Motion Detection Method Research Articles

Ghost-Free Multi-Exposure Image Fusion Technology Based on the Multi-Scale Block LBP Operator

This paper proposes a ghost-free multi-exposure image fusion technique based on the multi-scale block LBP (local binary pattern) operator. The method mainly includes two steps: first, the texture variation, brightness, and spatial consistency weight maps of the image are computed, and then these three image features are used to construct the initial weight map. Finally, the multi-resolution method is used to fuse the images to obtain the resulting image. The main advantage of this technique lies in the step of extracting the details of the source image based on the multi-scale block LBP operator, which is used to preserve the details of the brightest and darkest areas in high dynamic range scenes and preserve the texture features of the source image. Another advantage is that a new LBP operator-based motion detection method is proposed for fusing multi-exposure images in dynamic scenes containing moving objects. In addition, this paper also studies two spatially consistent weight distribution methods and compares and discusses the effects of these two methods on the results of dynamic image fusion. Through a large number of experimental comparisons, the superiority and feasibility of this method are proved.

A Novel Compensatory Motion Detection Method Using Multiple Signals and Machine Learning

Harmful compensatory motion will seriously influence the upper limb rehabilitation effect of stroke patients. Existing compensatory motion pattern detection methods, which are mainly based on accelerometers, inertial measurement units (IMUs), and vision, have problems such as high installation requirements, calibration difficulty, object occlusion, and complex operations. To solve these problems, by analyzing the principle of compensatory motion, this paper designs a trunk restraint belt, compensation motion mode detection system that is composed of a force sensor (F-S), angular displacement sensor (AD-S), and surface electromyography (sEMG). Fifteen healthy subjects without dyskinesia completed normal motion and simulated compensatory movement modes (trunk rotation, trunk forward tilt, and scapular elevation) based on the system. Machine learning (ML) methods are used to classify three compensated motion and normal motion (NM). Among them, the support vector machine (SVM) classifier shows good classification performance for trunk forward tilt (F1-score = 0.9256), shoulder blade elevation (F1-score = 0.9190), trunk rotation (F1-score = 0.8262) and normal motion (F1-score = 0.9758). This method is a new compensation detection method with obvious advantages: it is easy to wear, and without considering the problems of calibration and target occlusion, it can not only identify the patient motion mode but also limit the large range of compensatory motion.

Data-driven head motion correction for PET using time-of-flight and positron emission particle tracking techniques.

Positron emission tomography (PET) is susceptible to patient movement during a scan. Head motion is a continuing problem for brain PET imaging and diagnostic assessments. Physical head restraints and external motion tracking systems are most commonly used to address to this issue. Data-driven methods offer substantial advantages, such as retroactive processing but typically require manual interaction for robustness. In this work, we introduce a time-of-flight (TOF) weighted positron emission particle tracking (PEPT) algorithm that facilitates fully automated, data-driven head motion detection and subsequent automated correction of the raw listmode data. We used our previously published TOF-PEPT algorithm Dustin Osborne et al. (2017), Tasmia Rahman Tumpa et al., Tasmia Rahman Tumpa et al. (2021) to automatically identify frames where the patient was near-motionless. The first such static frame was used as a reference to which subsequent static frames were registered. The underlying rigid transformations were estimated using weak radioactive point sources placed on radiolucent glasses worn by the patient. Correction of raw event data were achieved by tracking the point sources in the listmode data which was then repositioned to allow reconstruction of a single image. To create a "gold standard" for comparison purposes, frame-by-frame image registration based correction was implemented. The original listmode data was used to reconstruct an image for each static frame detected by our algorithm and then applying manual landmark registration and external software to merge these into a single image. We report on five patient studies. The TOF-PEPT algorithm was configured to detect motion using a 500 ms window. Our event-based correction produced images that were visually free of motion artifacts. Comparison of our algorithm to a frame-based image registration approach produced results that were nearly indistinguishable. Quantitatively, Jaccard similarity indices were found to be in the range of 85-98% for the former and 84-98% for the latter when comparing the static frame images with the reference frame counterparts. We have presented a fully automated data-driven method for motion detection and correction of raw listmode data. Easy to implement, the approach achieved high temporal resolution and reliable performance for head motion correction. Our methodology provides a mechanism by which patient motion incurred during imaging can be assessed and corrected post hoc.

Analysis of Art Classroom Teaching Behavior Based on Intelligent Image Recognition

To solve the problem of intelligent image recognition in classroom behavior, this paper proposes a fast target detection based on FFmpeg CODEC, extracts MHI-HOG joint features according to the located foreground target area, and finally completes the behavior recognition model through a BP neural network support vector machine joint classifier based on the look-up table. The results are as follows: the motion detection method based on H.264 FFmpeg CODEC video has the highest detection accuracy, which can reach 95%. The foreground detection method takes about 10 ms and saves 90% of the time. The behavior classification and recognition effect of MHI-HOG joint features based on the model has been significantly improved, and the comprehensive recognition rate has reached 95%. The built-in BP neural network support vector machine has 97% accuracy in extracting, classifying, and recognizing the characteristics of a single sample. This study attempts to identify and analyze the class behavior and validate the effectiveness of the collaborative classifiers proposed in this paper to build an intellectual classroom.

A Comparison of Video-based Methods for Neonatal Body Motion Detection.

Preterm infants in a neonatal intensive care unit (NICU) are continuously monitored for their vital signs, such as heart rate and oxygen saturation. Body motion patterns are documented intermittently by clinical observations. Changing motion patterns in preterm infants are associated with maturation and clinical events such as late-onset sepsis and seizures. However, continuous motion monitoring in the NICU setting is not yet performed. Video-based motion monitoring is a promising method due to its non-contact nature and therefore unobtrusiveness. This study aims to determine the feasibility of simple video-based methods for infant body motion detection. We investigated and compared four methods to detect the motion in videos of infants, using two datasets acquired with different types of cameras. The thermal dataset contains 32 hours of annotated videos from 13 infants in open beds. The RGB dataset contains 9 hours of annotated videos from 5 infants in incubators. The compared methods include background substruction (BS), sparse optical flow (SOF), dense optical flow (DOF), and oriented FAST and rotated BRIEF (ORB). The detection performance and computation time were evaluated by the area under receiver operating curves (AUC) and run time. We conducted experiments to detect motion and gross motion respectively. In the thermal dataset, the best performance of both experiments is achieved by BS with mean (standard deviation) AUCs of 0.86 (0.03) and 0.93 (0.03). In the RGB dataset, SOF outperforms the other methods in both experiments with AUCs of 0.82 (0.10) and 0.91 (0.05). All methods are efficient to be integrated into a camera system when using low-resolution thermal cameras.

Vehicle Detection from Aerial Images with Object and Motion Detection

Moving vehicle detection is one of important issues in surveillance and traffic monitoring applications for aerial images. In this study, a vehicle detection method is proposed by combining motion and object detection. A method based on background modeling and subtraction is applied for motion detection, while Faster-RCNN architecture is used for object detection. Motion detection result is enhanced with the proposed superpixel based refinement method. Experimental study shows that performance of motion detection increases about 8\% for $F_1$ metric with the proposed post processing method. Object detection, motion detection and superpixel segmentation methods interact with each other in parallel processes with the proposed software architecture, which significantly increases the working speed of the method. In last step of the proposed method, each vehicle is tracked with the kalman filter. The performance of proposed method is evaluated on the VIVID dataset. The performance evaluation shows that proposed method increases $F_1$ and recall values significantly compared to the motion and object detection methods alone. It also outperforms SCBU and MCD methods which are widely used for performance comparison in motion detection studies in the literature

Joint instancewise and instance-union fusion for improving motion detection algorithms

Motion detection (MD) is a fundamental step in many advanced computer vision applications, but the various complex challenges in real surveillance videos lead to some false positives and false negatives in the detection results of traditional MD algorithms. Therefore, joint instancewise and instance-union fusion for improving MD algorithms, in which an instance segmentation model is combined with a traditional MD algorithm. are proposed to address this problem. First, for each input frame (indexed by t), the MD algorithm produces a binary mask Mt, and the instance segmentation model produces the specific categories of binary instance masks (BIMs). Second, according to the instance confidence, BIMs are divided into high-quality binary instance masks (HBIMs) and low-quality binary instance masks (LBIMs). Then instancewise fusion of HBIMs with Mt and instance-union fusion of LBIMs with Mt are used to generate a high-quality foreground segmentation mask DtH and a low-quality foreground segmentation mask DtL, respectively. Finally, the bitwise logic addition operation of DtH and DtL produces a more accurate foreground segmentation result than Mt, called Dt. The experimental results show that our proposed method with visual background extractor and YOLACT++ processes at a resolution of 320 × 240 videos at 30 frames per second. For the Changedetection.net -2014, SBM-RGBD, and labeled and annotated sequences for integral evaluation of segmentation algorithms datasets, the highest overall F-measure of our experimental results with our proposed method are 0.8454, 0.8094, and 0.8939, respectively, surpassing state-of-the-art unsupervised MD methods.

In Situ Loading of Polypyrrole onto Aramid Nanofiber and Carbon Nanotube Aerogel Fibers as Physiology and Motion Sensors.

Nanocomposite conductive fiber has been newly developed as a lightweight material with high flexibility and strong weavability, which can meet the requirements of flexible wearable devices. Herein, lightweight porous aramid nanofibers (ANF) and carbon nanotube (CNT) aerogel fibers coated with polypyrrole (PPy) layers are prepared by a wet spinning method for motion detection and information transmission. The ANF/CNT/PPy aerogel fiber with low density (56.3 mg/cm3), conductivity (6.43 S/m), and tensile strength (2.88 MPa) were used as motion sensors with high sensitivity (0.12) and long life (1000 cycles). At the same time, the differential conductivity of aerogel fibers is utilized to reduce the information transmission time (up to 46%). High- and low-temperature-resistant (-196 to 100 °C) aerogel fibers are also available as a quick heater and ionic solution detector. In summary, the prepared ANF/CNT/PPy aerogel fiber can be used as a multifunctional sensor for human-health detection and motion monitoring.

Wi-Exercise: An Indoor Human Movement Detection Method Based on Bidirectional LSTM Attention

Human motion recognition has become a hot topic in the field of human-computer interaction. Due to the traditional method of detecting human movement in indoor environments, there are still problems such as high hardware costs, influenced by the environment and the need for experimenters to be equipped with relevant equipment. With the large-scale deployment of wireless devices and the establishment of wireless network infrastructure, indoor personnel movement recognition systems based on wireless signals are gradually proposed. In this paper, we propose a device-independent motion-detection method Wi-exercise based on temporal recurrent neural networks. The acquired channel state information (CSI) is preprocessed by wavelet transform, and the output CSI matrix is filtered by the principal component analysis (PCA) to extract the feature values. The wavelet function is processed to further remove the noise also to make the action data more distinctive, and then PCA is used to track the entire CSI time series to improve and maintain its dimensional energy. The preprocessed data are subjected to feature extraction to obtain CSI of human motion and establish feature sequences, and then the action model is trained using the bidirectional long short-term memory attention (ABLSTM) mechanism to finally realize human motion recognition. Finally, the robustness of Wi-exercise is tested experimentally, and its performance is compared with that of existing recognition methods. The experimental results show that the average recognition rate of the method is 94.43% in the complex indoor environment, and the method is better than the traditional classifier method for action recognition, with lower and higher recognition accuracy.

Research on Sports Dance Movement Detection Based on Pose Recognition

In view of the poor effect of current sports dance movement detection, this paper puts forward a sports dance movement detection method based on posture recognition. By using the principle of posture recognition to obtain the characteristic information of sports dance movement, construct the action characteristic evaluation system, optimize the action detection algorithm combined with posture recognition technology, and realize the classified detection of sports dance movements. Finally, experiments show that the sports dance movement detection based on pose recognition has high practicability and effectiveness in the process of practical application and fully meets the research requirements.

PPGMotion: Model-based detection of motion artifacts in photoplethysmography signals

Photoplethysmography (PPG) is used widely in health wearables to monitor biomarkers like heart rate. However, motion activities degrade the quality of the measured PPG signal, thereby reducing the accuracy of heart-rate estimation. Existing state-of-the-art methods for motion detection rely on the semi-periodic structure of PPG to detect the aperiodic motion artifacts, thereby failing in scenarios when motion contamination tends to be periodic. We propose a novel technique, PPGMotion, for detecting all types of motion artifacts in PPG signals with high accuracy, without the need for any reference motion signals. Our approach relies on the morphological structure of the artifact-free PPG signal. We compare our method against some classical methods on one synthetic and four real datasets – dataset (1) and (2) are obtained from finger pulse-oximeter under motion activities, dataset (3) and (4) are obtained from a wearable smartwatch. We show that for the synthetic dataset, the performance of PPGMotion is significantly better than existing work as the contaminated PPG tends to become periodic, with an increase in sensitivity of at least 20% over state-of-the-art methods. For real data, PPGMotion achieves similar performance for random motion artifact detection as the classical methods but performs significantly better when motion tends to be periodic, with at least 10% increase in sensitivity in detecting motion artifacts in datasets (2), (3), and (4).

A visual method for threshold detection of sediment motion in a flume experiment without human interference

AbstractAn experimental investigation of the entrainment threshold of sediment grains conducted in a non‐tiltable flume is reported and an original processing method based on image correlation suitable for detection of sediment threshold of motion is presented. Unlike existing visual measurement methods, the proposed method is not affected by the individual judgement of the experimentalists, which may strongly impact the estimation of incipient motion. Three entrainment thresholds were exhibited. The method highlighted a first threshold for very low shear stress conditions that was interpreted as a nascent movement threshold. The other two thresholds of motion were related to distinct stages of surface mobility of the bed: one related to bedload threshold and the other to bedform threshold. Series of tests were first performed to study the sensitivity of the method to different parameters: angle of view of the camera, size of the image and acceleration rate of the linear ramp of flow velocity. A ratio of the image surface and the grain surface equal to 3000 was found to be the minimum size to perform reliable estimations of entrainment thresholds for all the sediments in the range of 0.328–2.648 mm tested. It was the only condition for the method to work. Once the method was validated, tests were performed with homogeneous sands and compared to results based on reference‐based and visual methods. The correlation method yields similar values for the bedload threshold to those obtained from reference‐based methods. Thus it could be an alternative to other methodologies by the simplicity of its implementation, precision, no requirement for human interference and direct correlation between threshold velocity and bed mobility without extrapolation.

Finger motion detection based on optical fiber Bragg grating with polyimide substrate

Gestures play an important role in human-computer interaction, which provides a natural way for human-machine communication. In this paper, we proposed a new finger motion detection method based on optical fiber Bragg grating (FBG) with polyimide substrate. Several FBGs with polyimide substrate were fixed on the forearm to monitor the deformation around the forearm caused by finger motion. Firstly, the sensors layout was determined according to the distribution of forearm muscles which control finger motions, and the arrangement of FBGs was optimized. Then, through a series of tests, the response characteristics and applicability of the proposed FBG with polyimide substrate were verified. The tests results show that FBG with polyimide substrate has a high sensitivity, good linearity, low hysteresis error and good creep resistance compared with other two substrates. In the experiment of finger motion detection, test data based on six static gestures was adopted to evaluate the availability of the FBGs. The experimental results show that the proposed method can detect six static gestures effectively, and the FBG output signal has good repeatability under the same gesture. This is the first attempt to use FBGs to detect fingers’ monitor by monitoring deformations at the forearm, which is a technique with wide application prospects.

Privacy-preserving Motion Detection for HEVC-compressed Surveillance Video

In the cloud era, a large amount of data is uploaded to and processed by public clouds. The risk of privacy leakage has become a major concern for cloud users. Cloud-based video surveillance requires motion detection, which may reveal the privacy of people in a surveillance video. Privacy-preserving video surveillance allows motion detection while protecting privacy. The existing scheme [ 25 ], designed to detect motion on encrypted and H.264-compressed surveillance videos, does not work well on more advanced video compression schemes such as HEVC. In this article, we propose the first motion detection method on encrypted and HEVC-compressed videos. It adopts a novel approach that exploits inter-prediction reference relationships among coding blocks to detect motion regions. The partition pattern and the number of coding bits of each detection block used in prior art are also used to help detect motion regions. Spatial and temporal consistency of a moving object and Kalman filtering are applied to segment connected/merged motion regions, remove noise and background motions, and refine trajectories and shapes of detected moving objects. Experimental results indicate that our detection method achieves high detection recall, precision, and F1-score for surveillance videos of both high and low resolutions with various scenes. It has a similarly high detection accuracy on encrypted and HEVC-compressed videos as that of the existing motion detection method [ 25 ] on encrypted and H.264-compressed videos. Our proposed method incurs no bit-rate overhead and has a very low computational complexity for both motion detection and encryption of HEVC videos.

A Robust Movement Quantification Algorithm of Hyperactivity Detection for ADHD Children Based on 3D Depth Images.

Attention deficit hyperactivity disorder (ADHD) is one of the most common childhood mental disorders. Hyperactivity is a typical symptom of ADHD in children. Clinicians diagnose this symptom by evaluating the children's activities based on subjective rating scales and clinical experience. In this work, an objective system is proposed to quantify the movements of children with ADHD automatically. This system presents a new movement detection and quantification method based on depth images. A novel salient object extraction method is proposed to segment body regions. In movement detection, we explore a new local search algorithm to detect any potential motions of children based on three newly designed evaluation metrics. In the movement quantification, two parameters are investigated to quantify the participation degree and the displacements of each body part in the movements. This system is tested by a depth dataset of children with ADHD. The movement detection results of this dataset mainly range from 91.0% to 95.0%. The movement quantification results of children are consistent with the clinical observations. The public MSR Action 3D dataset is tested to validate the performance of this system.

Simulation and Classification of Spatial Disorientation in a Flight Use-Case Using Vestibular Stimulation

A commonly used definition of spatial disorientation (SD) in aviation is “an erroneous sense of one’s position and motion relative to the plane of the earth’s surface”. There exists a wide range of SD use-cases dictated by situational factors, therefore SD has been predominantly studied using reduced motion detection experimental contexts in isolation. The study of SD by use-case makes it difficult to understand general SD occurrence and thus provide viable solutions. To investigate SD in a generalized manner, a two-part Human Activity Recognition (HAR) study was performed. In Part I, a generalized SD perception dataset was created using whole-body experimental motion detection methods in a naturalistic flight context; joystick response was measured during rotational or translational vestibular stimulation. Results showed that SD occurred less for faster speeds than slower speeds, and specific orientations and axes were more difficult to detect motion. Part II evaluated supervised and unsupervised model parameters, including: model architecture, data use-case, feature-type, feature quantity, ground-truth labeling, unsupervised labeling. Long-Short Term Memory (LSTM), Random Forest (RF), and Transformer Encoder models most accurately predicted SD with mean accuracy of 0.84, 0.82, and 0.77 respectively. Using permutation importance (PIM), a dependency score for time, frequency, and time & frequency feature-types quantified the amount that each model architecture depended on a feature-type. The lenient ground-truth label best characterized features, and K-medoids clustering using position and velocity features most accurately replicated ground-truth labels.

Retracted] Detection Method of Limb Movement in Competitive Sports Training Based on Deep Learning

Traditional methods have the problems of insufficient accuracy and slow speed in human posture detection. In order to solve the above problems, a limb movement detection method in competitive sports training based on deep learning is proposed. The force change parameters of sports limb movements in the process of sports are computed to achieve the detection of limb movements in competitive sports training, and the limb movement characteristics in competitive sports training are extracted using a deep learning algorithm. The experimental results show that the limb movement detection method based on deep learning in competitive sports training has significantly higher detection accuracy and faster speed.

Real-time motion detection with candidate masks and region growing for moving cameras

A fast and reliable motion detection method is proposed for moving cameras. Existing methods generally build background models and then apply background subtraction for moving pixels detection. In background modeling, statistical methods and/or features, such as edges, local binary patterns are used. Parameters of the proposed methods need to be updated adaptively for better performance. In recent studies, adaptive learning rates are used with main and candidate background models. Simple and adaptive thresholding methods are used for foreground detection in different studies. We build a statistical background model with hue–saturation–value color space and perform background subtraction with the contribution of optical flow vectors. Dense optical flow is applied between warped the background model and the current frame to estimate optical flow vectors. If a pixel has a larger magnitude, we set a weight value for each pixel in the background subtraction process. Then, we extract two candidate foreground masks and apply some postprocessing techniques to determine the final mask. Our proposed method works fast in real time, and the experimental results on two different datasets show that our approach has the highest performance compared with the methods in the literature.

Neural Network for Intelligent and Efficient Volleyball Passing Training

Passing is a relatively basic technique in volleyball. In volleyball passing teaching, training the correct passing technique plays a very important role. The correct pass can not only accurately grasp the direction of the ball point and the drop point but also effectively connect the defense and the offense. In order to improve the efficiency and quality of volleyball passing training, improve the precise extraction of sport targets, reduce redundant feature information, and improve the generalization performance and nonlinear fitting capabilities of the algorithm, this paper studies volleyball based on the nested convolutional neural network model and passing training wrong movement detection method. The structure of the convolutional neural network is improved by nesting mlpconv layers, and the Gaussian mixture model is used to effectively and accurately extract the foreground objects in the video. The nested multilayer mlpconv layer automatically learns the deep-level features of the foreground target, and the generated feature map is vectorized and input to the Softmax classifier connected to the fully connected layer for passing wrong behavior detection in volleyball training. Based on the detection of nearly 1,000 athletes’ action datasets, the simulation experiment results show that the algorithm reduces the acquisition of redundant information and shortens the calculation time and learning time of the algorithm, and the improved convolutional neural network has generalization performance and nonlinearity. The fitting ability has been improved, and the detection of abnormal volleyball passing behaviors has achieved a higher accuracy rate.

Body Motion Detection in Neonates Based on Motion Artifacts in Physiological Signals from a Clinical Patient Monitor.

Motion patterns in newborns contain important information. Motion patterns change upon maturation and changes in the nature of motion may precede critical clinical events such as the onset of sepsis, seizures and apneas. However, in clinical practice, motion monitoring is still limited to observations by caregivers. In this study, we investigated a practical yet reliable method for motion detection using routinely used physiological signals in the patient monitor. Our method calculated motion measures with a continuous wavelet transform (CWT) and a signal instability index (SII) to detect gross-motor motion in 15 newborns using 40 hours of physiological data with annotated videos. We compared the performance of these measures on three signal modalities (electrocardiogram ECG, chest impedance, and photo plethysmography). In addition, we investigated whether their combinations increased performance. The best performance was achieved with the ECG signal with a median (interquartile range, IQR) area under receiver operating curve (AUC) of 0.92(0.87-0.95), but differences were small as both measures had a robust performance on all signal modalities. We then applied the algorithm on combined measures and modalities. The full combination outperformed all single-modal methods with a median (IQR) AUC of 0.95(0.91-0.96) when discriminating gross-motor motion from still. Our study demonstrates the feasibility of gross-motor motion detection method based on only clinically-available vital signs and that best results can be obtained by combining measures and vital signs.