独立性低、迭代过程中误差累积和整体泛化性能低的问题,将多视图理论、编码理论和万有引力公式引入协同训练分类算法中,提出了改进算法,算法有效地防止了迭代过程中的误差累积,同时提高了分类系统的泛化性能。在高光谱图像分类实验中,随机地从数据集中抽取5%、10%和20%样本作为已标记训练集时,码字匹配的协同训练分类算法对比Co-training和Tri-training算法,在分类精度上平均分别提高了12.38%和6.13%,在Kappa系数上平均分别提高了0.2和0.07。进一步加入引力筛选机制,对比Co-training和Tri-training算法,在分类精度上平均分别提高了21.30%和10.99%,在Kappa系数上平均分别提高了0.26和0.13,结果表明了本文算法的有效性。