Global Motion Parameters Research Articles

Video Global Motion Compensation Based on Affine Inverse Transform Model.

Global motion greatly increases the number of false alarms for object detection in video sequences against dynamic backgrounds. Therefore, before detecting the target in the dynamic background, it is necessary to estimate and compensate the global motion to eliminate the influence of the global motion. In this paper, we use the SURF (speeded up robust features) algorithm combined with the MSAC (M-Estimate Sample Consensus) algorithm to process the video. The global motion of a video sequence is estimated according to the feature point matching pairs of adjacent frames of the video sequence and the global motion parameters of the video sequence under the dynamic background. On this basis, we propose an inverse transformation model of affine transformation, which acts on each adjacent frame of the video sequence in turn. The model compensates the global motion, and outputs a video sequence after global motion compensation from a specific view for object detection. Experimental results show that the algorithm proposed in this paper can accurately perform motion compensation on video sequences containing complex global motion, and the compensated video sequences achieve higher peak signal-to-noise ratio and better visual effects.

TVnet: automated global analysis of tricuspid valve plane motion in CMR long-axis cines with residual neural networks for assessment of right ventricular function

Abstract Funding Acknowledgements Type of funding sources: Foundation. Main funding source(s): Clarendon Fund, John Fell Oxford University Press Research Fund, Oxford BHF Centre of Research Excellence (RE/18/3/34214), Alison Brading Memorial Graduate Scholarship in Medical Science, National Institute for Health Research Oxford Biomedical Research Centre, National Institutes of Health (R01HL144706). Background Right ventricular (RV) function evaluation is an integral part of comprehensive cardiac assessment, including for pulmonary hypertension, congenital heart disease and arrhythmogenic RV cardiomyopathy (ARVC) [1]. It is commonly assessed by measuring tricuspid annular plane systolic excursion (TAPSE) and peak systolic velocity (RV s’) on echocardiography [2]. However, it is highly sensitive to imaging window and small changes in the beam angle, limiting reliability [3]. Cardiovascular magnetic resonance (CMR) is the imaging gold-standard for assessing RV structure and function, and is highly reproducible. CMR can assess tricuspid valve (TV) motion using four-chamber (4Ch) and RV two-chamber (2Ch) cines, with high diagnostic performance when compared against single-plane analysis [4]. However, manual placement of the TV insertion points is highly time-consuming for routine clinical workflows. TVnet, a deep-learning framework for automatically tracking the TV in 4Ch cines [5] has been recently validated, but without the orthogonal plane (RV 2Ch) which is helpful to more reliably characterise TV motion. Purpose We further extend TVnet to automatically track RV 2Ch cines and derive analysis of global TV motion parameters (global TAPSE and RV s’) on par with expert level performance. Methods 74 patients undergoing CMR (1.5T Siemens MR scanner) with 4Ch and RV 2Ch views were retrospectively included in this ethically-approved study. The patients had the following cardiovascular conditions: myocardial infarction (n=43), ARVC (n=28) and Takotsubo cardiomyopathy (n=3). The dual-stage deep-learning pipeline with a residual neural network backbone [5, 6] (Figure 1A) was trained using 69 patient datasets and 15 patients were randomly chosen for testing. The TVnet trained on 4Ch cines [5] was used to automatically annotate the 4Ch cines of the testing set for global analysis comparison. For manual reference, the software Segment [7] was used to manually annotate the TV insertion points in all imaging data (1,865 RV 2Ch images, 375 4Ch images). The global TAPSE and RV s’ were derived as the mean perpendicular motion from the end-diastolic plane from both chamber views (Figure 1B). Results TVnet achieved a fast processing accuracy (<1 second per cine) and successfully tracked the TV insertion points from the RV 2Ch cine with a plane tracking error of 0.08±0.83 mm. The integrated pipeline yielded an excellent clinical-metric agreement with the manual reference (Figure 2) for both global TAPSE (error=0.42±0.68 mm, ICC=0.95) and RV s’ (error=-0.10±0.71 cm/s, ICC=0.85). Conclusion TVnet demonstrated excellent performance in both tracking the TV insertion points in RV 2Ch cines and deriving global TAPSE and RV s’ compared to manual reference. TVnet can eventually provide a complete automatic inline analysis of TV plane motion for a fast, reliable and reproducible assessment of RV function in routine clinical workflows. (A) TVnet pipeline (B) Metric derivationCorrelation and Bland-Altman plots

A Multi-Stage Vessel Tracklet Association Method for Compact High-Frequency Surface Wave Radar

A compact high-frequency surface wave radar, used for target detection, suffers from a low signal-to-noise ratio, low detection probability, a high false alarm rate, and low positioning accuracy; this is due to its low transmit power and the reduced aperture size of the receiving antenna array. When target tracking algorithms are applied to compact high-frequency surface wave radar data, track fragmentation often occurs and a long track may be broken into several track segments (a.k.a. tracklets), which degrade the tracking continuity for a maritime surveillance system. We present a multi-stage vessel tracklet association method, based on bidirectional prediction and optimal assignment, to associate the broken tracklets belonging to the same target, and connect them to form one continuous track in a multi-target tracking scenario. Firstly, two global motion parameters, i.e., the average heading and average speed, were, respectively, extracted from the newly initiated and terminated tracklets as features for a rough tracklet association, then k-means clustering was used to produce the preliminary tracklet pairs. Subsequently, the temporal and spatial constraints on the initiated and terminated tracklets were considered to refine the preliminary tracklet pairs, to obtain the candidate tracklet pairs. Finally, the tracklet association costs were calculated using Doppler velocity, range, and azimuth to determine the similarity between tracklets in the candidate tracklet pairs, and an association cost matrix was obtained. Then an optimal assignment method based on Jonker–Volgenant–Castanon algorithm was applied to the association matrix to achieve optimal tracklet matching by minimizing the total association costs. Tracklet association experiments with both simulated and field data were conducted; experimental results show that, compared with existing track segment association methods, the association accuracy of the proposed method is significantly improved with better tracking continuity.

Translational Motion Compensation for ISAR Images Through a Multicriteria Decision Using Surrogate-Based Optimization

Inverse synthetic aperture radar (ISAR) image is constructed using 2-D spatial distributions of the radar cross section of a target. ISAR data gathered from moving targets might include interphase error that causes a blurry effect in the ISAR image. In this article, an efficient motion compensation (MC) scheme depending on multicriteria decision using surrogate-based optimization (SbO) for minimizing the entropy and maximizing the sharpness of the images is proposed to remove the blur from the images. In order to provide a multicriteria decision, Pareto optimality is exploited to balance two criteria of the entropy and sharpness synchronously. A signal with an interphase error is input to the MC system for determining the global optimal motion parameters of the velocity and acceleration so as to focus on the ISAR image. The proposed scheme is implemented to four simulated ISAR scenarios reported elsewhere through two aircraft models for performance demonstration and comparison with artificial bee colony (ABC), differential evolution (DE), and particle swarm optimization (PSO) implemented in the literature. It is pointed out that the proposed scheme is more successful and efficient in view of the image focusing quality as well as the numerical results such as the motion parameters, the entropy and sharpness, and structural similarity (SSIM) index. The results also show that the SbO outperforms the other methods as the velocity and acceleration increase.

High confidence detection for moving target in aerial video

The moving target detection and tracking in aerial video is a challenge task because of its moving background, smaller target sizes, lower resolution and limited onboard computing resources. In this study, a high confidence detection method based on background compensation and three-frame-difference method is designed, which can detect moving objects in a dynamic background accurately. First, the authors use local feature extraction and matching for image registration and demonstrate that speed-up robust feature key points are suitable for the stabilisation task. Then, they estimate the global camera motion parameters using affine transformation which are obtained by the random sample consensus algorithm. Finally, they detect moving object by three-frame-difference method. As the detection results of the frame-difference method generally exists ‘empty’ and noise, in order to select the two higher-quality differential images to perform the logic AND operation, they add image quality assessment to the three-frame-difference method to obtain more accurate moving objects. Moreover, the edge detection algorithm and morphological processing are integrated together to further boost the overall detecting performance. The extensive empirical evaluations on aerial videos demonstrate that the proposed detector is very promising for the various challenging scenarios.

F177. THALAMIC SUBREGION RESTING STATE CONNECTIVITY IN SCHIZOPHRENIA MEASURED AT 7T

BackgroundThe thalamus, a critical node in which multiple cerebral circuits converge, is organized into multiple subnuclei, classified as either first-order (receiving peripheral sensory input) or higher-order (receiving input primarily from the cortex). Higher-order nuclei are of particular salience in psychotic disorders, as they appear to control cortico-cortical information transmission, possibly through regulation of neuronal synchrony. Substantial evidence has demonstrated abnormalities of thalamo-cortical connectivity in schizophrenia, generally with hyperconnectivity with sensorimotor and temporal cortices and hypoconnectivity with frontal regions. We took advantage of the spatial resolution of 7T (voxels of 3.375 mm3 vs 27 mm3 at 3T) to preliminarily assess resting state connectivity between specific thalamic nuclei and cortical regions in schizophrenia.MethodsResting state fMRI scans were obtained for 14 SCZ patients (mean age 39.5, mean disease duration 18.8 years) and 14 matched controls (smoking, age, sex) using a Phillps 7T imaging system, with GRE EPI (TR/TE/FA=2000/22ms/60º, voxel=2.5mm iso, 54 slices, 7min. Data analysis was carried out with SPM8 / Matlab6. Preprocessing included realignment, slice time correction, co-registration, segmentation, normalization; nuisance removal (CompCor), regression of global mean and motion parameters; spatially smoothing (5mm kernel) and temporal filtering (0.01-0.1Hz). Seed-based analysis was carried out using thalamic sub-regions as described in the Oxford Thalamic Connectivity Atlas (seven regions based on anatomic connectivity rather than histology), and whole brain connectivity maps (z values) to each seed were calculated. Second-level t-tests were performed to examine differential connectivity between SCZ patients and controls (thresholded at a voxel-level of p<.001 and multiple-comparisons corrected at a cluster-level threshold of p<.05). Effect size was estimated with Cohen’s d. The IBASPM116 atlas was used to identify anatomical regions within the significant clusters.ResultsBoth reduced and enhanced functional connectivity between the thalamus and multiple brain regions were observed. Statistically significant differences between scz and controls were detected in 47 regions, with particularly strong differences between scz and control in thalamo-temporal cortex connectivity, consistent with previous results at 3T. The same analysis was performed but with seeds placed in each of the seven thalamic subregions defined by the Oxford thalamic connectivity atlas. Enhanced connectivity was observed between all thalamic sub-regions and the motor cortex. Enhanced connectivity to the temporal cortex was detected in several thalamic sub-regions, but not sub-region 7, which has the highest anatomical connection probability in controls. Reduced functional connectivity in SCZ was detected between thalamic sub-regions 4, 6, and 7, and prefrontal and cingulate cortex.DiscussionOur results provide preliminary evidence of changes in resting state thalamo-cortical connectivity in schizophrenia that are specific to particular thalamic subregions. If confirmed by larger scale studies, identifying altered functional connectivity patterns of specific thalamic subnuclei may provide important clues about the pathogenic process in schizophrenia, with the potential of serving as biomarkers for use in therapeutic development.

Reproducibility of regional- and global left-ventricular strain analyzes using tagging and feature tracking techniques - a cardiac magnetic resonance imaging study in healthy volunteers

Background Techniques for the evaluation of regionaland global left-ventricular wall motion parameters based on strain analyzes are emerging in cardiac magnetic resonance (CMR) imaging. Some of these techniques, such as tagging, require dedicated CMR sequences at the time of the examination. Other approaches are based on post-processing of routine imaging studies such as feature-tracking. Common to all is the need for specialized software solutions. Objective of our study was the evaluation of a tagging and a feature-tracking approach with regard to reproducibility and robustness. We therefore examined a cohort of healthy volunteers under rest conditions and during pharmacological exercise.

A SENSOR AIDED H.264/AVC VIDEO ENCODER FOR AERIAL VIDEO SEQUENCES WITH IN THE LOOP METADATA CORRECTION

Abstract. Unmanned Aerial Vehicles (UAVs) are often employed to collect high resolution images in order to perform image mosaicking and/or 3D reconstruction. Images are usually stored on board and then processed with on-ground desktop software. In such a way the computational load, and hence the power consumption, is moved on ground, leaving on board only the task of storing data. Such an approach is important in the case of small multi-rotorcraft UAVs because of their low endurance due to the short battery life. Images can be stored on board with either still image or video data compression. Still image system are preferred when low frame rates are involved, because video coding systems are based on motion estimation and compensation algorithms which fail when the motion vectors are significantly long and when the overlapping between subsequent frames is very small. In this scenario, UAVs attitude and position metadata from the Inertial Navigation System (INS) can be employed to estimate global motion parameters without video analysis. A low complexity image analysis can be still performed in order to refine the motion field estimated using only the metadata. In this work, we propose to use this refinement step in order to improve the position and attitude estimation produced by the navigation system in order to maximize the encoder performance. Experiments are performed on both simulated and real world video sequences.

Fast Approach to Video Stabilization Based on Hierarchical Estimation of Global Motion with Parallel Computation

In this article, a fast approach of video stabilization is presented based on haerachical estimmation of global motion and multi-thread parallel computation. At first, the structure-texture decomposition is adopted to tackle the negative effect from illumination changes. Then according to pyramid structure of image texture a hierachical model is built to estimate global motion parameters with least square method. Afterwards Gaussian smoothing method is employed to eliminate error accumulation in motion compensation. Meanwhile the multi-thread parallel computation is used to speed up the processing efficiency so as to achieve a real time performance for videos with 25fps.

Improving Video Stabilization Using Multi-Resolution MSER Features

ABSTRACTIn this paper, we investigate the application of multi-resolution maximally stable extremal region (MSER) features for improving the video stabilization performance. MSER features have been used for many computer vision applications like wide baseline stereo, object recognition, video object tracking, and video stabilization with very good results as compared to other features like scale invariant feature transform (SIFT) and Kanade Lucas Tomasi (KLT). However, a limitation of the MSER feature in the stabilization application was observed when the input video frames were severely blurred. The same limitation was also observed when other features like KLT and SIFT were utilized under blurring conditions. In this paper we propose to overcome this drawback for video stabilization application by utilizing MSERs which are extracted and matched in a scale pyramid fashion instead of the MSER features detected and matched on a single image resolution. The duplicate MSERs resulting due to the pyramid style detection are removed followed by MSER feature matching for establishing correspondence between video frames to estimate the global motion parameters. Once the global motion parameters are estimated, the accumulated transformation is smoothed followed by motion compensation to construct the stabilized frame. Comparative analysis with state-of-the-art stabilization methods shows improvement in stabilization performance as well as robustness to blurring degradations. The proposed method can easily be ported to other feature detectors like KLT and SIFT thereby making the proposed method generic to any feature detector.

Digital Image Stabilization Based on Harmony Filter

A digital image stabilization algorithm based on a harmony filter is presented in this paper. The corner points are extracted from the reference image. A new motion estimation method based on diamond search (DS) and partial distortion elimination (PDE) algorithm is proposed in the feature block matching. The global motion parameters are obtained based on the affine transformation model and the least square solution. Then a new filter algorithm named harmony filter is adopted to smooth the global motion by separating the active scanning movement from random jitter of camera. Finally, the original jitter sequences are compensated by the correction vectors. Experimental results show that our method can eliminate the high frequency tremble, keep active motion of camera and realize real-time image stabilization.

Moving Objects Detection Based on the Precise Background Compensation Under Dynamic Scene

In order to detect the moving object under dynamic scenes accurately, this paper proposes a moving object detection method which is based on the precise background compensation. First, the SURF (Speeded-Up Robust Features) algorithm is used to extract feature points, and the BBF(Best-Bin-First) search algorithm is adopted to match feature points, in addition the reverse constraint strategy is employed to remove the mismatching points. To enhance the accuracy of the background compensation, a dynamic threshold is set to remove the target feature points influence for the global motion parameters. At last, a combination of interval three-frame- -differencing and morphological method is used to detect the moving objects. Experimental results show that this method has good performance on multiple moving targets detection.

The Impact of the Width of the Tracking Area on Speckle Tracking Parameters—Methodological Aspects of Deformation Imaging

The aim of this study was to analyze the impact of the tracking area width on myocardial wall motion and deformation parameters in 2D speckle tracking. Standardized apical views were acquired in 30 healthy subjects and 15 patients with left ventricular systolic dysfunction using 2D echocardiography. Longitudinal peak systolic strain (PSS), longitudinal peak systolic strain rate (PSSR), postsystolic index (PSI), peak longitudinal (PLD), and peak transverse displacement (PTD) were determined by 2D speckle tracking to analyze the impact of the tracking area width on global and regional myocardial wall motion and deformation parameters. The dimension of the tracking area has a significant impact on all parameters. With increasing width of the tracking area higher values of PSS, PSSR, PSI, and lower values of PLD and PTD were determined. With increasing width of the tracking area a significant number of segments were not tracked. In summary, especially global PSS is significantly influenced by the width of the tracking area. The strain values determined by 2D speckle tracking are significantly influenced by the tracking area width. The tracking of the subendocardial layers only results in lower global strain values than tracking the complete ventricular wall using the medium or wide tracking area widths. The tracking quality in the far field is worse if the tracking area is too wide. The present data show that standard and reference values of deformation imaging should include detailed information about the position and the width of the tracking area.

Normal values of regional and global myocardial wall motion in young and elderly individuals using navigator gated tissue phase mapping

The purpose of this study was to evaluate normal values for regional and global myocardial wall motion parameters in young and elderly individuals, as detected by navigator gated high temporal resolution tissue phase mapping. Radial, longitudinal and circumferential ventricular wall motion, as well as ventricular torsion and longitudinal strain rates, were assessed in two age groups of volunteers, 23 ± 3 (n = 14) and 66 ± 7 years old (n = 9), respectively. All subjects were healthy, non-smokers without known cardiac disease. An increased global left ventricular (LV) torsion rate (peak systolic torsion rate 20.6 ± 2.0 versus 14.5 ± 1.0°/s/cm, peak diastolic torsion rate -25.2 ± 1.8 versus -14.1 ± 1.3°/s/cm) and a decrease in longitudinal LV motion (peak systolic values at mid-ventricle 5.9 ± 0.5 versus 8.5 ± 0.8 cm/s, peak diastolic values -10.7 ± 0.7 versus -15.2 ± 0.9 cm/s) in the older age group were the most prominent findings. Lower peak diastolic radial velocities with a longer time-to-peak values, most pronounced at the apex, are consistent with reduced diastolic function with ageing. Lower peak clockwise and counter-clockwise velocities at all LV levels revealed limitations in resting LV rotational motions in the older group. Significant changes in the undulating pattern of the rotational motions of the left ventricle were also observed. The results demonstrate distinct changes in regional and global myocardial wall motion in elderly individuals. Increased LV torsion rate and reduced LV longitudinal motion were particularly prominent in the older group. These parameters may have a role in the assessment of global LV contractility and help differentiate age-related changes from cardiac disease.

Feature point classification based global motion estimation for video stabilization

The performance of video stabilization is dependent on the accuracy of global motion estimation between two successive frames. In this paper, we propose a novel method to estimate the global motion accurately using the classified background (BG) feature points (FPs). In the proposed method, global motion estimation and FP classification are jointly performed using both the FP correspondences and the global motion parameters of the previous frame. The experimental results show that video stabilization using the proposed method outperforms the conventional stabilization methods, especially when the moving foreground (FG) objects occupy a large part of the image.

Fluid–structure interaction of an aortic heart valve prosthesis driven by an animated anatomic left ventricle

We develop a novel large-scale kinematic model for animating the left ventricle (LV) wall and use this model to drive the fluid–structure interaction (FSI) between the ensuing blood flow and a mechanical heart valve prosthesis implanted in the aortic position of an anatomic LV/aorta configuration. The kinematic model is of lumped type and employs a cell-based, FitzHugh–Nagumo framework to simulate the motion of the LV wall in response to an excitation wavefront propagating along the heart wall. The emerging large-scale LV wall motion exhibits complex contractile mechanisms that include contraction (twist) and expansion (untwist). The kinematic model is shown to yield global LV motion parameters that are well within the physiologic range throughout the cardiac cycle. The FSI between the leaflets of the mechanical heart valve and the blood flow driven by the dynamic LV wall motion and mitral inflow is simulated using the curvilinear immersed boundary (CURVIB) method (Ge and Sotiropoulos, 2007; Borazjani et al., 2008) [1,2] implemented in conjunction with a domain decomposition approach. The computed results show that the simulated flow patterns are in good qualitative agreement with in vivo observations. The simulations also reveal complex kinematics of the valve leaflets, thus, underscoring the need for patient-specific simulations of heart valve prosthesis and other cardiac devices.

Video stabilization using maximally stable extremal region features

Video stabilization is an important technique in present day digital cameras as most of the cameras are hand-held, mounted on moving platforms or subjected to atmospheric vibrations. In this paper we propose a novel video stabilization scheme based on estimating the camera motion using maximally stable extremal region features. These features traditionally used in wide baseline stereo problems were never explored for video stabilization purposes. Through our extensive experiments show we how some properties of these region features are suitable for the stabilization task. After estimating the global camera motion parameters using these region features, we smooth the motion parameters using a gaussian filter to retain the desired motion. Finally, motion compensation is carried out to obtain a stabilized video sequence. A number of examples on real and synthetic videos demonstrate the effectiveness of our proposed approach. We compare our results to existing techniques and show how our proposed approach compares favorably to them. Interframe Transformation Fidelity is used for objective evaluation of our proposed approach.

A Low-Complexity Image Registration Algorithm for Global Motion Estimation

An important recent application of image registration is the estimation of global motion parameters for object-based video coding. However, the main disadvantage of standard approaches to global motion estimation (GME) is the increased computational complexity with the higher degree of motion models when compared to block-based local motion estimation approaches. In this paper, we propose a new low complexity GME algorithm. In our proposed algorithm, full-precision images are replaced with 1 bit-per-pixel images which allows many of the arithmetic operations in the standard GME approach to be replaced with logic operations. Experimental results show that our proposed algorithm achieves the same registration accuracy as the standard GME approach but with significantly reduced computational complexity. Our results also demonstrate the superior performance of the proposed algorithm when compared with previously proposed low-complexity GME approaches.

Vision Stability of Four-legged Robot Based on the Feedback of Motion Parameters

The motion parameters of the legs of four-legged robot are collected and sent to the robot vision system, which can solve the stabilization problems of the software-based algorithms in searching for the global motion parameters. The motion jitter parameters of the four legs are extracted combined with the software stabilization methods, which work as the basis for solving global motion parameters and provide guidance for the parameters of the solution. The simulation tools of MATLAB SimMechanics toolkits are utilized to analysis stability. Compared with other related algorithms, the results indicate that the proposed algorithm for four-legged robot movement in real time is better and more accurate.

基于特征匹配的电子稳像优化技术

Electronic image stabilization still exists some problems,such as high time-consuming,low accuracy,high eror matching probability and so on.The paper takes appropriate measures to solove these problems from two aspects: feature points extraction and matching.Firstly,the FAST algorithm is adpoted to extracte the feature points,and positional precision of the feature points is improved to the level of sub-pixel.Then the RANSAC algorithm is used to eliminate the error matched points,avoid the interference of relative movement,and the global motion parameters calculated is more accurate.Experimental results show that a more higher precision and faster speed is obtained,which can also be applied for the complex shaking video containing translation,rotation shake and relative movement.