Spectral matching algorithm based on nonsubsampled contourlet transform and scale-invariant feature transform

A new spectral matching algorithm is proposed by us- ing nonsubsampled contourlet transform and scale-invariant fea- ture transform. The nonsubsampled contourlet transform is used to decompose an image into a low frequency image and several high frequency images, and the scale-invariant feature transform is employed to extract feature points from the low frequency im- age. A proximity matrix is constructed for the feature points of two related images. By singular value decomposition of the proximity matrix, a matching matrix （or matching result） reflecting the match- ing degree among feature points is obtained. Experimental results indicate that the proposed algorithm can reduce time complexity and possess a higher accuracy.

Efficient Scalable Template-Matching Technique for Ancient Brahmi Script Image

Analysis and recognition of ancient scripts is a challenging task as these scripts are inscribed on pillars,stones,or leaves.Optical recognition systems can help in preserving,sharing,and accelerate the study of the ancient scripts,but lack of standard dataset for such scripts is a major constraint.Although many scholars and researchers have captured and uploaded inscription images on various websites,manual searching,downloading and extraction of these images is tedious and error prone.Web search queries return a vast number of irrelevant results,and manually extracting images for a specific script is not scalable.This paper proposes a novelmultistage system to identify the specific set of script images from a large set of images downloaded from web sources.The proposed system combines the two most important pattern matching techniques-Scale Invariant Feature Transform(SIFT)and Template matching,in a sequential pipeline,and by using the key strengths of each technique,the system can discard irrelevant images while retaining a specific type of images.

基于Transformer的无人机多目标跟踪算法研究

针对无人机多目标跟踪面临目标遮挡、尺度变化、快速运动、复杂环境等问题,提出了一种基于Transformer的无人机多目标跟踪算法,采用Focal Transformer来捕获高分辨率输入的Transformer层中的局部和全局交互。该算法能够生成目标的检测信息以及目标的外观特征,从而提高了跟踪性能。在轨迹预测方面,采用了卡尔曼滤波方法,以准确地预测目标的运动轨迹,有助于提高跟踪的准确性和鲁棒性。在数据关联过程中,同时考虑了检测置信度、外观嵌入距离和IOU距离3个因素,以更有效地处理数据关联过程,提高了多目标跟踪模型的鲁棒性,使其能够在复杂场景中更好地跟踪目标。此外,还使用了轨迹的二次匹配方法,进一步提高了算法的性能。在VisDrone和UAVDT数据集上进行了对比验证,证明了该算法在实际应用中的有效性和可行性。本研究为无人机多目标跟踪提供了一种新的解决方案,具有广泛的应用前景。

Modified SIFT descriptor and key-point matching for fast and robust image mosaic

To improve the performance of the scale invariant feature transform （ SIFT）, a modified SIFT （M-SIFT） descriptor is proposed to realize fast and robust key-point extraction and matching. In descriptor generation, 3 rotation-invariant concentric-ring grids around the key-point location are used instead of 16 square grids used in the original SIFT. Then, 10 orientations are accumulated for each grid, which results in a 30-dimension descriptor. In descriptor matching, rough rejection mismatches is proposed based on the difference of grey information between matching points. The per- formance of the proposed method is tested for image mosaic on simulated and real-worid images. Experimental results show that the M-SIFT descriptor inherits the SIFT＇ s ability of being invariant to image scale and rotation, illumination change and affine distortion. Besides the time cost of feature extraction is reduced by 50% compared with the original SIFT. And the rough rejection mismatches can reject at least 70% of mismatches. The results also demonstrate that the performance of the pro- posed M-SIFT method is superior to other improved SIFT methods in speed and robustness.

Image matching algorithm based on SIFT using color and exposure information

Image matching based on scale invariant feature transform（SIFT） is one of the most popular image matching algorithms, which exhibits high robustness and accuracy. Grayscale images rather than color images are generally used to get SIFT descriptors in order to reduce the complexity. The regions which have a similar grayscale level but different hues tend to produce wrong matching results in this case. Therefore, the loss of color information may result in decreasing of matching ratio. An image matching algorithm based on SIFT is proposed, which adds a color offset and an exposure offset when converting color images to grayscale images in order to enhance the matching ratio. Experimental results show that the proposed algorithm can effectively differentiate the regions with different colors but the similar grayscale level, and increase the matching ratio of image matching based on SIFT. Furthermore, it does not introduce much complexity than the traditional SIFT.

Face recognition using SIFT features under 3D meshes

Expression, occlusion, and pose variations are three main challenges for 3D face recognition. A novel method is presented to address 3D face recognition using scale-invariant feature transform(SIFT) features on 3D meshes. After preprocessing, shape index extrema on the 3D facial surface are selected as keypoints in the difference scale space and the unstable keypoints are removed after two screening steps. Then, a local coordinate system for each keypoint is established by principal component analysis(PCA).Next, two local geometric features are extracted around each keypoint through the local coordinate system. Additionally, the features are augmented by the symmetrization according to the approximate left-right symmetry in human face. The proposed method is evaluated on the Bosphorus, BU-3DFE, and Gavab databases, respectively. Good results are achieved on these three datasets. As a result, the proposed method proves robust to facial expression variations, partial external occlusions and large pose changes.

Wide-baseline stereo matching based on multiple views

To solve the problem of wide-baseline stereo image matching based on multiple cameras,the paper puts forward an image matching method of combining maximally stable extremal regions (MSER) with Scale Invariant Feature Transform (SIFT) . It uses MSER to detect feature regions instead of difference of Gaussian. After fitted into elliptical regions,those regions will be normalized into unity circles and represented with SIFT descriptors. The method estimates fundamental matrix and removes outliers by auto-maximum a posteriori sample consensus after initial matching feature points. The experimental results indicate that the method is robust to viewpoint changes,can reduce computational complexity effectively and improve matching accuracy.

改进Census变换与特征融合的立体匹配算法

针对局部立体匹配算法匹配精度较低问题,提出一种改进Census变换与特征融合的立体匹配算法。首先,使用变换窗口的邻域像素信息代替中心像素,解决传统Census变换过度依赖窗口中心像素问题;其次,引入图像的颜色信息与梯度信息构建融合代价计算函数,提高初始匹配代价的可靠性;为建立邻域像素间联系,引入单向动态规划思想进行代价聚合;最后,提出一种基于八方向的视差空洞填充方法对视差图进行优化。实验结果表明:该算法在Middlebury数据集上的平均误匹配率为3.77%,优于其他改进Census变换方法,具有较高的匹配精度。

利用BERT和覆盖率机制改进的HiNT文本检索模型

为有效提升文本语义检索的准确度,本文针对当前文本检索模型衡量查询和文档的相关性时不能很好地解决文本歧义和一词多义等问题,提出一种基于改进的分层神经匹配模型(hierarchical neural matching model,HiNT)。该模型先对文档的各个段提取关键主题词,然后用基于变换器的双向编码器(bidirectional encoder representations from transformers,BERT)模型将其编码为多个稠密的语义向量,再利用引入覆盖率机制的局部匹配层进行处理,使模型可以根据文档的局部段级别粒度和全局文档级别粒度进行相关性计算,提高检索的准确率。本文提出的模型在MS MARCO和webtext2019zh数据集上与多个检索模型进行对比,取得了最优结果,验证了本文提出模型的有效性。

Algorithm Based on Morphological Component Analysis and Scale-Invariant Feature Transform for Image Registration

In this paper, we proposed a registration method by combining the morphological component analysis(MCA) and scale-invariant feature transform(SIFT) algorithm. This method uses the perception dictionaries,and combines the Basis-Pursuit algorithm and the Total-Variation regularization scheme to extract the cartoon part containing basic geometrical information from the original image, and is stable and unsusceptible to noise interference. Then a smaller number of the distinctive key points will be obtained by using the SIFT algorithm based on the cartoon part of the original image. Matching the key points by the constrained Euclidean distance,we will obtain a more correct and robust matching result. The experimental results show that the geometrical transform parameters inferred by the matched key points based on MCA+SIFT registration method are more exact than the ones based on the direct SIFT algorithm.

迷宫机器人迷宫信息提取方法研究

针对迷宫机器人自主获取迷宫信息耗时长、耗能高、信息缺失等问题,提出借助图像处理相关方法获取迷宫单元格信息,以提升迷宫机器人迷宫任务效率。针对迷宫图像中的亮度不均、色彩异化等固有缺陷,提出一种融合Kirsch和改进Canny算子的迷宫单元格边缘检测方法,实现了迷宫单元格的边缘特征提取。利用图像形态学原理,对迷宫单元格特征进行去噪、合并、膨胀和填充,实现图像边缘增强。针对迷宫单元格特征,提出了一种像素分块匹配特征法进行迷宫单元格信息匹配,以实现迷宫单元格的信息提取。实验结果表明对亮度范围在γ=1.1且拍摄角度30度及以上的迷宫图像信息提取正确率达到100%,因此,提出的迷宫信息提取方法是实际可行的,为后续迷宫机器人迷宫任务的高效执行提供了保证。

一种基于谱图SIFT的同源频谱监测数据判定方法

随着各类无线电应用的普及,在一定空间范围内,超短波监测过程中的监测数据易受到非同源的同频或邻频信号的影响,仅依靠常规监测中的频谱数据是无法判定信号是否同源的,因而不同监测站点获得的数据缺乏关联性,数据分析结果可能产生误导,降低工作效率。依据人工监测的经验,尝试用计算机视觉等技术分析监测数据的频谱图和时频谱图,结合谱图特性引入角度阈值改进SIFT算法的特征点匹配模式,以适应无线电监测数据分析的需要,并提出以图像特征点检测匹配率为前提,利用卡帕值综合评价两种谱图同源判定结果一致性的方法。通过实验模拟和实例验证,两种谱图同源判定结果的卡帕值为0.7605,达到高度一致;同时,所提方法在实践过程中有提高工作效率的作用,具备操作可行性和实际意义。

基于计算机技术的加密纸张图像识别模型构建

为实现造纸企业对加密纸张图像的自动化识别,提高数字图像识别准确率,通过伽马变换算法提升数字图像的对比度并对其实施边缘检测处理,进而实现原始纸张加密图像的外观增强,并获取用于识别加密纸张的目标图像。在此基础上,基于O-FAST角点检测技术实现目标图像与待测图像之间的近距离匹配,进而达到针对加密纸张图像的识别效果。为验证该方法的有效性,专门组建了一个图像识别匹配系统用于统计图像匹配效果。经试验研究发现,加密纸张图像识别模型在各匹配项目中的准确率均在95%以上。

基于四元数极性复指数变换的图像复制-粘贴篡改检测算法

在面对复制-粘贴(Copy-Move)篡改检测时,图像经过压缩、缩放、旋转和加噪等篡改操作处理后会导致检测性能的急剧下降甚至检测失败。本研究提出一种基于四元数极性复指数变换(quaternion polar complex exponential transform,QPCET)和改进PatchMatch的篡改检测算法。将待测图像进行重叠分块之后,计算各分块的四元数极性复指数变换不变量,并作为每一块的特征向量,构成特征矩阵。特征向量的初步匹配通过改进的PatchMatch算法完成,再通过随机抽样一致(random sampling consistency,RANSAC)算法去除错误的匹配块。在此基础上,使用形态学运算对标记区域进行处理,最终确定篡改区域。仿真结果表明,该算法可以有效检测图像中的Copy-Move篡改,并且对图像旋转、缩放、加噪和JPEG压缩等篡改区域后处理操作具有较好的鲁棒性。

多特征提取与匹配矩阵驱动的点云配准

针对三维点云配准时容易受到噪声、奇异值等不利因素影响的问题,提出一种多特征提取与匹配矩阵驱动的点云配准方法。利用多特征提取模块提取稳健的关键点和关键点的局部几何特征;分别计算出关键点的特征匹配矩阵和空间匹配矩阵,并对二者进行融合,提高正确匹配点对的概率;在前两方法的驱动下,利用加权奇异值分解计算点云间的刚体变换矩阵,降低噪声和奇异值等因素对配准的影响。实验结果表明,所提方法与现有的点云配准方法相比,具有更高的配准精度和较强的鲁棒性。

液压恒压网络驱动系统参数匹配

匹配了液压恒压网络驱动系统各部件参数,根据液压恒压网络驱动系统的结构、工作原理和特性,提出了一种有效的参数匹配方法。基于液压恒压网络驱动系统原理,分析了驱动力、恒压网络、液压变压器和液压马达之间的关系,研究了系统参数与车辆动力性能的关系,总结了关键参数的匹配原则和方法,引入了液压恒压网络驱动系统特征驱动力、液压变压器等效功率和等效流量,确定了衡量驱动系统驱动能力的指标,以及液压变压器匹配的原则。利用驱动系统参数匹配方法,对液压恒压网络驱动系统中的发动机、蓄能器、恒压网络、液压变压器和液压马达进行了参数匹配。研究结果表明,匹配的液压恒压网络驱动系统能够满足性能要求。搭建液压驱动系统实验台,验证了系统加减速能力,表明系统能够稳定运行。

基于开源GIS数据的广域小重叠卫星影像定位模型精化

设计了一种适用于大区域、小重叠卫星影像有理多项式模型(RPC)定位精度优化的技术流程,基于开源数字正射影像(DOM)、数字高程模型(DEM)数据和RPC几何模型约束,通过优化尺度不变特征变换(SIFT)特征提取与匹配算法,实现了无像幅约束的控制点和连接点的快速稳健匹配,应用DEM支持下的RPC模型二维区域网方法实现了多景影像RPC模型精度的联合精化。GF-1卫星WFV影像的实验结果表明:在DEM支持下经过区域网平差后,RPC模型的定位精度可达到像素级水平。

基于深度学习LoFTR算法的路面图像拼接

相比基于特征点的传统图像特征匹配算法,基于深度学习的特征匹配算法能产生更大规模和更高质量的匹配.为获取较大范围且清晰的路面裂缝图像,并解决弱纹理图像拼接过程中发生的匹配对缺失问题,本文基于深度学习LoFTR(detector-free local feature matching with Transformers)算法实现路面图像的拼接,并结合路面图像的特点,提出局部拼接方法缩短算法运行的时间.先对相邻图像做分割处理,再通过LoFTR算法产生密集特征匹配,根据匹配结果计算出单应矩阵值并实现像素转换,然后通过基于小波变换的图像融合算法获得局部拼接后的图像,最后添加未输入匹配网络的部分图像,得到相邻图像的完整拼接结果.实验结果表明,与基于SIFT(scale-invariant feature transform)、SURF(speeded up robust features)、ORB(oriented FAST and rotated BRIEF)的图像拼接方法比较,研究所提出的拼接方法对路面图像的拼接效果更佳,特征匹配阶段产生的匹配结果置信度更高.对于两幅路面图像的拼接,采用局部拼接方法耗费的时间较改进之前缩短了27.53%.研究提出的拼接方案是高效且准确的,能够为道路病害监测提供总体病害信息.

双目视觉下的自动驾驶车辆多类型障碍物感知

为解决视差变化率与距离变化率呈现非线性关系而导致障碍物感知误差大,本文提出基于双目视觉的多类型障碍物感知方法。利用极性几何约束双目摄像机相对位置关系,将多视极线约束与双目视觉下位置运动信息相结合,高斯滤波滤除图像噪声。采用卷积函数算子提取图像特征信号的角点,设置查找窗口,匹配左右目视觉下图像的相似程度,提高像素点集正确匹配准确率。研究表明:所提方法能够准确感知不同类型障碍物真实位置,障碍物特征匹配正确率高,实际感知误差小,该方法可为智能交通和城市交通管理提供可靠的数据支持,减少交通事故的发生率。

面向大视角差的无人机影像序列学习型特征匹配

针对无人机大视角差影像之间存在仿射变形大、遮挡严重、视角差异显著等问题导致的同名点匹配存在多解和大量误匹配难题,本文提出了一种适用于大视角差影像稳健匹配方法。利用改进的具有双头通信机制的D2-Net卷积神经网络提取倾斜影像的学习型特征,在之后的同名点匹配搜索阶段,为解决唯一匹配点受到较多潜在可行解干扰的问题,设计了一种由粗到精的提纯策略,在稳健匹配同名点对的同时大幅降低匹配开销成本。将HPatches数据集中多组不同场景的影像序列和实地采集的无人机大视角差影像序列作为数据源对提出的方法进行测试,并与具有代表性的基于手工设计的ASIFT方法和基于深度学习的多种方法进行了比较。结果表明,本文方法能够提取稳健的大视角差影像序列仿射不变学习型特征,在正确匹配点数、匹配点正确率、匹配点均方根误差和匹配时间开销方面具有优势。