无地面控制点航空图像无缝拼接算法

针对航拍图像拼接中,因为航带中航片拼接误差积累导致拼接后期图像发生扭曲问题,本文提出一种利用捆绑调整技术削弱航片拼接过程中误差累积。该算法采用SIFT（Scale Invariant Feature Transform）进行特征点提取和匹配;结合改进的RANSAC（Random Sample Consensus）对特征点进行提纯,剔除外点;由过滤后的特征点通过最小二乘法计算图像间的单应性矩阵,在此基础上运用捆绑调整法整体优化单应性矩阵进行图像间的拼接,解决了拼接后期图像扭曲问题。最后,通过动态加权的融合方法实现图像接缝处平滑过渡。为验证该算法的有效性,选用真实无人机航拍序列图像进行拼接实验,取得良好的拼接效果。     

一种抗几何攻击的小波域水印算法

目的针对小波变换域数字水印算法抗几何攻击能力差的问题,提出一种基于SIFT特征点匹配的DWT数字水印算法。方法将SIFT算法提取匹配特征点所具有的旋转、缩放和平移不变性的特性与DWT水印算法相结合,根据SIFT特征点的尺度特征和坐标关系,实现带水印图像的几何攻击参数估计和校正。结果仿真结果表明:提出的水印算法在受到系列旋转、缩放和平移攻击及组合攻击后,提取水印的NC值均大于0.8394,说明了算法的可行性。尤其是对于抗旋转攻击,优于其他同类或相关算法。结论提出的算法对旋转、缩放、平移等3种几何攻击都具有较好的鲁棒性。     

基于SIFT变换和RBF神经网络的彩色全景图拼接算法

目的 为了复原存在平移、色彩差异、旋转、形变等问题的全景图,提出一种结合SIFT（尺度不变特征变换）和RBF神经网络的彩色全景图拼接算法。方法 通过SIFT算法匹配出两子图中对应的特征点,利用仿射变换解决图像间的旋转和形变问题,采用RBF神经网络纠正子图的色彩差异,最后利用权值矩阵融合技术实现重叠区域的融合。结果 文中算法在拼接效果上优于其他算法,其拼接效果DoEM值为0.902,图像重叠区域过度平滑,有效地避免了融合区域的亮度块或亮度线。结论 该算法效果好,可解决全景图复原过程中多方面的难题。     

Feature‐assisted stereo correlation

Stereo correlation in digital image correlation (DIC) involves an optimisation problem that is sensitive to initial guess. In practice, this problem is circumvented by manually selecting a pair of points in the two stereo images that guarantees convergence and provides stereo mapping parameter estimates that are used as initial guesses at neighbouring subsets. However, such an approach is not always feasible, especially in the presence of substantial perspective distortions, for example, due to large stereo angles or complexities in specimen geometry. Therefore, it is desirable to provide high‐quality independent initial estimates over the entire region of interest. Recently, SIFT has been used for this purpose, but it fails when perspective distortions are severe. In this work, we investigate seven other feature‐based matching techniques to address this gap. Among these, DeepFlow algorithm provides the highest quality and most spatially uniform initial estimates. Further, we use DeepFlow estimates as initial guesses in a conventional stereo optimisation to compute geometry measures of a specimen in DIC challenge dataset. These geometry measures show excellent agreement with ground truth, further supporting the choice of DeepFlow in stereo correlation.     

基于SIFT的NSCT域抗几何攻击水印算法

目的针对基于尺度不变特征变换(SIFT)的抗几何攻击图像水印算法在图像匹配时容易产生误匹配,影响提取水印的鲁棒性,提出一种改进的SIFT图像水印算法。方法先对载体图像进行两级非下采样Contourlet变换(NSCT),利用中间值量化算法把水印信息嵌入低频系数的方向子带中。图像匹配时利用广义霍夫变换删除误匹配特征点对,提高匹配精度。根据筛选后的特征点匹配对估算几何失真参数,对含水印的载体图像进行几何校正并提取水印,从而实现水印的抗几何攻击。结果实验数据表明对原始特征点匹配对进行筛选后,至少提高了6.8%的匹配精度,提取水印的NC值平均达到0.9以上。结论文中提出的改进算法不仅对几何攻击和常规信号攻击均具有较好的鲁棒性,还能保证水印的不可见性。     

基于颜色矩的改进尺度不变特征变换的移动机器人定位算法

针对基于图像外观的移动机器人定位中图像特征提取与匹配实时性和准确性差的问题,提出基于颜色矩的改进尺度不变特征变换分级图像匹配算法。该算法先由颜色矩来排序图像序列,再由改进尺度不变特征变换特征与排序后图像序列精确匹配实现定位。其中,改进的尺度不变特征变换算法以基于采样的迭代搜索算法检测极值点,由Sobel算子计算特征点的梯度方向和幅值,提高尺度不变特征变换算法速度及匹配精度。实验结果表明:改进的尺度不变特征变换算法降低误匹配率约9.2%,特征提取与匹配耗时减少约25.8%;分级图像匹配算法减少尺度不变特征变换特征计算代价约70%,减少总体耗时约43.3%。     

The Enhanced Digital Image Correlation Technique for Feature Tracking During Drying of Wood

Abstract: The enhanced digital image correlation (EDIC) technique is proposed as an improvement of the digital image correlation (DIC) technique in that it utilises monogenic filtering as a prefilter for extracting intrinsic local phase information from the low‐contrast images and normalized cross‐correlation (NCC) as a feature‐tracking algorithm. The monogenic filtering separates local structural information that is the local phase of an image, which is invariant with respect to the local energy of the image. Therefore, it improves the image, permitting the DIC technique to produce stable and accurate measurements of deformation for a heterogeneous and hygroscopic material like wood during drying.     

模式图像的特征提取与配准方法

目的提高产品包装模式图像的匹配速度和准确性,得出算法中影响这两方面的关键因素。方法运用高斯金字塔对原始图像进行向下采样,将图像转换为尺度空间的表示方式;利用加速稳健特征(SURF)方法提取特征点,并对SURF方法提取的特征点用Brute-Force算法进行匹配;通过对每组匹配点欧式距离的排序,剔除误匹配点,仅保留一定数量的正确匹配点对。结果得出高斯金字塔、Hessian值、颜色空间对计算速度及获取特征点数量的影响。颜色空间的改变不影响特征点数量,在计算时间上的差别也可忽略。尺度空间缩小1/2时,计算速度能够提升75%,同时剔除2/3的冗余特征点。结论文中方法能够有效提升特征提取速度,并且具有匹配精度高、鲁棒性强的特点,同时对旋转角度的变化具有较强的适应性。     

基于不变矩特征模型耦合相似度量规则的图像匹配算法

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。     

Uneven intensity change correction of speckle images using morphological Top-Hat transform in digital image correlation

By comparing two digital speckle images recorded before and after deformation, two-dimensional digital image correlation (DIC) method can accurately determine the in-plane displacement fields and strain fields. In a practical measurement, however, the variance of light source intensity, location and direction will cause the random uneven intensity change of the random speckle images and will lead to the obvious measurement error. Numerical simulation experiment is first carried out to analyse the influence of the recorded speckle images undergoing uneven light variation on DIC measurement accuracy. Then, a correction method for speckle images with uneven intensity change is proposed based on morphological Top-Hat transform. In addition, quantitative measurements of both in-plane rotation of a rigid body and three-point bending beam are investigated experimentally by DIC to verify the feasibility of the correction method. Experimental results show that the measurement accuracy of DIC is improved dramatically after the procedure of uneven light variation correction.     

基于SIFT特征点匹配的抗几何攻击水印算法

目的为了有效抵抗几何攻击,实现水印图像的嵌入与检测的同步。方法将水印嵌入到图像小波分解后的奇异值中,然后利用SIFT(scale invariant feature transform)特征点所具有的旋转、缩放和平移不变性进行宿主图像和受攻击图像的匹配,并估计受攻击图像的几何攻击参数,对可能失真的图像进行几何校正。结果图像经过几何失真、常规图像处理攻击或JPEG压缩后,嵌入的水印依然能被可靠地检测和提取。结论理论分析和大量实验结果表明,该算法校正精度高,具有良好的不可见性和鲁棒性。     

加权相位一致性改进的图动态精确配准算法

目的为了解决当前图像配准算法匹配精度较低的问题。方法提出加权相位一致性耦合改进的图变换匹配的精准动态图像配准算法。首先,基于SIFT机制,检测图像中的关键点;并嵌入加权因子,定义相位一致性特征,对关键点完成提纯,消除误配点与稳定性不佳的特征点;随后,设计角度距离,替代相邻特征,改进图变换匹配技术,形成精准匹配关系集;再利用初始匹配特征点与精准匹配特征点间的映射关系,对其完成修正;最后,利用改进的图变换匹配算法处理修正后的匹配关系,进一步提高匹配精度。结果仿真结果显示,与当前图像配准技术相比,改进的算法拥有更强的鲁棒性与更高的匹配精度。结论改进的算法能够提高图像在几何变换程度较大时的匹配精度。     

旋转不变纹理特征用于两级图像检索

针对图像中常见的旋转问题提出一种旋转不变纹理特征进行两级图像检索的方法。粗检中,通过坐标变换把图像的旋转转换为行移,并提取近似行移不变的小波特征,结合粗比较算法对整个图像库进行粗检。然后对通过粗检的图像进行 Gabor 变换,提取旋转不变精检索特征,并使用Canberra 距离进行相似性度量。通过对旋转图像库的测试表明,该方法不仅加快了运算速度,且当参数选择适当时,在相同特征条件下,检索率比直接使用精检索方法检索时还提高了 1.625%。     

结合Zernike矩的多尺度模板形状匹配

针对形状匹配中小波表达对起始点依赖的问题,提出一种结合Zernike矩的多尺度模板进行形状匹配的方法。该算法对输入图像进行预处理后提取目标轮廓,经过归一化处理得到目标形状的平移、尺度不变的链状表达,再通过小波变换进行多尺度分析;引入Zernike矩,利用Zernike矩的特性,实现小波表达的旋转不变性,解决了小波变换对起始点的依赖。匹配过程是以小波表达的各阶Zernike矩为特征向量,在由粗到精的尺度上进行的。实验结果表明,对于同一目标,原图像与旋转不同角度的图像的正确匹配率为91％。该算法适用于轮廓较明显的目标。     

On image gradients in digital image correlation

In digital image correlation (DIC), the unknown displacement field is typically identified by minimizing the linearized form of the brightness conservation equation, while the minimization scheme also involves a linearization, yielding a two‐step linearization with four implicit assumptions. These assumptions become apparent by minimizing the non‐linear brightness conservation equation in a consistent mathematical setting, yielding a one‐step linearization allowing a thorough study of the DIC tangent operator. Through this analysis, eight different image gradient operators are defined, and the impact of these alternative image gradients on the accuracy, efficiency, and initial guess robustness is discussed on the basis of a number of academic examples and representative test cases. The main conclusion is that for most cases, the image gradient most common in literature is recommended, except for cases with: (1) large rotations; (2) initial guess instabilities; and (3) costly iterations due to other reasons (e.g., integrated DIC), where a large deformation corrected mixed gradient is recommended instead. Copyright © 2015 John Wiley & Sons, Ltd.     

Application of Elastic Image Registration and Refraction Correction for Non‐Contact Underwater Strain Measurement

Abstract: The refraction‐induced image distortion introduces large errors in the deformation measurement of fluid submerged specimens using digital image correlation (DIC). This study provides a review of the nature of the refraction‐induced image distortion, assesses experimental conditions that interact with refraction and proposes an elastic image registration technique to correct the refraction distortion of underwater images. In the elastic image registration technique, control points are selected on reference and refracted images of a template object and locally sensitive transformation functions that overlay the two images are obtained. The transformation functions so obtained are then used to reconstruct undistorted images from underwater images and the former are used as input to a DIC system. The proposed approach has shown to improve the refraction error in the order of 5–8% for typical material test samples undergoing deformation inside a water‐filled glass chamber.     

基于兴趣点特征匹配的印刷图像缺陷检测

提出了1种基于兴趣点特征匹配的印刷图像缺陷检测方法.首先利用SIFT特征检测器,获取图像中具有旋转和平移不变性的特征点,然后采用最近邻方法进行特征点匹配,最后使用最小二乘优化算法,计算2幅图像特征点对的变换矩阵来实现缺陷图像的检测.实验结果表明:该方法能够快速准确地提取出2幅图像间的对应特征点,大大降低了误匹配的概率,在图像发生较大平移和旋转的情况下,仍能准确地实现图像的对准及缺陷图像的检测.