Motion Analysis Algorithm Research Articles

Underwater Doppler-bearing maneuvering target motion analysis based on joint estimated adaptive unscented Kalman filter

Noncooperative maneuvering target motion analysis is one of the challenging tasks in the field of underwater target localization and tracking for passive sonar. Underwater noncooperative targets often perform various maneuvers, and the targets are commonly modeled as a combination of constant-velocity models and coordinate-turn models with unknown turning rates. Traditional algorithms for Doppler-bearing target motion analysis are incapable of processing noncooperative maneuvering targets because the algorithms rely on a priori information of the turning rate and the center frequency. To address these shortcomings, this paper proposes the joint estimated adaptive unscented Kalman filter (JE-AUKF) algorithm. The JE-AUKF places the center frequency and turning rate into the state vector and constructs a time-varying state model that self-adapts to a maneuvering target. The JE-AUKF also introduces a time-varying fading factor into the process noise covariance matrix to improve the tracking performance. Simulations and sea trials are conducted to compare the performance of the JE-AUKF with the iterative unscented Kalman filter, the interacting multiple model-unscented Kalman filter, the interacting multiple model-iterative unscented Kalman filter, and the interacting multiple model-joint estimated unscented Kalman filter. The result shows that the JE-AUKF achieves better tracking performance for noncooperative maneuvering targets.

Passive ranging of a moving target in the direct-arrival zone in deep sea using a single vector hydrophone.

The vector hydrophone covers more comprehensive sound field information over the sound pressure hydrophone. The passive target ranging method based on the shallow-located unmanned platform equipped with vector hydrophones is explored based on the measured surface ship data acquired in the deep-sea area in December 2021. First, a bearings-only target motion analysis (TMA) algorithm is proposed, determining the motion state of a moving target (e.g., azimuth angle, abeam time, heading angle, and the ratio of velocity to initial distance) in accordance with its horizontal bearing time recording (BTR) data. Subsequently, the loss function is built following the situation information and the average complex acoustic intensity to determine the real-time grazing angle of the target. Last, the real-time range of the target is determined in accordance with the situation information and the grazing angle. As revealed by the comparison of the calculated value of the sea trial data with the GPS trajectory, the average distance error of the target reaches 11.6%, the root mean square error (RMSE) of the grazing angle is 1.99°, the RMSE of the velocity is 1.9 kn, and the RMSE of the abeam time reaches 51.4 s.

Motion-region annotation for complex videos via label propagation across occluders

Motion cue is pivotal in moving object analysis, which is the root for motion segmentation and detection. These preprocessing tasks are building blocks for several applications such as recognition, matching and estimation. To devise a robust algorithm for motion analysis, it is imperative to have a comprehensive dataset to evaluate an algorithm’s performance. The main limitation in making these kind of datasets is the creation of ground-truth annotation of motion, as each moving object might span over multiple frames with changes in size, illumination and angle of view. Besides the optical changes, the object can undergo occlusion by static or moving occluders. The challenge increases when the video is captured by a moving camera. In this paper, we tackle the task of providing ground-truth annotation on motion regions in videos captured from a moving camera. With minimal manual annotation of an object mask, we are able to propagate the label mask in all the frames. Object label correction based on static and moving occluder is also performed by applying occluder mask tracking for a given depth ordering. A motion annotation dataset is also proposed to evaluate algorithm performance. The results show that our cascaded-naive approach provides successful results. All the resources of the annotation tool are publicly available at http://dixie.udg.edu/anntool/.

Quantitative downhill skiing technique analysis according to ski instruction curricula: A proof-of-concept study applying principal component analysis on wearable sensor data.

Downhill skiing technique represents the complex coordinative movement patterns needed to control skiing motion. While scientific understanding of skiing technique is still incomplete, not least due to challenges in objectively measuring it, practitioners such as ski instructors have developed sophisticated and comprehensive descriptions of skiing technique. The current paper describes a 3-step proof-of-concept study introducing a technology platform for quantifying skiing technique that utilizes the practitioners’ expert knowledge. The approach utilizes an inertial measurement unit system (Xsens™) and presents a motion analysis algorithm based on the Principal Movement (PM) concept. In step 1, certified ski instructors skied specified technique elements according to technique variations described in ski instruction curricula. The obtained data was used to establish a PM-coordinate system for skiing movements. In step 2, the techniques parallel and carving turns were compared. Step 3 presents a case study where the technique analysis methodology is applied to advise an individual skier on potential technique improvements. All objectives of the study were met, proving the suitability of the proposed technology for scientific and applied technique evaluations of downhill skiing. The underlying conceptual approach - utilizing expert knowledge and skills to generate tailored variability in motion data (step 1) that then dominate the orientation of the PMs, which, in turn, can serve as measures for technique elements of interest - could be applied in many other sports or for other applications in human movement analyses.

3-D Target Localization and Motion Analysis Based on Doppler Shifted Frequencies

This article proposes two algorithms for the localization or motion analysis of a moving target, by using a number of stationed sensors observing the frequency of the emitted target signal. This is a challenging problem due to the complicated non-linear relation between the target location parameters and the observations. The first algorithm is closed-form through algebraic evaluation that is computationally efficient. The second is derived from semidefinite programming by relaxationthat is robust against noise. The situations of having target frequency known but erroneous and completely unknown are investigated, as well as the presence of sensor position errors. Sequential algorithms for motion analysis are proposed in addition to the two for reducing latency and complexity. The algorithms are analyzed and their performance is able to achieve the CRLB accuracy under Gaussian noise.

Data-Driven Classification of Human Movements in Virtual Reality-Based Serious Games: Preclinical Rehabilitation Study in Citizen Science.

BackgroundSustained engagement is essential for the success of telerehabilitation programs. However, patients’ lack of motivation and adherence could undermine these goals. To overcome this challenge, physical exercises have often been gamified. Building on the advantages of serious games, we propose a citizen science–based approach in which patients perform scientific tasks by using interactive interfaces and help advance scientific causes of their choice. This approach capitalizes on human intellect and benevolence while promoting learning. To further enhance engagement, we propose performing citizen science activities in immersive media, such as virtual reality (VR).ObjectiveThis study aims to present a novel methodology to facilitate the remote identification and classification of human movements for the automatic assessment of motor performance in telerehabilitation. The data-driven approach is presented in the context of a citizen science software dedicated to bimanual training in VR. Specifically, users interact with the interface and make contributions to an environmental citizen science project while moving both arms in concert.MethodsIn all, 9 healthy individuals interacted with the citizen science software by using a commercial VR gaming device. The software included a calibration phase to evaluate the users’ range of motion along the 3 anatomical planes of motion and to adapt the sensitivity of the software’s response to their movements. During calibration, the time series of the users’ movements were recorded by the sensors embedded in the device. We performed principal component analysis to identify salient features of movements and then applied a bagged trees ensemble classifier to classify the movements.ResultsThe classification achieved high performance, reaching 99.9% accuracy. Among the movements, elbow flexion was the most accurately classified movement (99.2%), and horizontal shoulder abduction to the right side of the body was the most misclassified movement (98.8%).ConclusionsCoordinated bimanual movements in VR can be classified with high accuracy. Our findings lay the foundation for the development of motion analysis algorithms in VR-mediated telerehabilitation.

CONFIDENCE LEVEL OF A MOTION FEEDBACK SYSTEM FOR ANALYZING EXERCISE TRAINING EFFICACY

The increase in aged population is a global trend. Inculcating healthy behaviors such as regular exercises in the elderly has a significant impact on the financial and medical burden globally. Moreover, air pollution and the outbreak of the coronavirus disease 19 (COVID-19) pose a serious threat to public health. In order to improve the health conditions of the population, this study developed a motion feedback system named MoveV that can be used for several indoor training exercises. This system provides instant motion feedback by synchronizing exercise training videos on the website using a motion analysis algorithm that is applicable on smartphones, and a cloud database platform is used to record health behaviors. Feature extraction is performed based on force intensity, motion velocity, and exercise direction. The resultant accuracy of the motion feedback system was tested by a motion science expert and presented as the confidence level. For perfect movement, a confidence level of up to 90.5% was achieved, indicating that the MoveV system was able to record users’ exercise frequency and distinguish whether the user was performing well in the exercise movements. The proposed system is convenient and does not incur additional expenditure by purchasing any new device. Furthermore, it provides visual and voice feedback, companionship, and exercise motivation to the users, all of which are important factors when using online exercise platforms.

An Efficient Dynamic Regulated Fuzzy Neural Network for Human Motion Retrieval and Analysis

Human motion retrieval and analysis is a useful means of activity recognition to 3D human bodies. An efficient method is proposed to estimate human motion by using symmetric joint points and limb features of various limb parts based on regression task. We primarily obtain the 3D coordinates of symmetric joint points based on the located waist and hip points. By introducing three critical feature points on torso and symmetric joint points’ matching on motion video sequences, the 3D coordinates of symmetric joint points and its asymmetric limb features will not be affected by shading and interference of limb on different postures. With the asymmetric limb features of various human parts, a dynamic regulated Fuzzy neural network (DRFNN) is proposed to estimate human motion for different asymmetric postures using learning algorithm of network parameters and weights. Finally, human sequential actions corresponding to different asymmetric postures are presented according to the best retrieval results by DRFNN based on 3D human action database. Experiments show that compared with the traditional adaptive self-organizing fuzzy neural network (SOFNN) model, the proposed algorithm has higher estimation accuracy and better presentation results compared with the existing human motion analysis algorithms.

A Low-Cost Telerehabilitation Paradigm for Bimanual Training

The COVID-19 pandemic has transformed daily life, as individuals must reduce contacts among each other to prevent the spread of the disease. Consequently, patients’ access to outpatient rehabilitation care was curtailed and their prospect for recovery has been compromised. Telerehabilitation has the potential to provide these patients with equally efficacious therapy in their homes. Using commercial gaming devices with embedded motion sensors, data on movement can be collected toward objective assessment of motor performance, followed by training and documentation of progress. Herein, we present a low-cost telerehabilitation system dedicated to bimanual exercise, wherein the healthy arm drives movements of the affected arm. In the proposed setting, a patient manipulates a dowel embedded with a sensor in front of a Microsoft Kinect sensor. In order to provide an engaging environment for the exercise, the dowel is interfaced with a personal computer, to serve as a controller. The patient’s gestures are translated into actions in a custom-made citizen-science project. Along with the system, we introduce an algorithm for classification of the bimanual movements, whose inner workings are detailed in terms of the procedures performed for dimensionality reduction, feature extraction, and movement classification. We demonstrate the feasibility of our system on eight healthy subjects, offering support to the validity of the algorithm. These preliminary findings set forth the development of precise motion analysis algorithms in affordable home-based rehabilitation.

Analysis of swing tempo, swing rhythm, and functional swing plane slope in golf with a wearable inertial measurement unit sensor

Swing tempo, rhythm and swing plane are shown to be important in maintaining the performance. However, nearly all studies utilized optical motion capture system for the planar behavior of golf swings and the movement of the club. The primary aim of this study was to develop inertial measurement unit sensor-based swing motion analysis algorithm, and validate against an optical motion camera system by comparing the estimated clubhead trajectories during the golf swing. Then, the tempo, rhythm and functional swing plane were investigated using a validated wearable inertial sensor. Fourteen male golfers performed repeated swings for three clubs (driver, 7-iron, and wedge) and at three distances (30 m, 50 m, and 70 m using the wedge). The swing tempo of all the participants was consistent across different clubs. The swing rhythm tends to decrease for club types with less carrying distance. The functional swing plane slope tends to decrease for club types with greater carrying distance. Our study demonstrated a potential application of a wearable inertial measurement unit system for analyzing golf performance parameters.

Human motion analysis in medical robotics via high-dimensional inverse reinforcement learning

This work develops a novel high-dimensional inverse reinforcement learning (IRL) algorithm for human motion analysis in medical, clinical, and robotics applications. The method is based on the assumption that a surgical robot operators’ skill or a patient’s motor skill is encoded into the innate reward function during motion planning and recovered by an IRL algorithm from motion demonstrations. This class of applications is characterized by high-dimensional sensory data, which is computationally prohibitive for most existing IRL algorithms. We propose a novel function approximation framework and reformulate the Bellman optimality equation to handle high-dimensional state spaces efficiently. We compare different function approximators in simulated environments, and adopt a deep neural network as the function approximator. The technique is applied to evaluating human patients with spinal cord injuries under spinal stimulation, and the skill levels of surgical robot operators. The results demonstrate the efficiency and effectiveness of the proposed method.

Cost-Effective Wearable Indoor Localization and Motion Analysis via the Integration of UWB and IMU.

Wearable indoor localization can now find applications in a wide spectrum of fields, including the care of children and the elderly, sports motion analysis, rehabilitation medicine, robotics navigation, etc. Conventional inertial measurement unit (IMU)-based position estimation and radio signal indoor localization methods based on WiFi, Bluetooth, ultra-wide band (UWB), and radio frequency identification (RFID) all have their limitations regarding cost, accuracy, or usability, and a combination of the techniques has been considered a promising way to improve the accuracy. This investigation aims to provide a cost-effective wearable sensing solution with data fusion algorithms for indoor localization and real-time motion analysis. The main contributions of this investigation are: (1) the design of a wireless, battery-powered, and light-weight wearable sensing device integrating a low-cost UWB module-DWM1000 and micro-electromechanical system (MEMS) IMU-MPU9250 for synchronized measurement; (2) the implementation of a Mahony complementary filter for noise cancellation and attitude calculation, and quaternions for frame rotation to obtain the continuous attitude for displacement estimation; (3) the development of a data fusion model integrating the IMU and UWB data to enhance the measurement accuracy using Kalman-filter-based time-domain iterative compensations; and (4) evaluation of the developed sensor module by comparing it with UWB- and IMU-only solutions. The test results demonstrate that the average error of the integrated module reached 7.58 cm for an arbitrary walking path, which outperformed the IMU- and UWB-only localization solutions. The module could recognize lateral roll rotations during normal walking, which could be potentially used for abnormal gait recognition.

The Use of Motion Analysis as Particle Biomarkers in Lensless Optofluidic Projection Imaging for Point of Care Urine Analysis

Urine testing is an essential clinical diagnostic tool. The presence of urine sediments, typically analyzed through microscopic urinalysis or cell culture, can be indicative of many diseases, including bacterial, parasitic, and yeast infections, as well as more serious conditions like bladder cancer. Current urine analysis diagnostic methods are usually centralized and limited by high cost, inconvenience, and poor sensitivity. Here, we developed a lensless projection imaging optofluidic platform with motion-based particle analysis to rapidly detect urinary constituents without the need for concentration or amplification through culture. A removable microfluidics channel ensures that urine samples do not cross contaminate and the lens-free projection video is captured and processed by a low-cost integrated microcomputer. A motion tracking and analysis algorithm is developed to identify and track moving objects in the flow. Their motion characteristics are used as biomarkers to detect different urine species in near real-time. The results show that this technology is capable of detection of red and white blood cells, Trichomonas vaginalis, crystals, casts, yeast and bacteria. This cost-effective device has the potential to be implemented for timely, point-of-care detection of a wide range of disorders in hospitals, clinics, long-term care homes, and in resource-limited regions.

Simulation of Object Movement Analysis

There are many approaches for motion detection in a continuous video stream. All of them are based on comparing of the current video frame with one from the previous frames or with something that we'll call background. This research project is carried out to determine some of the basic simulation of object motion analysis algorithm that had been founded or developed or even researched and Supports the following types of video sources: AVI files, local capture device .This thesis report would bring a presentation of these algorithms for researchers to get a basic idea of performing an algorithm for simulation of object motion Analysis. One of the most common approaches is to compare the current frame with the previous one. It's useful in video compression when you need to estimate changes and to write only the changes, not the whole frame. But it is not the best one for motion detection applications. If the object is moving smoothly we'll receive small changes from frame to frame. So, it's impossible to get the whole moving object. Things become worse, when the object is moving so slowly, when the algorithms will not give any result at all. I used an image processing library for simplicity, it's not a video processing library. Besides, the library allows me to research different areas more quickly, than to write optimized solutions. I use LDA (Linear Discriminant Analysis) Algorithm for face and object detection. LDA maximizing the component axes for class separation. LDA tries to find projection axes, such as classes are best separated. LDA can be used not only for classification, but also for dimensionality reduction.

Human motion analysis based on extraction of skeleton and dynamic time warping algorithm using RGBD camera

Human action analysis is an extremely popular topic in the field of computer vision. It has wide application prospects in intelligent monitoring, virtual reality, pedestrian tracking, etc. This paper present an algorithm for human motion analysis based on extraction of skeleton and dynamic time warping algorithm using RGBD camera. First, to solve the problem of the limitation of information in two-dimensional space, the RGBD camera is adopted to obtain the three-dimensional spatial information of the human body. Then, in the process of feature extraction, 11 skeleton points are selected from the depth image and the relative distance of the space is calculated, reducing the computational complexity significantly. Furthermore, an optimisation algorithm of dynamic time warping is introduced so that the adverse effects of time difference are decreased. Finally, the human motion analysis is studied. The experimental results show that the proposed method can recognise single action and double action effectively.

Golf swing analysis system with a dual band and motion analysis algorithm

In this paper, we developed a golf position analysis system with an inertial sensor and swing motion analysis algorithm that can be used in golf courses. Specifically, we developed a band for both wrists that analyzes the golf swing of whoever is wearing it. By analyzing the movements of both the right and left wrists of the golfer, their golf swing can be judged more accurately, which can be used to advise the golfer regarding their golf swing. Experimental results show that this portable instrument along with its swing motion detection algorithm is a promising training tool for golfers.

The minimally acceptable classification criterion for surgical skill: intent vectors and separability of raw motion data.

Minimally invasive surgery requires objective methods for skill evaluation and training. This work presents the minimally acceptable classification (MAC) criterion for computational surgery: Given an obvious novice and an obvious expert, a surgical skill evaluation classifier must yield 100% accuracy. We propose that a rigorous motion analysis algorithm must meet this minimal benchmark in order to justify its cost and use. We use this benchmark to investigate two concepts: First, how separable is raw, multidimensional dry laboratory laparoscopic motion data between obvious novices and obvious experts? We utilized information theoretic techniques to analytically address this. Second, we examined the use of intent vectors to classify surgical skill using three FLS tasks. We found that raw motion data alone are not sufficient to classify skill level; however, the intent vector approach is successful in classifying surgical skill level for certain tasks according to the MAC criterion. For a pattern cutting task, this approach yields 100% accuracy in leave-one-user-out cross-validation. Compared to prior art, the intent vector approach provides a generalized method to assess laparoscopic surgical skill using basic motion segments and passes the MAC criterion for some but not all FLS tasks.

Motion analysis and fuzzy-PID control algorithm designing for the pitch angle of an underwater glider

Motion analysis and fuzzy-PID control algorithm designing for the pitch angle of an underwater glider

Folk Dance Evaluation Using Laban Movement Analysis

Motion capture (mocap) technology is an efficient method for digitizing art performances, and is becoming increasingly popular in the preservation and dissemination of dance performances. Although technically the captured data can be of very high quality, dancing allows stylistic variations and improvisations that cannot be easily identified. The majority of motion analysis algorithms are based on ad-hoc quantitative metrics, thus do not usually provide insights on style qualities of a performance. In this work, we present a framework based on the principles of Laban Movement Analysis (LMA) that aims to identify style qualities in dance motions. The proposed algorithm uses a feature space that aims to capture the four LMA components (B ody , E ffort , S hape , S pace ), and can be subsequently used for motion comparison and evaluation. We have designed and implemented a prototype virtual reality simulator for teaching folk dances in which users can preview dance segments performed by a 3D avatar and repeat them. The user’s movements are captured and compared to the folk dance template motions; then, intuitive feedback is provided to the user based on the LMA components. The results demonstrate the effectiveness of our system, opening new horizons for automatic motion and dance evaluation processes.

스테레오 카메라를 이용한 지능형 보행보조로봇의 개발

용자 보행 추종 성능을 실험적으로 검증하였다. Abstract: This paper describes the development of a walking assistive robot for effective self-rehabilitation for elderly people facing an inconvenience in walking. The main features of the developed robot are enhanced safety and mobility using the baby walker and electric wheelchair mechanisms and an accurate walking tracking control algorithm using potentiometers and stereo cameras. Specifically, a pelvis supporter is designed to prevent the user from falling down and reduce the burden on their legs, and electric motors are used for easy locomotion with low effort. Next, the walking intention and direction of the user are automatically recognized by using potentiometers attached at the pelvis supporter so that the robot can track the user, and the rapidity and accuracy of the tracking were increased by applying a lower-body motion analysis algorithm with stereo cameras. Finally, the user-tracking performance of the developed robot was experimentally verified through stepwise walking assistance experiments.