基于平流矢量场聚类的图像复杂空间映射配准

复杂形变下的图像配准在用几何约束模型逼近时存在固有误差,造成配准细节失真.提出一种根据计算流体动力学获取图像像素空间复杂映射的方法,用于局部形变下的图像配准、拼接等任务.利用二维空间网格上的特征点无监督聚类得到图像平流输运矢量场,并将鲁棒估计器嵌入最小二乘迭代以缓解特征点匹配困难,最后依据散度消除映射流在奇异点处的输出...     

基于Legendre正交矩的模糊形变图像的配准方法

针对同时含有模糊和几何形变的图像,本文提出一种新的基于Legendre正交矩模糊和几何混合不变量的图像配准方法.该方法首先利用Harris- Laplace算子检测出图像的特征点,然后构造Legendre矩混合不变量,并将其作为特征点的描述子获取特征点的对应关系,接着通过该对应关系估计图像间的形变参数,最后利用插值方法...     

一种抗信息丢失的稳像系统

针对二维电子稳像补偿全局运动矢量后会出现大量 的空白区域,提出了一种不需要采用单应性模型明确估计全局运动矢量的快速平滑特征轨迹 的稳像算法。首先,采用改进的快速鲁棒特征(SURF)提取图像局部特征点;然后,利用空间 运动的 一致性连接帧与帧之间匹配的特征点得到特征点轨迹;最后,建立同时考虑特征轨迹的平滑 度和视频质量退化程度的目标函 数平滑特征点轨迹,得到稳定的视频。实验结果表明,用本文方法稳定的视频比Matsushita 方法处理后的视频丢失的区域减小 了30%左右,更满足人眼感官需求,减轻了费时的运动修复任务;同时 消除了运动估计中帧间匹配的累积误差,对前景存在较大局部运动的视频仍能表现较好的稳 像效果。     

基于序列多尺度特征融合表示的层级舞蹈动作姿态估计方法

人体姿态估计是计算机视觉研究领域的热点研究问题之一,但其在传统民间舞蹈动作姿态估计方面的应用研究尚处于起步阶段.由于舞蹈图像中人体动作复杂多变、舞蹈动作连贯性强、舞蹈者存在严重遮挡不易检测等特点,传统人体姿态估计方法难以准确估计舞蹈者的动作变化,导致舞蹈动作姿态估计准确率较低.针对此问题,本文提出一种基于序列多尺度特征融合表示的层级舞蹈动作姿态估计方法,该方法针对舞蹈动作骨骼关节点尺度变化剧烈的问题,构建基于序列多尺度特征融合表示的关节点估计模型.并且,针对舞蹈姿态形变较大,遮挡严重的问题,设计基于关节点几何关系的层级姿态估计模型,提高舞蹈动作姿态估计的效果.实验结果表明,本文方法在标准人体姿态估计数据集及自建舞蹈数据集上取得较好的姿态估计结果.     

计及偏移量的非线性光学显微成像误差校正方法

针对因非线性光学显微成像以客观像素特征为驱动源，一旦出现特征缺失，推断过程很容易形成误差，导致的光学显微图像失真现象严重、清晰度低问题，提出计及偏移量的非线性光学显微成像误差校正方法。利用数据驱动法全面、快速以及敏感地捕捉光学数据，划分光学显微图像的边缘和非边缘区域，设定标准滑动窗口，计算不同区域内像素点在该窗口内的像素灰度值，根据灰度值判定边缘点和非边缘点的误差形成概率。在此基础上，将误差校正看做一种角度或相位偏离补偿问题，设定偏离中心，计算误差概率较大的图像区域内各节点与中心间角度和相位偏移量，根据偏移量给出相应正向和负向补偿，完成有效误差校正。实验数据证明：所提方法误差校正精准度高，校正后成像失真、细节丢失以及分辨率低问题被解决，误差点的分布离散程度降低，算法整体实用性较强。     

维纳滤波最优权修正导向矢量的SAR-GMTI动目标径向速度估计方法

针对通道幅相误差和图像配准误差等非理想因素导致动目标径向速度估计性能下降问题,本文提出利用维纳滤波最优权修正导向矢量的动目标径向速度估计方法.该方法利用抑制杂波的维纳滤波最优权矢量对动目标理想导向矢量加权处理获得修正导向矢量,并采用匹配滤波算法估计动目标径向速度.仿真数据和某机载多通道SAR-GMTI实测数据处理表明,所提方法对通道幅相误差和图像配准误差稳健,在图像相邻像素存在较大相关性时仍可获得较高的动目标径向速度估计精度.     

基于误差阈值和最小二乘图像拼接关系矩阵的实现

为了获得图像最佳拼接效果,对相邻图像间变换矩阵的求解问题进行研究,提出了一种全稳健的图像拼接算法.此算法采用SIFT进行特征点提取,初步得到了特征点匹配的伪匹配集合,并运用稳健的误差阈值法将伪匹配点集合划分为内点和外点,在内点域上运用误差的最小二乘优化算法精确地估计出了图像间的点变换关系,最后采用颜色插值对交接处进行颜...     

基于动态特征剔除的图像与点云融合的机器人位姿估计方法

针对动态物体影响传感器进行机器人位姿估计的问题,本文提出了一种基于动态特征剔除点云与图像融合的位姿估计方法。首先,YOLOv4和PointRCNN分别被用于识别图像和点云中的潜在运动目标并提取候选框。其次,在视觉定位方面,双目视觉与稀疏光流被用于路标点的构建与追踪,并根据候选框剔除动态特征点,随后构建重投影误差函数,通过基于RANSAC剔除的非线性优化方法求解相机位姿;在激光定位方面,提取前后帧的直线与平面特征点,并根据候选框进行筛选,基于特征点到直线或平面的距离构建误差函数,进而求解激光雷达位姿。为使系统不再局限于单一传感器的使用环境限制,通过自适应加权方法,有效融合了两种位姿结果。最后,通过KITTI数据集和动态场景采集的数据进行定量实验对比,验证了剔除动态特征后的位姿估计的精确性以及融合算法的有效性。     

基于混合遗传算法的对极几何估计

在未定标系统中,对极几何约束给出了图像间的全部信息,成为解决许多视觉问题的关键环节.本文提出了一种基于混合遗传算法的对极几何估计方法,它利用每个基因代表一个匹配点,每条染色体作为对极几何估计最小子集.此方法在很大程度上减小了出格点对估计过程的影响,能够较好地汇聚到全局(或近似全局)最优解.模拟数据和真实图像的实验结果都表明,本文所给出的方法能够有效地检测和删除错定位和误匹配点,提高了对极几何估计的鲁棒性和精度.     

粗DEM辅助的广域PS-InSAR数据预处理方法及应用

PS-InSAR技术是一种高精度的地表形变探测方法,小区域PS-InSAR处理的研究较为深入,但处理方法并不适用广域的形变探测和数据处理方法。本文针对卫星实时轨道精度差的问题,首先提出利用辅助DEM进行斜距误差和轨道系统误差校正提升差分干涉相位反演精度的方法;其次,针对广域图像配准误差的空变性,提出了一种由粗到精的层级配准方法,解决了配准误差空变对PS-InSAR永久散射体选取和图像相干性的影响;最后,通过对形变观测结果的地理编码结合加权处理,实现对超广域观测图像的拼接。利用仿真数据验证了粗DEM对系统误差校正的有效性,并进一步通过Sentinel-1A的2000多景雷达影像对云南省全境39.4万平方千米的覆盖区域进行了处理,结果表明了本文方法对系统误差校正和对广域形变探测处理的有效性。     

Probabilistic inference of multijoint movements, skeletal parameters and marker attachments from diverse motion capture data

This paper describes a comprehensive solution to the problem of reconstructing the multijoint movement trajectories of the human body from diverse motion capture data. The problem is formulated in a probabilistic framework so as to handle multiple and unavoidable sources of uncertainty: sensor noise, soft tissue deformation and marker slip, inaccurate marker placement and limb measurement, and missing data due to occlusions. All unknown quantities are treated as state variables even though some of them are constant. In this way, state estimation and system identification can be performed simultaneously, obtaining not only the most likely values but also the confidence intervals of the joint angles, skeletal parameters, and marker positions and orientations relative to the limb segments. The inference method is a Gauss-Newton generalization of the extended Kalman filter. It is adapted to the kinematic domain by expressing spatial rotations via quaternions and computing the sensor residuals and their Jacobians analytically. The ultimate goal of this project is to provide a reliable data analysis tool used in practice. The software implementation is available online.     

Robust statistical fusion of image labels

Image labeling and parcellation (i.e., assigning structure to a collection of voxels) are critical tasks for the assessment of volumetric and morphometric features in medical imaging data. The process of image labeling is inherently error prone as images are corrupted by noise and artifacts. Even expert interpretations are subject to subjectivity and the precision of the individual raters. Hence, all labels must be considered imperfect with some degree of inherent variability. One may seek multiple independent assessments to both reduce this variability and quantify the degree of uncertainty. Existing techniques have exploited maximum a posteriori statistics to combine data from multiple raters and simultaneously estimate rater reliabilities. Although quite successful, wide-scale application has been hampered by unstable estimation with practical datasets, for example, with label sets with small or thin objects to be labeled or with partial or limited datasets. As well, these approaches have required each rater to generate a complete dataset, which is often impossible given both human foibles and the typical turnover rate of raters in a research or clinical environment. Herein, we propose a robust approach to improve estimation performance with small anatomical structures, allow for missing data, account for repeated label sets, and utilize training/catch trial data. With this approach, numerous raters can label small, overlapping portions of a large dataset, and rater heterogeneity can be robustly controlled while simultaneously estimating a single, reliable label set and characterizing uncertainty. The proposed approach enables many individuals to collaborate in the construction of large datasets for labeling tasks (e.g., human parallel processing) and reduces the otherwise detrimental impact of rater unavailability.     

System parameter estimation with input/output noisy data andmissing measurements

An investigation is undertaken to examine the parameter estimation problem of linear systems when some of the measurements are unavailable (i.e., missing data) and the probability of occurrence of missing data is unknown a priori. The system input and output data are also assumed to be corrupted by measurement noise, and the knowledge of the noise distribution is unknown. Under the unknown noise distribution and missing measurements, a consistent parameter estimation algorithm [which is based on an l_p norm iterative estimation algorithm-iteratively reweighted least squares (IRLS)] is proposed to estimate the system parameters. We show that if the probability of missing measurement is less than one half, the parameter estimates via the proposed estimation algorithm will converge to the true parameters as the number of data tends to infinity. Finally, several simulation results are presented to illustrate the performance of the proposed l _p norm iterative estimation algorithm. Simulation results indicate that under input/output missing data and noise environment, the proposed parameter estimation algorithm is an efficient approach toward the system parameter estimation problem     

Autoregressive-Model-Based Missing Value Estimation for DNA Microarray Time Series Data

Missing value estimation is important in DNA microarray data analysis. A number of algorithms have been developed to solve this problem, but they have several limitations. Most existing algorithms are not able to deal with the situation where a particular time point (column) of the data is missing entirely. In this paper, we present an autoregressive-model-based missing value estimation method (ARLSimpute) that takes into account the dynamic property of microarray temporal data and the local similarity structures in the data. ARLSimpute is especially effective for the situation where a particular time point contains many missing values or where the entire time point is missing. Experiment results suggest that our proposed algorithm is an accurate missing value estimator in comparison with other imputation methods on simulated as well as real microarray time series datasets.     

A Spatial Correlation Based Adaptive Missing Data Estimation Algorithm in Wireless Sensor Networks

In wireless sensor networks, the missing of sensor data is inevitable due to the inherent characteristic of wireless sensor networks, and it causes many difficulties in various applications. To solve the problem, the missing data should be estimated as accurately as possible. In this paper, an adaptive missing data estimation algorithm is proposed based on the spatial correlation of sensor data. It adopts multiple regression model to estimate the missing data with the data of multiple neighbor nodes jointly rather than independently, which makes its estimation performance stable and reliable. In addition, for different missing data, it can adjust the estimation equation adaptively to capture the dynamic correlation of sensor data. Thereby, it can estimate the missing data more accurately. Further more, it can also give the confidence interval of each missing data for the given confidence level, which is helpful greatly for users. Experimental results on two real-world datasets show that the proposed algorithm can estimate the missing data accurately.     

Sampled-data filtering framework for cardiac motion recovery: optimal estimation of continuous dynamics from discrete measurements

Quantitative and noninvasive estimation of cardiac kinematics has significant physiological and clinical implications. In this paper, a sampled-data filtering framework is presented for the recovery of cardiac motion and deformation functions from periodic medical image sequences. Cardiac dynamics is a continuously evolving physical/physiological process, whereas the imaging data can provide only sampled measurements at discrete time instants. Given such a hybrid paradigm, stochastic multiframe filtering frameworks are constructed to couple the continuous dynamics with the discrete measurements, and to coordinately deal with the parameter uncertainty of the biomechanical constraining model and the noisy nature of the imaging data. The state estimates are predicted according to the continuous-time biomechanically constructed state equation between observation time points, and then updated with the new imaging-derived measurements at discrete time instants, yielding physically more meaningful and more accurate estimation results. Both continuous-discrete Kalman filter and sampled-data Hinfinity filter are applied for motion recovery. While Kalman filter is the optimal estimator under Gaussian noises, the Hinfinity scheme can give robust estimation results when the types and levels of model uncertainties and data disturbances are not available a priori. The strategies are validated through synthetic data experiments to illustrate their advantages and on canine MR phase contrast images and human MR tagging data to show their clinical potential.     

基于EM算法的极大似然分布式量化估计融合新方法

该文针对水下目标探测中的多传感器分布式量化估计融合问题,建立了分布式量化估计融合模型,在考虑信道噪声且其统计特性不完全已知条件下,充分利用EM算法在观测数据缺失时参数估计的优越性,提出了一种基于期望极大化(EM)算法的极大似然分布式量化估计融合新方法。该方法将未知的水声信道噪声参数以及局部量化器量化概率建模为EM算法中二元高斯混合模型参数,利用极大似然估计方法的估计不变性得到目标参数的估计融合结果。仿真实验表明:该方法在局部传感器观测样本数目大于5000和信噪比大于6 dB时与已有理想信道条件下的估计方法性能相当,该方法为水下目标探测中分布式量化估计融合系统的工程实现提供了理论依据。     

S-transformation based integrated approach for spectrum estimation,storage, and sensing in cognitive radio

Cognitive Radio (CR) uses the principle of dynamic spectrum allocation to improve the utilization of spectrum bands. The estimation of missing data is essential for maintaining an uninterrupted quality of service in the CR. However, the existing methods are not suitable for interpolating missing data in high frequency signals. The storage of spectrum occupancy information is crucial for learning the spectrum usage and prediction. The existing techniques for wideband spectrum sensing suffer from poor edge detection capabilities. This paper proposes an S-Transformation (ST) based approach to solve these problems. For missing samples, the proposed method improves the accuracy of estimation. The ST can also be used to store the spectrum occupancy information. The simulation results show that the proposed scheme outperforms others by improving the accuracy of edge detection. Further, the simple implementation of the ST in the frequency domain is an advantage for the real time application.     

Estimation Method Based on Deep Neural Network for Consecutively Missing Sensor Data

The phenomenon of missing sensor data is very common in wireless sensor networks (WSN). It has a dramatic effect on the usability, stability and efficiency of the WSN-based applications. There exist many methods for the missing sensor data estimation. However, the accurate and efficient consequent estimation of missing sensor data remains a challenging problem. To solve this problem, we propose a new method named consecutive sensor data deep neural network (CSDNN). In this method, firstly, we analyze the correlation coefficients among different types of sensor data and choose a certain number of nearest neighbors of the target sensor nodes. Secondly, to estimate a certain type of sensor data from a target sensor node, we utilize the different types of sensor data that are from the same target sensor node and have strong correlation with the missing ones, and the same type of sensor data from the aforementioned nearest neighbors. We treat these data as the input of the deep neural networks (DNN). Thirdly, we construct the DNN model, discuss the optimized DNN structure for the missing data problem, and test the accuracy of CSDNN for different types of environmental sensor data. The results show that the CSDNN method allows to accurately estimate the consecutively missing sensor data.     

缺少观测数据下信号谱分析

提出了一种处理时间序列中出现数据丢失时的信号谱估计的方法。这时观测所得到的,不再是连续等间隔的时间序列,而是多个数据段,所要进行的即是对这些分段数据的自回归模型的估计。该方法基于标准Burg谱估计算法提出,算法可以建立一个同时适用于各个分段数据的统一的信号模型。在仿真部分的结果显示,与直接使用均值方法进行谱估计相比较,分段Burg算法偏差更小,谱估计更精确。