Image Relaxation Matching Based on Feature Points for DSM Generation

In photogrammetry and remote sensing, image matching is a basic and crucial process for automatic DEM generation. In this paper we presented a image relaxation matching method based on feature points. This method can be considered as an extention of regular grid point based matching. It avoids the shortcome of grid point based matching. For example, with this method, we can avoid low or even no texture area where errors frequently appear in cross correlaton matching. In the mean while, it makes full use of some mature techniques such as probability relaxation, image pyramid and the like which have already been successfully used in grid point matching process. Application of the technique to DEM generaton in different regions proved that it is more reasonable and reliable.

A calculation method for low dynamic vehicle velocity based on fusion of optical flow and feature point matching

Aming at the problem of the low accuracy of low dynamic vehicle velocity under the environment of uneven distribution of light intensity,an improved adaptive Kalman filter method for the velocity error estimate by the fusion of optical flow tracking and scale mvaiant feature transform(SIFT)is proposed.The algorithm introduces anonlinear fuzzy membership function and the filter residual for the noise covariance matrix in the adaptive adjustment process.In the process of calculating the velocity of the vehicle,the tracking and matching of the inter-frame displacement a d the vehicle velocity calculation a e carried out by using the optical fow tracing and the SIF'T methods,respectively.Meanwhile,the velocity difference between theoutputs of thesetwo methods is used as the observation of the improved adaptive Kalman filter.Finally,the velocity calculated by the optical fow method is corrected by using the velocity error estimate of the output of the modified adaptive Kalman filter.The results of semi-physical experiments show that the maximum velocityeror of the fusion algorithm is decreased by29%than that of the optical fow method,and the computation time is reduced by80%compared with the SIFT method.

GRADIENT OF REFERENCE DIFFERENCE BASED MATCHING ALGORITHM FOR IMAGE FEATURE POINT

During matching on feature point, gray correlation matching technology is utilized to extract multi-peaks as a coarse matching set. A pair of given corresponding reference points within the left and right images is used to calculate gradients of reference difference between the reference points and each feature point within the multi-peaks set. The unique correspondence is determined by criterion of minimal gradients of reference difference. The obtained correspondence is taken as a new pair of reference points to update the reference points continuously until all feature points in the left (or right) image being matched with the right (or left) image. The gradients of reference difference can be calculated easily by means of pre-setting a pair of obvious feature points in the left and right images as a pair of corresponding reference points. Besides, the efficiency of matching can be improved greatly by taking the obtained matching point as a new pair of reference points, and by updating the reference point continuously. It is proved that the proposed algorithm is valid and reliable by 3D reconstruction on two pairs of actual natural images with abundant and weak texture, respectively.

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.

Image Feature Extraction and Matching of Augmented Solar Images in Space Weather

Augmented solar images were used to research the adaptability of four representative image extraction and matching algorithms in space weather domain.These include the scale-invariant feature transform algorithm,speeded-up robust features algorithm,binary robust invariant scalable keypoints algorithm,and oriented fast and rotated brief algorithm.The performance of these algorithms was estimated in terms of matching accuracy,feature point richness,and running time.The experiment result showed that no algorithm achieved high accuracy while keeping low running time,and all algorithms are not suitable for image feature extraction and matching of augmented solar images.To solve this problem,an improved method was proposed by using two-frame matching to utilize the accuracy advantage of the scale-invariant feature transform algorithm and the speed advantage of the oriented fast and rotated brief algorithm.Furthermore,our method and the four representative algorithms were applied to augmented solar images.Our application experiments proved that our method achieved a similar high recognition rate to the scale-invariant feature transform algorithm which is significantly higher than other algorithms.Our method also obtained a similar low running time to the oriented fast and rotated brief algorithm,which is significantly lower than other algorithms.

FeatureMatching Combining Variable Velocity Model with Reverse Optical Flow

The ORB-SLAM2 based on the constant velocity model is difficult to determine the search window of the reprojection of map points when the objects are in variable velocity motion,which leads to a false matching,with an inaccurate pose estimation or failed tracking.To address the challenge above,a new method of feature point matching is proposed in this paper,which combines the variable velocity model with the reverse optical flow method.First,the constant velocity model is extended to a new variable velocity model,and the expanded variable velocity model is used to provide the initial pixel shifting for the reverse optical flow method.Then the search range of feature points is accurately determined according to the results of the reverse optical flow method,thereby improving the accuracy and reliability of feature matching,with strengthened interframe tracking effects.Finally,we tested on TUM data set based on the RGB-D camera.Experimental results show that this method can reduce the probability of tracking failure and improve localization accuracy on SLAM(Simultaneous Localization and Mapping)systems.Compared with the traditional ORB-SLAM2,the test error of this method on each sequence in the TUM data set is significantly reduced,and the root mean square error is only 63.8%of the original system under the optimal condition.

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.

基于改进SURF的图像特征点匹配算法

为了提升图像在三维重建过程中特征点匹配时的准确率,提出了一种基于改进SURF(speeded-up robust features)的图像特征点匹配算法。首先,将SURF的64维度描述符提升至128维度;其次,在SURF算法引入KD-Tree模块,利用BBF(best bin first)最近邻查询机制实现特征点匹配;最后,通过对同一数据集进行旋转、缩小,并利用传统算法和改进SURF算法分别对图像进行特征点匹配实验,验证改进SURF算法的有效性。结果表明:改进SURF算法的特征点匹配正确率达到了89.19%,相较于传统SURF算法提高了17.62个百分点;特征错误匹配数由85减少至31,显著降低了特征点的匹配误差;运行时间由1.956 s缩短至1.647 s,进一步提升了算法的运行速度。改进后的SURF算法具备正确率高、误差小、速度快的特点,可为三维重建特征匹配工作提供重要的参考。

基于改进的SuperGlue模型的浮选泡沫稳定度检测方法研究

在浮选过程中,浮选泡沫保持一定的稳定度对保证浮选指标的稳定至关重要。由于浮选泡沫本身的复杂性和现有检测方法的局限性,目前还无法对工业现场泡沫的稳定度进行定量检测和评估。为此,开发了一种基于改进的SuperGlue模型的浮选泡沫图像特征匹配算法,用于对浮选泡沫的稳定度进行测量。该算法采用改进的SuperPoint模型网络对泡沫图像进行特征点提取,将原有的VGG网络进行了改进,利用特征匹配模型对所得到的两组特征点进行匹配,再进行误匹配精筛选,设置置信度阈值进一步提升匹配精度。对比了在匹配算法中应用比较多的GMS算法,本文算法的有效特征点匹配对数提升了19.58%,匹配精度达99.85%。与传统灰度差值法对比,本文的泡沫稳定度测量方法对不同状态的泡沫可辨识性提升明显,极大地提高了图像检测灵敏度,可以满足生产对泡沫稳定度测量的要求。

基于HQB-SHOT特征描述符门座起重机特征匹配研究

为推动港口件杂货码头的自动化发展和减少激光雷达在门座起重机特征匹配过程中的计算开销,文中从SHOT特征描述符的构建过程和实际应用方面进行改进,提出了半球化的区间双编码位SHOT特征描述符:将局部参考坐标系获得的球形空间选取包含点多的一半球形为邻域,然后沿着仰角、方位角和径向线将球形邻域划分,统计每个小块中邻居点的法线和特征点的法线间的角度形成直方图,最后把直方图组合形成特征,在此基础上对所得到的描述子进行QB-SHOT二进制编码,最后得到半球化的区间双编码SHOT特征描述子。在采集到的门座起重机点云数据集进行实验,实验结果表明,HQB-SHOT在算法速度和匹配精度上均有所提高,实验验证了HQB-SHOT在港口门座起重机上应用的可行性和有效性。

改进ORB提取匹配算法的SLAM应用研究

由于传统的ORB特征点提取匹配方法在图像纹理信息不丰富或者光照变化剧烈时极易产生特征点丢失、分布不均等问题,不利于SLAM系统的定位与建图。为此本文提出了一套较为鲁棒、精度较高的提取匹配算法。首先基于ORB特征点对其提取算法进行改进,计算自适应阈值并基于网格模型提取特征点,可提高特征点提取的鲁棒性并使其分布均匀。此外还提出了G-R图像匹配算法,基于网格特征计算邻域支持估计量来区分正误匹配点,再结合引入评价函数的RANSAC算法进一步剔除误匹配点,相比ORB-SLAM2原始匹配算法提高匹配精度9.36%,并减少时间消耗约13.6%。最后将本文提出的特征点提取匹配算法加入到ORB-SLAM2算法框架,经数据集与实际场景验证本文方法能有效提高ORB-SLAM2系统定位精度36.6%以上,使系统更具鲁棒性。

基于SURF-OKG特征匹配的三维重建技术

为了解决结构光三维重建中传统立体匹配存在的特征点匹配错误、匹配缺失和匹配重复等问题,本文将SURF算法中高斯滤波改进为自适应中值滤波结合小波变换,并提出了一种基于OKG算法的二次特征匹配方法。该算法首先使用自适应中值滤波结合小波变换算法对图像进行平滑和降噪处理,再进行初步特征点提取和匹配,然后将构建的尺度空间划分成多个网格,在每个网格内使用FAST算法提取尺度空间特征点,使用ORB算子提取左右图像的特征点,用BRIEF描述子对其进行描述,采用K-D树最近邻搜索法限制特征点选取,通过GMS算法剔除误匹配点。最后,将本文SURF-OKG算法与传统特征匹配算法进行对比分析,并对阶梯块进行三维重建来验证本文算法的有效性。实验结果表明:SURF-OKG算法的正确匹配率为92.47%;对阶梯宽度为40 mm,精度为0.02 mm的阶梯块进行三维重建,实验测得阶梯宽度的误差均值为1.312 mm,最大误差值不超过1.72 mm,基本满足结构光三维重建系统的实验要求。

GNSS辅助的视觉动态定位方法研究

针对在城市环境中全球导航卫星系统间歇失锁时运动平台无法连续定位的问题,研究一种GNSS辅助的视觉动态定位方法。该方法利用相机对街景拍摄3幅影像且记录相应位置的GNSS坐标,以GNSS坐标系为世界坐标系。首先分别提取这3幅影像中的SIFT特征点进行三维重建,得到这些特征点在第1幅影像所对应相机坐标系中的坐标以及相机在这3个位置之间的位姿变换,接着利用这3幅影像所对应的GNSS坐标求得相机坐标系与GNSS坐标系之间的位姿变换。然后通过对此街景任意拍摄1幅影像,即可利用P3P+RANSAC对当前影像所对应的相机位姿进行解算得到相机平台此时的GNSS坐标。最后对某场景的影像数据进行实验,实验结果验证了此方法的可行性,且其定位精度一般不超出6 m。

基于四叉树法和PROSAC算法改进的视觉SLAM技术

为解决在同时定位与地图构建(simultaneous localization and mapping,SLAM)的前端进行特征点匹配时,随机抽样一致法(random sample consensus,RANSAC)存在的迭代次数高、实时性较差、鲁棒性不稳定等问题,提出一种基于四叉树法和渐进一致采样法(progressive sample consensus,PROSAC)算法融合改进的图像匹配算法。实现四叉树法+PROSAC算法的误匹配剔除算法,在EuRoC数据集上对改进后的ORB-SLAM2算法进行实验。结果表明:相比于ORB-SLAM2系统,该算法在Vicon Room 103数据集上总体绝对轨迹误差平均值减小了39.28%,总体相对位姿误差减小了35.45%,具有更高的建图精度。

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ORB-SLAM2的改进特征匹配与稠密地图算法

针对ORB-SLAM2算法在特征匹配时容易出现误匹配以及无法构建稠密地图的问题,引入GMS算法来改进ORB-SLAM2算法中的误匹配问题以及添加稠密地图线程。首先,建立图像金字塔,对每层图像金字塔进行网格划分,提取特征点,对每个网格中的特征点引入四叉树策略进行筛选,得到均匀的特征点;其次,在特征匹配阶段引入GMS算法剔除误匹配;最后,根据位姿估计和关键帧构建稠密点云地图。通过TUM数据集上的实验验证,结果表明改进算法的匹配数比原ORB-SLAM2算法增加了18.36%,匹配用时减少了8.53%,将改进算法应用于移动机器人自动导航和避障中,能够提高系统的可靠性和运行效率。

基于点线特征的快速视觉惯性SLAM算法

为了提高基于点特征的SLAM算法的定位精度和鲁棒性,提出一种点线特征融合的快速单目视觉惯性SLAM算法。使用ELSED算法快速提取高质量的线特征,在非关键帧追踪时,基于连续帧之间微小运动的假设,实现连续图片间的快速线段匹配,且无需线段描述子。在插入新关键帧时,提取线段描述子来完成关键帧之间的线特征匹配,创造新的地图线。最后在公开数据集上进行实验,结果表明:ELSED算法在提取高质量线段的同时,耗时仅为LSD算法的13%;与传统利用线段描述子的匹配算法相比,此算法的时间效率提升了83%,并减少线段误匹配,提高系统定位精度,系统的平均跟踪帧率为33帧/s,保证了系统的实时性。

VSLAM系统中的快速特征点匹配算法

连续图像帧之间特征点匹配是视觉同步定位与建图(VSLAM)技术的关键技术;针对VSLAM系统中连续图像帧之间特征点匹配耗时且精度低的问题,一种基于局部像素运动模型的快速特征点匹配算法(LPMM)被提出;该算法基于运动平滑约束假设,利用连续图像帧中局部区域内的像素点的运动具有一致性这一特性,将图像划分成局部网格区域后利用每个网格中的部分特征点估算该网格区域的运动向量,并以此为基础,计算下一帧匹配特征点的搜索范围的中心点;最终在计算出下一帧的中心点的局部邻域内搜索与当前帧的特征点相匹配的特征点;实验结果表明,所提出的匹配算法与广泛使用的ORB-SLAM2中的投影匹配算法相比,平均匹配速度提高50%以上,匹配精度提升了约4%。

一种基于GMS的ORB-SLAM3特征匹配改进算法

针对ORB-SLAM3中ORB特征点匹配准确率低的问题,本文提出了一种改进的特征点匹配策略。首先,考虑到特征点提取与匹配会受到场景昏暗与对比度太低的影响,对昏暗的场景数据集进行对比度增强和去噪。其次,为了提高特征点匹配的数量及速度,将运动平滑性约束作为去除特征点错误匹配的依据,舍弃旋转不变性和尺度不变性并将图片转换为3×3网格来加速运算。最后,为了提高特征匹配的精度,考虑距离与置信度之间的关系,通过计算特征点邻域内的匹配数量,与设定的阈值进行对比,筛选出正确的特征匹配,之后再进行相机的位姿估计等视觉里程计算,估计出相机的移动路径。通过实验分析,该方法能够提高约72.8%的正确特征点匹配数量,并比原本的匹配时间减少约9%。在对RGB-D数据集和Euroc数据集进行实验后,面对昏暗的数据集,定位精度分别提升约21.20%和63.67%。与其他对比方法相比较,该方法不仅增强了系统的处理速度和鲁棒性,也使平均定位精度有所提升。