共查询到19条相似文献,搜索用时 140 毫秒
1.
无人机航空遥感电子稳像系统中,稳像的关键技术之一是影像特征点的选取,其中图像角点是遥感影像中重要的特征信息,准确地选取角点可提高图像处理的精度。然而现有的图像角点检测算法多因计算速度慢不能满足视频图像数字稳像的实时性。因此提出了一种基TSUSAN角点检测算法的改进算法。新算法分析了影像中角点所在区域的灰度变化特征,改进了SUSAN角点检测算法中的判断准则,提高了算法的精度和速度。实验结果表明,改进的算法可较大幅度的提高运算速度,满足稳像技术对视频图像实时处理的要求。 相似文献
2.
目的旨在传统Harris角点检测算子的基础上进行改进,以提高算子的漏检率和伪角点检测能力。方法以自动物流包装线上物料的识别为例,把获取到的图像先进行预处理,得到灰度图像,在灰度图的基础上,首先通过方向可调滤波器进行4个不同角度的旋转,再分别进行角点检测,最后通过逻辑运算综合判断真伪角点。结果把图像预处理的图像数据使用改进后的Harris角点检测算子进行角点检测,并与经典角点检测算子进行比较,结果表明改进后的算子确实有很强的辨别真伪角点的能力。结论实验证明该方法可有效提高角点检测算子的识别准确率,误检率降低到了1.3%,漏检率降低到了2.9%。 相似文献
3.
4.
基于Radon变换的图像角点角度提取算法 总被引:3,自引:0,他引:3
针对现有角点检测算法只提取图像角点位置而无法提取角点角度的缺陷,本文在SUSAN角点检测算法的基础上,提出基于Radon变换的图像角点角度提取算法.该算法首先利用SUSAN算子检测候选角点,然后得到候选角点子邻域图像,对其进行角点角度可测量性判定,对满足可测量性的角点子邻域图像中每个像素点进行梯度映射后,利用Radon变换提取角点边缘直线,最后利用坐标几何关系提取角度.并针对Radon变换无法检测直线起始点导致角点角度提取时存在二值歧义性的缺陷,本文借鉴USAN思想,把同值核引入到角度提取中,从而实现了对角度的正确提取.该算法实现简单,实验结果证明了其有效性. 相似文献
5.
使用多尺度Harris算子检测图像的角点作为初始兴趣点.针对自适应非极大值抑制排除了大量潜在匹配点的缺陷,引入条件理论对初始兴趣点进行控制,排除病态点,减少后续过程的计算量,提高算法效率,同时最大限度的保留了匹配点.满足条件理论控制下的特征称为良态特征.由于初始Harris角点的位置会发生偏移以及有伪角点产生,所以利用亚像素定位技术进行精确定位,并排除伪角点和不稳定的角点.使用PCA-SIFT对特征点及其邻域进行描述获得特征向量.最后通过向量之间的欧几里德距离判断特征点是否匹配.实验结果表明算法效率改进明显,匹配效果良好,对图像的几何变换、噪声及光照变化等具有较强的鲁棒性. 相似文献
6.
具有SIFT描述的Harris角点多源图像配准 总被引:3,自引:0,他引:3
多源传感器成像原理的差异给图像配准带来了很大困难,本文针对红外与可见光图像配准提出了一种具有SIFT描述特征的Harris角点多源图像配准算法。首先建立多尺度空间,以多尺度空间检测尺度不变的Harris角点作为特征点;然后通过改进SIFT对特征点的描述方法,采用圆环结构算子对Harris角点进行类SIFT的特征描述;最后利用双向最近邻方法进行匹配,通过最小二乘法实现图像的配准。实验证实了算法配准的精确性、快速性和稳定性,具有较好的配准效果。 相似文献
7.
利用小波边缘增强的可靠性匹配方法 总被引:1,自引:1,他引:0
为提高景像匹配的可靠性,提出了一种基于小波边缘增强的可靠性匹配方法。采用四阶中心B样条小波对实时图和基准图进行小波分解和边缘增强,以提取可靠的边缘特征。在粗尺度上基于小波边缘增强图进行相关匹配,选择相似度曲面上前5个峰值点作为候选匹配点,保证正确匹配点可以包含在候选匹配点中。对实时图进行旋转校正,利用候选匹配点处的局部灰度特征确定边缘提取的双阈值,应用形态学连接算子来获得二值边缘图,再进行相关匹配,筛选出正确匹配点。在细尺度上获得精确的定位点。应用该方法进行匹配实验,其匹配概率比基于小波二值边缘提取的匹配算法提高了6.95%。 相似文献
8.
9.
目的为了解决当前图像匹配算法因主要利用特征点之间的距离来实现特征匹配,从而忽略了特征点的结构特征,导致算法存在较多的漏匹配点以及错误匹配点等不足的问题。方法提出基于不变矩特征模型耦合相似度量规则的图像匹配算法。通过对待检测像素点构造的邻域圆上的点进行分类,制定检测规则,对FAST算子进行改进,利用改进的FAST算子快速、精准地检测图像的特征点。随后,构造不变矩特征模型,取代SIFT算法中获取特征向量的方法,生成低维度的特征描述符。通过Euclidean模型和SSIM建立相似度量规则,对特征点之间的相似度进行度量,完成图像的特征匹配。最后,引入随机抽样一致性(RANSAC)算法剔除错误匹配点,完成图像的匹配。结果仿真结果显示,相较于当前的图像匹配算法,所提算法具有更高的匹配正确度和鲁棒性,其查全率最高可达95%左右,且匹配效率较快,约为3.75 s。结论所提匹配方法具备良好的匹配精度,在图像信息安全、包装条码识别与拼接等领域具有一定的参考价值。 相似文献
10.
基于包装件智能分拣的视觉尺寸测量技术 总被引:1,自引:1,他引:0
目的快速实现包装纸箱尺寸的机器视觉测量。方法采用机器视觉技术方法,运用双目摄像机的成像原理,通过SUSAN角点提取算法结合棋盘标定法求取摄像机内外参数,修正图像畸变,采用SIFT匹配算子对左右2幅图像进行匹配,找到对应的匹配特征点,利用匹配点对的视差值恢复图像深度信息,进而求解出包装箱的长宽高值。结果对不同摆放姿态的包装箱均能实现快速测量,机器视觉检测值与实物值相比,其误差均在1 cm左右,满足检测要求。结论文中方法具有匹配精度高、鲁棒性强的特点,能快速实现对不同摆放姿态的包装箱尺寸测量。 相似文献
11.
基于小波的多尺度SUSAN角点检测 总被引:1,自引:0,他引:1
SUSAN角点检测是一种经典的角点检测算法,但不具有尺变化特性.利用小波变换的多尺度特性,即在小尺度下的定位准确和大尺度下的抗噪性强,该文把多分辨分析的思想引入到该算法中,从而构建了一种新的基于小波变换的SUSAN多尺度角点检测算法.新的角点检测可以在不同的尺度下获取角点,克服了单一尺度的SUSAN角点检测可能存在的角点位置偏移和易受噪声干扰而提取出伪角点等问题.为了综合利用各个尺度下的角点信息,该文提出了由粗到细的角点筛选方案.通过对比实验,新算法明显地提高了图像角点检测性能. 相似文献
12.
13.
C. P. Chalmers 《技术计量学》2013,55(4):536-537
Following an analogous distinction in statistical hypothesis testing and motivated by chemical plume detection in hyperspectral imagery, we investigate machine-learning algorithms where the training set is comprised of matched pairs. We find that even conventional classifiers exhibit improved performance when the input data have a matched-pair structure, and we develop an example of a “dipole” algorithm to directly exploit this structured input. In some scenarios, matched pairs can be generated from independent samples, with the effect of not only doubling the nominal size of the training set, but of providing the matched-pair structure that leads to better learning. The creation of matched pairs from a dataset of interest also permits a kind of transductive learning, which is found for the plume detection problem to exhibit improved performance. Supplementary materials for this article are available online. 相似文献
14.
Yu. V. Tarbeev P. V. Novitskii V. I. Mishustin A. G. Lupei 《Measurement Techniques》1999,42(11):1051-1056
The effect of individual and matched pairs of resistance thermometers on the error in determining thermal energy by a metering
unit is estimated. Criteria for selecting domestic mass-produced matched pairs of resistance thermometers are given and the
existing approach to producing matched pairs is analyzed. Metrological requirements, rules, and a program for selecting matched
pairs based on a new criterion are formulated.
Translated from Izmeritel'naya Tekhnika, No. 11, pp. 32–36, November, 1999. 相似文献
15.
Chambers RB Krousel-Wood MA Re R 《The Joint Commission journal on quality improvement》2001,27(2):101-106
INTRODUCTION: It has been proposed that a ratio of the discordant cells from a McNemar's Chi-square table be used as a measure of quality improvement, and that this measure be called the Quality Improvement Ratio (QuIR). As proposed, patients enrolled in only one year of a two-year study are excluded from the McNemar's table of the QuIR. Since the original proposal of the McNemar's Chi-square in 1947 included application to matched pair data, a more comprehensive analysis would be possible if the single-year enrollees were matched into pairs. METHODS: Patients enrolled in only the first study year are matched and paired with patients enrolled in only the second study year. The pairs are matched on variables important to the disease or process being evaluated. The matched pairs are combined with the repeatedly measured subjects to increase the statistical power of the analysis. The Combined Quality Improvement Ratio (CQuIR) is demonstrated with parameters from the original articles, in a--Markov chain Monte-Carlo simulation, so a direct comparison can be made. RESULTS: CQuIR improved statistical power, especially in simulations of small populations. In some simulations the statistical power was double that of the QuIR alone. DISCUSSION: Although the QuIR provides important information, the CQuIR allows more of the data to be used to evaluate the effect of interventions in policy, delivery, and practice. The increase in statistical power of the CQuIR over the QuIR can facilitate successful evaluation of health care services. 相似文献
16.
17.
基于SUSAN和Hough变换的直线边缘亚像素定位方法 总被引:3,自引:0,他引:3
提出了一种基于SUSAN算法和Hough变换的直线边缘亚像素定位方法.在该方法中,给出了SUSAN算法模板选择的依据,同时定义了直线边缘响应函数并引入加权Hough变换.首先,利用直线边缘响应函数对直线边缘进行提取;然后对具有响应值的灰度点进行Hough变换并将该响应值作为权值记入参数空间累加器,得到粗定位;在粗定位的基础上对映射区进行局部细化,并对区域内点进行拟合,最终得到直线边缘精定位.实验证明:直线边缘定位精度可达0.3 pixels,同时为解析曲线亚像素定位提供了一种新的思路. 相似文献
18.
19.
Solving constrained optimization problems (COPs) via evolutionary algorithms (EAs) has attracted much attention. In this article, an orthogonal design based constrained optimization evolutionary algorithm (ODCOEA) to tackle COPs is proposed. In principle, ODCOEA belongs to a class of steady state evolutionary algorithms. In the evolutionary process, several individuals are chosen from the population as parents and orthogonal design is applied to pairs of parents to produce a set of representative offspring. Then, after combining the offspring generated by different pairs of parents, non-dominated individuals are chosen. Subsequently, from the parent’s perspective, it is decided whether a non-dominated individual replaces a selected parent. Finally, ODCOEA incorporates an improved BGA mutation operator to facilitate the diversity of the population. The proposed ODCOEA is effectively applied to 12 benchmark test functions. The computational experiments show that ODCOEA not only quickly converges to optimal or near-optimal solutions, but also displays a very high performance compared with another two state-of-the-art techniques. 相似文献