Search

Motion detection is becoming prominent for computer vision applications. The background subtraction method that uses the Gaussian mixture model (GMM) is utilized frequently in camera or video settings. However, there is still more work that needs to be done to develop a reliable, accurate and high-performing technique due to various challenges. The degree of difficulty for this challenge is primarily determined by how the object to be detected is defined. It could be influenced by the changes in the object posture or deformations. In this context, we describe and bring together the most significant challenges faced by the background subtraction techniques based on GMM for dealing with a crucial background situation. Therefore, the findings of this study can be used to identify the most appropriate GMM version based on the crucial background situation.

Patient motion during dynamic PET imaging can induce errors in myocardial blood flow (MBF) estimation. Motion correction for dynamic cardiac PET is challenging because the rapid tracer kinetics of 82Rb leads to substantial tracer distribution change across different dynamic frames over time, which can cause difficulties for image registration-based motion correction, particularly for early dynamic frames. In this paper, we developed an automatic deep learning-based motion correction (DeepMC) method for dynamic cardiac PET. In this study we focused on the detection and correction of inter-frame rigid translational motion caused by voluntary body movement and pattern change of respiratory motion. A bidirectional-3D LSTM network was developed to fully utilize both local and nonlocal temporal information in the 4D dynamic image data for motion detection. The network was trained and evaluated over motion-free patient scans with simulated motion so that the motion ground-truths are available, where one million samples based on 65 patient scans were used in training, and 600 samples based on 20 patient scans were used in evaluation. The proposed method was also evaluated using additional 10 patient datasets with real motion. We demonstrated that the proposed DeepMC obtained superior performance compared to conventional registration-based methods and other convolutional neural networks (CNN), in terms of motion estimation and MBF quantification accuracy. Once trained, DeepMC is much faster than the registration-based methods and can be easily integrated into the clinical workflow. In the future work, additional investigation is needed to evaluate this approach in a clinical context with realistic patient motion.

Football is one of the favorite sports of people nowadays. Shooting is the ultimate goal of all offensive tactics in football matches. This is the most basic way to score a goal and the only way to score a goal. The choice and use of shooting technical indicators can have a great impact on the final result of the game. Therefore, how to improve the shooting technique of football players and how to adjust the shooting posture of football players are important issues faced by coaches and athletes. In recent years, deep learning has been widely used in various fields such as image classification and recognition and language processing. How to apply deep learning optimization to shooting gesture recognition is a very promising research direction. This article aims to study the football player’s shooting posture specification based on deep learning in sports event videos. Based on the analysis of target motion detection algorithm, target motion tracking algorithm, target motion recognition algorithm, and football shooting posture classification, KTH and Weizmann data sets are used. As the experimental verification data set of this article, the shooting posture of football players in the sports event video is recognized, and the accuracy of the action recognition is finally calculated to standardize the football shooting posture. The experimental results show that the Weizmann data set has a higher accuracy rate than the KTH data set and is more suitable for shooting attitude specifications.

International audience; In this paper, we consider a biologically inspired spiking neural network model for motion detection. The proposed model simulates the neurons' behavior in the cortical area MT to detect different kinds of motion in image sequences. We choose the conductance-based neuron model of the Hodgkin-Huxley to define MT cell responses. Based on the center-surround antagonism of MT receptive fields, we model the area MT by its great proportion of cells with directional selective responses. The network's spiking output corresponds to an MT neuron population's firing rates and enables to extract motion boundaries. We conduct several experiments on real image sequences. The experimental results show the proposed network's ability to segregate multiple moving objects from an image sequence and reproduce the MT cells' responses. We perform a quantitative evaluation on the YouTube Motion Boundaries (YMB) dataset, and we compare the result to stateof-the-art methods for boundary detection in videos: boundary flow estimation (BF) and temporal boundary difference (BD). The proposed network model provides the best results on YMB compared to BF and BD methods.

Sports injuries can be a major problem for athletes. Therefore, sports injury protection has become a key focus of attention in sports and medical circles. With widening participation in sport, related injuries can have an impact at national level. However, many areas around the world lack adequate medical resources. It takes more time and money for local people to get to the nearest rehabilitation department or physical therapy studio. Artificial intelligence (AI) has undergone vigorous development, leading to increased computing speed and accuracy. Nowadays, two-dimensional image signals can be used for body-posture recognition. This research is based on the Openpose limb-detection AI model, which has corrective exercise training elements and uses functional motion-detection technology as the diagnostic basis (combined with physical therapists’ clinical knowledge of rehabilitation interventions). We propose a 2-D imaging physical health detection system. The system is divided into four main parts: a mobile app user interface, the computing server, professional interface and database. A user video is recorded by the app. The computing server then calculates keypoints of the human body through Openpose and converts these data into clinical test indicators. Finally, health indicators are displayed, and the app registers action scores. The professional interface presents users with health feedback and recommends suitable rehabilitation videos. The computing server is divided into two parts: limb detection and the detection system. The limb-detection aspect is divided into four parts: sample collection, video processing, keypoint processing and results comparison. The detection system is subdivided into system architecture and a health evaluation (forming the basis for video recommendations). The key contributions of this paper are that the proposed system can calculate body posture and automatically detect the physical condition and health of the body. In addition to reducing dependence on professional human resources, the system can also save the trouble of manual angle measurement in traditional physical therapy.

We are implementing a project for memory optimization for video surveillance with the help of human motion happening in the surrounding in the warehouse and also will be able to playback the recorded video which will only have the human motion recorded video and images will be click continuously after a fixed interval of time to get a view when there is human motion or no human motion images will be always clicked and stored. This system is based on IoT (Internet of Things). It has a Raspberry Pi (RPI), Camera module to detect human (thief) or detection of fire. Motion detection is a process of confirming a change in the position of an object relative to its surroundings or the change in the surroundings relative to an object. Generally, motion detection is useful in real-time or active surveillance systems. IN this paper the main focus is given to the processing of the captured video data to detect human motion in it. So that it is easy for the user to view images and videos whenever he wants. So this system is very useful to maintain a warehouse and memory optimization will be done.

Radar sensors and micro-Doppler signatures have been widely used to recognize human motions. Apart from the motion classification task, human motion detection has attracted much attention as an emerging topic. A majority of existing motion detectors are designed for a specific motion, such as falling. In some scenarios, however, a broader range of human actions is of interest, hence a general motion detector is desired. In this paper, we propose a radar-based motion detection model named dual generative adversarial network (DGN). The proposed model tackles the detection task as a one-class classification problem and is applicable to detecting various motions. Unlike prior fall detection algorithms, which depend on manually collected alien data, the DGN employs a dual generation scheme to automatically produce valid alien samples in both the pixel level and the semantic level. The model is verified on two measured radar datasets containing individual motions and interactive motions, respectively. The experimental results show that our method outperforms other existing models on the human motion detection task.

This paper proposes a marker-based motion capture system for rat motion detection and gait analysis. Motion capture in small animals such as rodents is more challenging than in humans because of th...

By leveraging motion sensors, the study of physical activities has become effortless and convenient. Yoga is an excellent form of physical activity or exercise that involves all parts of the body. Regular practice of yoga improves both the physical and mental health of the people, if the practitioner performs it correctly. Though the existing exercise recognition methods have shown quite a good performance using deep neural networks, they fail to assess the correctness of execution. Feedback describing correctness level is very useful to an amateur practitioner. In this article, we aim to develop a YogaHelp system to help amateurs for learning the correct execution of yoga without any supervision of a trainer. The importance of such a system is much higher during a pandemic situation, where the trainers can not be availed due to the risk of catching an infection. YogaHelp leverages the motion sensors including accelerometer and gyroscope, to recognize 12 linked-steps of sun salutation (Surya Namaskar) yoga along with their correctness level. YogaHelp employs a deep learning model built using convolutional layers for yoga step recognition without explicit feature extraction. The novelty of the system lies in the feedback that describes the speed of execution and angular deviation of the posture from the standard ones. We develop a prototype for collecting a training dataset from eight professional yoga trainers and for validating the effectiveness of the system.

Methods of studying human motion in computer vision systems can be divided into two types. These are analysis in twodimensional and three-dimensional space. The former uses a single camera image and/ or multiple body sensors. Such an approach leads to a rapid accumulation of error and, consequently, low accuracy of the figure representation. Multiple cameras are usually used in the case of three-dimensional space analysis, while the objects are represented as sets of volumetric elements. Despite the high accuracy of this method, it is associated with high computational complexity and internal network load. The purpose of the paper is to develop a model using a single camera, while approaching threedimensional space analysis methods in terms of accuracy. In this paper a human figure is represented as a skeleton. The skeleton is described by an acyclic connected graph. The general structure of a human figure is analyzed. Fifteen basic points are selected. Physical and logical connections between them were studied and mathematically described. The velocity and spatial characteristics of the points and connections outline the general dynamics of motion. The study describes a model of human motion and gives the option for model construction on the example of a particular image. The developed algorithm for collection and analysis of information estimates relative locations and velocity characteristics of the graph elements. The model can be used for acquisition of information about the reference dynamics of human movements. In case of detecting major differences between the reference and the reality, the behavior is defined as deviant. Thus, the obtained algorithm can be applied in computer vision systems for detection and analysis of human movements.

Computer Vision and Pattern Recognition is one of the most interesting research subject on computer science, especially in case of reading or recognition of objects in realtime from the camera device. Object detection has wide range of segments, in this study we will try to find where the better methodologies for detecting a text and human skin. This study aims to develop a computer vision technology that will be used to help people with disabilities, especially illiterate (tuna aksara) and deaf (penyandang tuli) to recognize and learn the letters of the alphabet (A-Z). Based on our research, it is found that the best method and technique used for text recognition is Convolutional Neural Network with achievement accuracy reaches 93%, the next best achievement obtained OCR method, which reached 98% on the reading plate number. And also OCR method are 88% with stable image reading and good lighting conditions as well as the standard font type of a book. Meanwhile, best method and technique to detect human skin is by using Skin Color Segmentation: CIELab color space with accuracy of 96.87%. While the algorithm for classification using Convolutional Neural Network (CNN), the accuracy rate of 98% Key word: Computer Vision, Segmentation, Object Recognition, Text Recognition, Skin Color Detection, Motion Detection, Disability Application

Closed-Circuit TV (CCTV) system is one of the technologies in the surveillance field to solve the problem of detection and monitoring by providing extra features such as email alert or motion detection. However, detecting and alerting the admin on CCTV system may complicate due to the complexity to integrate the main program with an external Application Programming Interface (API). In this study, pixel processing algorithm is applied due to its efficiency and SMS alert is added as an alternative solution for users who opted out email alert system or have no Internet connection. A CCTV system with SMS alert (CMDSA) was developed using evolutionary prototyping methodology. The system interface was implemented using Microsoft Visual Studio while the backend components, which are database and coding, were implemented on SQLite database and C# programming language, respectively. The main modules of CMDSA are motion detection, capturing and saving video, image processing and Short Message Service (SMS) alert functions. Subsequently, the system is able to reduce the processing time making the detection process become faster, reduce the space and memory used to run the program and alerting the system admin instantly.

An algorithm of automatic detection and tracking the moving objects for the use in equipment on board of unmanned aerial vehicles is considered. The developed algorithm is based on a tracking specially selected points for a certain period. Tracked points are selected from the areas on the current frame, where the pixel intensity differs from the intensities of the same pixels in previous frames, aligned with the current frame using projective transformation. If the displacement of the tracked points is not fixed on several adjacent frames, they are being deleted, and new points from the areas presumably belonging to moving objects in the current frame are added instead. On each frame the points similar by the location and shape of trajectories of movement are combined into groups that presumably correspond to moving objects. Objects are tracked by comparing the groups of moving points with the points of neighboring frames. Groups of moving points from neighboring frames are matched if they contain a large number of common tracked points. The algorithm allows simultaneous tracking of more than 20 objects in real time. The indication of objects as moving occurs only if during the time of its tracking it has shifted a considerable distance. The algorithm has a low percentage of false detections of moving objects, it detects well small objects and is capable reliably to accompany moving objects.

It is the capability of humans and as well as vehicles to automatically detect object level motion that results into collision less navigation and also provides sense of situation. This paper presents a technique for secure object level motion detection which yields more accurate results. To achieve this, python code has been used along with various machine learning libraries. The detection algorithm uses the advantage of background subtraction and fed in data to detect even the slightest movement this system makes use of a webcam to scan a premise and detect movement of any sort; on the recognition of any activity it immediately sends an alert message to the owner of the system via mail. Any person requiring a surveillance system can use it.

In recent years, with the rapid development of artificial intelligence, information technology, intelligent digital video surveillance systems, real-time sports competition playback, and other technologies have emerged one after another, making the advantages of deep learning-based football posture detection tasks become more obvious. Related models and methods have been applied to the research field of sports posture estimation and have achieved great improvement, surpassing the traditional football posture estimation method based on manual design features in one fell swoop. In addition, the application of video foreground detection has developed rapidly and has great application value in sports analysis. Therefore, this paper proposes a novel football motion detection approach combining foreground detection and deep learning for real-time detection of football player posture. The main task of foreground target detection is to extract the interesting foreground target in the real monitoring scene and use it as the target of interest for subsequent analysis. Then, we propose a triple DetectNet detection framework based on deep learning technology, which can quickly and robustly realize the three-dimensional pose estimation of multiperson motion. For input, the triple DetectNet framework uses three neural networks and is executed in three stages; the first stage is to use the DetectNet (DN) network to detect the bounding box of each person separately, the second stage uses the 2DPoseNet (2DPN) network to estimate each of the corresponding two-dimensional poses of the individual, and the third stage uses the 3DPoseNet (3DPN) network to obtain the 3D pose of the person. This paper also conducted experiments on four datasets, and the results proved the superiority and success of this algorithm.

The motion of the camera in a video effectively conveys to the viewers the intention of the director, and is an essential element that enhances their interest. Therefore, detecting the motion of the camera is a very important factor in movie analysis. Existing research to detect the motion of the camera in a video has mainly focused on pan, tilt, and zoom. However, movies use more diverse camera motions to represent complex and varied emotions. Recognizing only pan, tilt, and zoom in a movie has limitations, especially not being able to detect lateral and longitudinal movements of the camera. In this study, a method is proposed to additionally detect boom and truck as well as pan, tilt, and zoom by using deep learning technology to improve this recognition ability. Thus, this study proposes the Improved Extractor of Camera Motion along with the CNN-Based Detector. The Improved Extractor of Camera Motion uses optical flow to extract camera motion vectors from video at eight-frame intervals. The CNN-Based Detector identifies five camera motions by using ResNet-152. As a result, the performance of our proposed method shows accuracy of 86.2%.

To enhance the effect of motion detection, a Gaussian modeling algorithm is proposed to fix holes and breaks caused by the conventional frame difference method. The proposed algorithm uses an improved three-frame difference method. A three-frame image sequence with one frame interval is selected for pairwise difference calculation. The logical “OR” operation is used to achieve fast motion detection and to reduce voids and fractures. The Gaussian algorithm establishes an adaptive learning model to make the size and contour of the motion detection more accurate. The motion extracted by the improved three-frame difference method and Gaussian model is logically summed to obtain the final motion foreground picture. Moreover, a moving target detection method, based on the U-Net deep learning network, is proposed to reduce the dependency of deep learning on the number of training datasets. It helps the algorithm to train models on small datasets. Next, it calculates the ratio of the number of positive and negative samples in the dataset and uses the reciprocal of the ratio as the sample weight to deal with the imbalance of positive and negative samples. Finally, a threshold is set to predict the results for obtaining the moving object detection accuracy. Experimental results show that the algorithm can suppress the generation and rupture of holes and reduce the noise. Also, it can quickly and accurately detect movement to meet the design requirements.

Breathing is one of the vital signs used to assess the physical health of a subject. Non-contact-based measurements of both breathing rate and changes in breathing rate help monitor health condition of subjects more flexibly. In this paper, we present an improved real-time camera-based adaptive breathing monitoring system, which includes real time (1) adaptive breathing motion detection, (2) adaptive region of interest detection to eliminate environmental noise, (3) breathing and body movement classification, (4) respiration rate estimation, (5) monitor change in respiration rate to examine overall health of an individual, and (6) online adaptation to lighting. The proposed system does not pose any positional and postural constraint. For evaluation, 30 videos of 15 animals are tested with drugs to simulate various medical conditions and breathing patterns, and the results from the proposed system are compared with the outputs of an existing FDA-approved invasive medical system for patient monitoring. The results show that the proposed method performs significantly correlated RR results to the reference medical device with the correlation coefficient equal to 0.92 and p-value less than 0.001, and more importantly the proposed video-based method is demonstrated to produce alarms 10 to 20 s earlier than the benchmark medical device. Graphical abstract The proposed system flowchart to extract the respiratory pattern from video.

Video surveillance has become a major tool in security maintenance. But analyzing in a playback version to detect any motion or any sort of movements might be tedious work because only for a short length of the video there would be any motion. There would be a lot of time wasted in analyzing the video and also it is impossible to always find the accurate frame where the transition has occurred. So there is a need in obtaining a summary video that captures any changes/motion. With the advancements in image processing using OpenCV and deep learning, video summarization is no longer an impossible work. Captions are generated for the summarized videos using an encoder–decoder captioning model. With the help of large, well-labeled video data sets like common objects in context, Microsoft video description, video captioning is a feasible task. Encoder–decoder models are used extensively to extract text from visual features with the arrival of long short term memory (LSTM). Attention mechanism has been widely used on decoder for the work of video captioning. Keyframes are obtained from very long videos using methods like dynamic mode decomposition, an algorithm in fluid dynamics, OpenCV’s absdiff(). We propose these tools for motion detection and video/image captioning for very long videos which are common in video surveillance.

Digital twins are meant to bridge the gap between real-world physical systems and virtual representations. Both stand-alone and descriptive digital twins incorporate 3D geometric models, which are the physical representations of objects in the digital replica. Digital twin applications are required to rapidly update internal parameters with the evolution of their physical counterpart. Due to an essential need for having high-quality geometric models for accurate physical representations, the storage and bandwidth requirements for storing 3D model information can quickly exceed the available storage and bandwidth capacity. In this work, we demonstrate a novel approach to geometric change detection in a digital twin context. We address the issue through a combined solution of dynamic mode decomposition (DMD) for motion detection, YOLOv5 for object detection, and 3D machine learning for pose estimation. DMD is applied for background subtraction, enabling detection of moving foreground objects in real-time. The video frames containing detected motion are extracted and used as input to the change detection network. The object detection algorithm YOLOv5 is applied to extract the bounding boxes of detected objects in the video frames. Furthermore, we estimate the rotational pose of each object in a 3D pose estimation network. A series of convolutional neural networks (CNNs) conducts feature extraction from images and 3D model shapes. Then, the network outputs the camera orientation’s estimated Euler angles concerning the object in the input image. By only storing data associated with a detected change in pose, we minimize necessary storage and bandwidth requirements while still recreating the 3D scene on demand. Our assessment of the new geometric detection framework shows that the proposed methodology could represent a viable tool in emerging digital twin applications.

This paper empirical investigates two basic statistical methods namely Adaptive Median and Adaptive Mean for motion detection in video surveillance for the optimization of parameters namely threshold and the refresh rate of background frame used in these methods. Experimentation shows that the optimum choice of parameters majorly affects the quality of motion detection. The performance of methods for different parameters is measured using precision, recall and f1-score. PR curves are also drawn which are based on precision and recall values to show the effect of different parameters. Test data includes six data sets from different scenarios of ‘CDNet2012’. Experimental results verify that for every method there are fixed values of parameters with slight variations which gives better result of object motion. These parameter values can be used or adapted for future experimentation on these methods with respect to each scenario.

Fire outbreak is a major issue in oil wells, forests, houses, industries all over the world. The damage caused by these types of accidents is tremendous towards nature and humankind. After these incidents, the need for an application for fire detection has increased. However various fire detection systems use temperature or smoke sensors which takes more response time. Moreover, these systems are expensive and are not widely effective, when the fire is placed far away from the detectors. This led to various alternatives such as computer vision, image processing techniques. One of the cost-effective methods would be the usage of surveillance cameras to detect the fire to inform the relevant parties. The proposed research work suggests a method to use surveillance cameras to monitor the occurrence of fire anywhere within the camera range. In this method, an RGB color pattern and motion detection technologies are used to detect the fire by background subtraction method. The choice capacity of fire-pixels is concluded by the force and immersion of the R part. It has been used that finds the boundary of the moving region in the color segmented image and calculates the number of fire pixels in this area. At that point, a fire identification framework is created dependent on this technique to identify fire effectively to spare life and property from fireperil.

Fire is a disaster that can endanger lives and cause property loss. The solution to detect fire that is commonly used today is to use a sensor. Fire sensors can be used together with surveillance cameras (CCTV) which are now being installed in many office buildings. This study tries to build a model for detecting fire in video with a digital image processing approach using the Gaussian Mixture Model for motion detection and fire color segmentation in the YCbCr color space. The model is then tested with metrics for accuracy, precision, recall, and processing speed. The dataset used is in the form of videos with small, medium, large fire sizes, and videos that only have fire-like objects. The test results show that the algorithm is able to detect fire when the size of the fire is not too small or the position of the fire is close enough to the camera. For videos with a resolution of 800x600 and a framerate of 30 fps, it can achieve 66.89% accuracy, 73.77% precision, and 66.66% recall. The performance during the day is relatively better than at night. Algorithm processing speed is too slow to be implemented in real-time

Map-based localization and sensing are one of the key components in autonomous driving technologies, where high quality 3D map reconstruction is fundamentally utmost important. However, due to the highly dynamic and uncontrollable properties of real world environment, building a high quality 3D map is not straightforward and requires several strong assumptions. To address this challenge, we present a complete framework, which detects and extracts the moving objects from a sequence of unordered and texture-less point clouds, to build high quality static maps. To accurately detect the moving objects from data acquired with a possibly fast moving platform, we propose a novel 3D Flow Field Analysis approach in which we inspect the motion behaviour of the registered point sets. The proposed algorithm elegantly models the temporal and spatial displacement of the moving objects. Thus, both small moving objects ( e.g. walking pedestrians) and large moving objects ( e.g. moving trucks) can be detected effectively. Further, by incorporating the Sparse Subspace Clustering framework, we propose a Sparse Flow Clustering algorithm to group the 3D motion flows under both the constraints of motion similarity and spatial closeness. To this end, the static scene parts and the moving objects can be independently processed to achieve photo-realistic 3D reconstructions. Finally, we show that the proposed 3D Flow Field Analysis algorithm and the Sparse Flow Clustering approach are highly effective for motion detection and segmentation, as exemplified on the KITTI benchmark, and yield high quality reconstructed static-maps as well as rigidly moving objects.

Different from traditional gestures, sign language gestures involve a lot of finger-level gestures without wrist or arm movements. They are hard to detect using existing motion sensors-based approaches. We introduce the first low-cost sign language gesture recognition system that can differentiate fine-grained finger movements using the Photoplethysmography (PPG) and motion sensors in commodity wearables. By leveraging the motion artifacts in PPG, our system can accurately recognize sign language gestures when there are large body movements, which cannot be handled by the traditional motion sensor-based approaches. We further explore the feasibility of using both PPG and motion sensors in wearables to improve the sign language gesture recognition accuracy when there are limited body movements. We develop a gradient boost tree (GBT) model and deep neural network-based model (i.e., ResNet) for classification. The transfer learning technique is applied to ResNet-based model to reduce the training effort. We develop a prototype using low-cost PPG and motions sensors and conduct extensive experiments and collect over 7000 gestures from 10 adults in the static and body-motion scenarios. Results demonstrate that our system can differentiate nine finger-level gestures from the American Sign Language with an average recognition accuracy over 98 percent.

In primates’ cerebral cortex, depth rotation sensitive (DRS) neurons have the property of preferential selectivity for depth rotation motion, whereas such a property is rarely adopted to create computational models for depth rotation motion detection. To fill this gap, a novel feedforward visual neural network is developed to execute depth rotation object detection, based on the recent neurophysiologic achievements on the mammalian vision system. The proposed neural network consists of two parts, i.e., presynaptic and postsynaptic neural networks. The former comprises multiple lateral inhibition neural sub-networks for the capture of visual motion information, and the latter extracts the cues of translational and depth motion and later, synthesizes such clues to perceive the process of depth rotation of an object. Experimentally, the neural network is sufficiently examined by different types of depth rotation under multiple conditions and settings. Numerical experiments show that not only it can effectively detect the spatio-temporal energy change of depth rotation of a moving object, but also its output excitation curve is a quasi-sinusoidal one, which is compatible with the hypothesis suggested by Johansson and Jansson in projective geometry. This research is a critical step toward the construction of artificial vision system for depth rotation object recognition.

Athletes’ sports detection has a heavy pressure on athletes’ training and post-injury rehabilitation. In the traditional mobilization test, there is no effective combination of exercise and rehabilitation, which directly leads to the athlete’s physical health cannot be guaranteed. Based on this, this study combines the current situation of the athletes’ field and the training ground, and uses monocular vision as the video input interface, and combines the monocular vision technology in the research. Moreover, in the research, this paper combines the human body model to construct an athlete’s human body model that adapts to monocular vision. At the same time, this paper combines the image processing technology to transform the image of the monocular visual athlete into a skeleton model, so as to realize the modeling of the athlete’s movement. In addition, this paper combines the model to explore the indoor and outdoor athlete recovery techniques and validates the model by experiment. The research shows that the research model has certain effects, which can meet the actual needs, and can provide theoretical reference for subsequent related research.

There are many technical and nontechnical steps involved in a successful clinical functional MRI (fMRI) scan. The output from scanning and analysis can only be as good as the input, so task instruction and rehearsal are the most important steps during an clinical fMRI procedure. Properly pre-processed data significantly affects statistical analysis, which has a great impact on image interpretation. Even though there is general agreement on how to process clinical fMRI data, such as algorithms for head motion detection and correction, the theory and practicalities associated with data processing remain complex and constantly evolving.

Video frame interpolation has increasingly attracted attention in computer vision and video processing fields. When motion patterns in a video are complex, large and non-linear (exceptional motion), the generated intermediate frame is blurred and likely to have large artifacts. In this paper, we propose a novel video frame interpolation considering the exceptional motion patterns. The proposed video frame interpolation takes into account an exceptional motion map that contains the location and intensity of the exceptional motion. The proposed method consists of three parts, which are optical flow based frame interpolation, exceptional motion detection, and frame refinement. The optical flow based frame interpolation predicts an optical flow which is used to synthesize the pre-generated intermediate frame. The exceptional motion detection detects the position and intensity of complex and large motion with the current frame and the previous frame sequence. The frame refinement focuses on the exceptional motion region of the pre-generated intermediate frame by using the exceptional motion map. The proposed video frame interpolation can be robust against the exceptional motion including complex and large motion. Experimental results showed that the proposed video frame interpolation achieved high performance on various public video datasets and especially on videos with exceptional motion patterns.

Purpose To investigate the ability of free induction decay navigator (FIDnav)-based motion monitoring to predict diagnostic utility and reduce the time and cost associated with acquiring diagnostically useful images in a pediatric patient cohort., Methods A study was carried out in 102 pediatric patients (aged 0-18 years) at 3T using a 32-channel head coil array. Subjects were scanned with an FID-navigated MPRAGE sequence and images were graded by two radiologists using a five-point scale to evaluate the impact of motion artifacts on diagnostic image quality. The correlation between image quality and four integrated FIDnav motion metrics was investigated, as well as the sensitivity and specificity of each FIDnav-based metric to detect different levels of motion corruption in the images. Potential time and cost savings were also assessed by retrospectively applying an optimal detection threshold to FIDnav motion scores., Results A total of 12% of images were rated as non-diagnostic, while a further 12% had compromised diagnostic value due to motion artifacts. FID-navigated metrics exhibited a moderately strong correlation with image grade (Spearman's rho >= 0.56). Integrating the cross-correlation between FIDnav signal vectors achieved the highest sensitivity and specificity for detecting non-diagnostic images, yielding total time savings of 7% across all scans. This corresponded to a financial benefit of $2080 in this study., Conclusions Our results indicate that integrated motion metrics from FIDnavs embedded in structural MRI are a useful predictor of diagnostic image quality, which translates to substantial time and cost savings when applied to pediatric MRI examinations.

Localization accuracy is a fundamental requirement for Simultaneous Localization and Mapping (SLAM) systems. Traditional visual SLAM (vSLAM) schemes are usually based upon the assumption of static environments, so they do not perform well in dynamic environments. While a number of vSLAM frameworks have been reported for dynamic environments, the localization accuracy is usually unsatisfactory. In this article, we present a novel motion detection and segmentation method using Red Green Blue-Depth (RGB-D) data to improve the localization accuracy of feature-based RGB-D SLAM in dynamic environments. To overcome the problem due to undersegmentation generated by the semantic segmentation network, a mask inpainting method is developed to ensure the completeness of object segmentation. In the meantime, an optical flow-based motion detection method is proposed to detect dynamic objects from moving cameras, allowing robust detection by removing irrelevant information. Experiments performed on the public Technical University of Munich (TUM) RGB-D data set show that the presented scheme outperforms the state-of-art RGB-D SLAM systems in terms of trajectory accuracy, improving the localization accuracy of RGB-D SLAM in dynamic environments.

Autonomous driving can obtain accurate perception and reliable motion prediction with the support of multi-modal fusion. Recently, there has been growing interest in leveraging features from various onboard sensors to enhance the primary stages of autonomous driving. This paper proposes LiCaNext to capture additional accuracy advancements in joint perception and motion prediction while maintaining real-time requirements. LiCaNext is the next version of LiCaNet, which fuses LIDAR data in both bird’s-eye view (BEV) and range view (RV) representations with a camera image. In contrast to LiCaNet, we introduce sequential range residual images into the multi-modal fusion network to further improve performance, with minimal increase in inference time. Employing sequential range residual images has a substantial direct impact on motion prediction and positively influences perception. We provide an extensive evaluation on the public nuScenes dataset. Our experiments show that incorporating sequential range residuals secures significant performance gain, with monotonic progress for a larger number of exploited residuals.

We demonstrate an interactive holographic display system for real-time drawing and erasing of 3D point-cloud images. This system detects the position of the observer’s fingertip with a motion sensor, which it uses to calculate the complex amplitude distribution for the hologram. Because the calculated distribution is added to or subtracted from the complex amplitude distribution of the previous frame, the calculation time per frame is independent of the number of points comprising the 3D point cloud. Then, the system can quickly update the hologram even when the number of points comprising the 3D point cloud is increased. Because the 3D point-cloud image reconstructed from the calculated hologram is projected at the same position as the observer’s fingertip with almost no latency, the system can draw and erase a 3D point-cloud image through interactions with the observer’s fingertip. We experimentally confirmed that the system successfully draws and erases a 3D point-cloud image.