Abstract: In this paper we present a method for body motion analysis in dance using multiple Kinect sensors. The proposed method applies fusion to combine the skeletal tracking data of multiple sensors in order to solve occlusion and self-occlusion tracking problems and increase the robustness of skeletal tracking. The fused skeletal data is split into five different body parts (torso, left hand, right hand, left leg and right leg), which are then transformed to allow view invariant posture recognition. For each part, a posture vocabulary is generated by performing k-means clustering on a large set of unlabeled postures. Finally, body part postures are combined into body posture sequences and Hidden Conditional Random Fields (HCRF) classifier is used to recognize motion patterns (e.g. dance figures). For the evaluation of the proposed method, Tsamiko dancers are captured using multiple Kinect sensors and experimental results are presented to demonstrate the high recognition accuracy of the proposed method.

Abstract: Disclosed are techniques that provide a “best” picture taken within a few seconds of the moment when a capture command is received (e.g., when the “shutter” button is pressed). In some situations, several still images are automatically (that is, without the user's input) captured. These images are compared to find a “best” image that is presented to the photographer for consideration. Video is also captured automatically and analyzed to see if there is an action scene or other motion content around the time of the capture command. If the analysis reveals anything interesting, then the video clip is presented to the photographer. The video clip may be cropped to match the still-capture scene and to remove transitory parts. Higher-precision horizon detection may be provided based on motion analysis and on pixel-data analysis.

Abstract: The invention generally relates to motion analysis systems and methods of use thereof. In certain aspects, the system includes an image capture device, at least one accelerometer, and a central processing unit (CPU) with storage coupled thereto for storing instructions that when executed by the CPU cause the CPU to receive a first set of motion data from the image capture device related to at least one joint of a subject while the subject is performing a task and receive a second set of motion data from the accelerometer related to the at least one joint of the subject while the subject is performing the task. The CPU also calculates kinematic and/or kinetic information about the at least one joint of a subject from a combination of the first and second sets of motion data, and outputs the kinematic and/or kinetic information for purposes of assessing a movement disorder.

Abstract: A motion analysis device includes a calculation unit which specifies a first imaginary plane, that is, a shaft plane formed by a first line segment representing a direction in which a shaft part of a sporting gear in a static posture extends and a second line segment representing a ball hitting direction, with the use of an output from an inertial sensor.

Abstract: The invention discloses a face unlocking method based on motion analysis. The method comprises the steps that image information is collected, if the image information contains face image information, face recognition is conducted on the face image information, and a recognized face image is obtained; if the recognized face image is matched with a preset face image, and prompt information is sent out to prompt a user to make a corresponding face motion according to the prompt information; a face motion image of the user is collected, and the face motion of the user is analyzed; if the face motion of the user is matched with the face motion which is made by the user according to the requirement of the prompt information, a terminal device is unlocked. According to the face unlocking method, users without permissions are prevented from logging in to the terminal device through pictures or videos in a cracking mode, and face unlocking safety is improved. The invention further discloses a face unlocking device and terminal based on motion analysis.

Abstract: Current trends in swimming biomechanics are focused on accurate measurements. Nowadays, reliable calibration methods have been proposed to reach an accuracy of about 1 mm on rigid structure. But the question remains about the final accuracy for three-dimensional hand kinematics measurement during the underwater phase of front crawl swimming. Furthermore, most research is based on manual tracking with two or more cameras. In this paper we propose a protocol to acquire three-dimensional hand kinematics when swimming in a specific pool with a motion analysis system behind windows. Results highlight the benefits of using such a system in terms of accuracy and feasibility: the time allowed for post-processing is ten times lower and the quantified improved accuracy is better than with manual tracking.

Abstract: Motion analysis based moving object detection from UAV aerial image is still an unsolved issue due to inconsideration of proper motion estimation. Existing moving object detection approaches from UAV aerial images did not deal with motion based pixel intensity measurement to detect moving object robustly. Besides current research on moving object detection from UAV aerial images mostly depends on either frame difference or segmentation approach separately. There are two main purposes for this research: firstly to develop a new motion model called DMM (dynamic motion model) and secondly to apply the proposed segmentation approach SUED (segmentation using edge based dilation) using frame difference embedded together with DMM model. The proposed DMM model provides effective search windows based on the highest pixel intensity to segment only specific area for moving object rather than searching the whole area of the frame using SUED. At each stage of the proposed scheme, experimental fusion of the DMM and SUED produces extracted moving objects faithfully. Experimental result reveals that the proposed DMM and SUED have successfully demonstrated the validity of the proposed methodology.

Abstract: Objective. To demonstrate the technical feasibility and the potential interest of using a digital optical camera inside the MR magnet bore for monitoring the breathing cycle and subsequently gating the PRFS MR thermometry, MR-ARFI measurement, and MRgHIFU sonication in the upper abdomen. Materials and Methods. A digital camera was reengineered to remove its magnetic parts and was further equipped with a 7 m long USB cable. The system was electromagnetically shielded and operated inside the bore of a closed 3T clinical scanner. Suitable triggers were generated based on real-time motion analysis of the images produced by the camera (resolution pixels, 30 fps). Respiratory-gated MR-ARFI prepared MRgHIFU ablation was performed in the kidney and liver of two sheep in vivo, under general anaesthesia and ventilator-driven forced breathing. Results. The optical device demonstrated very good MR compatibility. The current setup permitted the acquisition of motion artefact-free and high resolution MR 2D ARFI and multiplanar interleaved PRFS thermometry (average SNR 30 in liver and 56 in kidney). Microscopic histology indicated precise focal lesions with sharply delineated margins following the respiratory-gated HIFU sonications. Conclusion. The proof-of-concept for respiratory motion management in MRgHIFU using an in-bore digital camera has been validated in vivo.

Abstract: In this paper, we propose a nonparametric camera motion descriptor for video shot classification. In the proposed method, a motion vector field (MVF) is constructed for each consecutive video frame by computing the motion vector (MV) of each macroblock. Then, the MVFs are divided into a number of local region of equal size. Next, the inconsistent/noisy MVs of each local region are eliminated by a motion consistency analysis. The remaining MVs of each local region from a number of consecutive frames are further collected for a compact representation. Initially, a matrix is formed using the MVs. Then, the matrix is decomposed using a singular value decomposition technique to represent the dominant motion. Finally, the angle of the most variance retaining principal component is computed and quantized to represent the motion of a local region by using a histogram. In order to represent the global camera motion, the local histograms are combined. The effectiveness of the proposed motion descriptor for video shot classification is tested by using a support vector machine. First, the proposed camera motion descriptors for video shots classification are computed on a video data set consisting of regular camera motion patterns (e. g., pan, zoom, tilt, static). Then, we apply the camera motion descriptors with an extended set of features to the classification of cinematographic shots. The experimental results show that the proposed shot level camera motion descriptor has a strong discriminative capability to classify different camera motion patterns of different videos effectively. We also show that our approach outperforms state-of-the-art methods.

Abstract: In this paper we propose a novel approach to detect anomalies in crowded scenes. This is achieved by analyzing the crowd behavior by extracting the corner features. For each corner feature we collect a set of motion features. The motion features are used to train an MLP neural network during the training stage, and the behavior of crowd is inferred on the test samples. Considering the difficulty of tracking individuals in dense crowds due to multiple occlusions and clutter, in this work we extract corner features and consider them as an approximate representation of the people motion. Corner features are then advected over a temporal window through optical flow tracking. Corner features well match the motion of individuals and their consistency, and accuracy is higher both in structured and unstructured crowded scenes compared to other detectors. In the current work, corner features are exploited to extract motion information, which is used as input prior to train the neural network. The MLP neural network is subsequently used to highlight the dominant corner features that can reveal an anomaly in the crowded scenes. The experimental evaluation is conducted on a set of benchmark video sequences commonly used for crowd motion analysis. In addition, we show that our approach outperforms a state of the art technique proposed in.

Abstract: This paper deals with the measurement of spherical impactor positions, velocities and acceleration (translations and rotations) during medium velocity impact experiments performed with gas-gun devices. A dedicated 2D Digital Image Correlation (DIC) technique based on customized interpolation functions is presented. The proposed method considers the rotations of the projectile which a standard subset-based DIC technique would undoubtedly have difficulty managing. Emphasis is placed on metrological performance and various validations are proposed. Measurements are additionally compared to those retrieved with conventional techniques. This DIC method provides a precise quantification of projectile motion and impact loads during gas-gun tests with a single high speed camera.

Abstract: In this paper, we describe a novel methodology for dance learning and evaluation using multi-sensor and 3D gaming technology. The learners are captured during dancing, while an avatar visualizes their motion using fused input from multiple sensors. Motion analysis and fuzzy-logic are employed for the evaluation of the learners’ performance against the performance of an expert. Specifically, a two level Fuzzy Inference System is proposed which uses as input low level skeletal data and high level motion recognition probabilities for the evaluation of dancer’s performance. Tests with real dancers, both learners and experts, dancing Tsamiko, a very popular traditional Greek dance, are presented showing the potential of the proposed method.

Abstract: In this paper, a low-cost motion analysis system using a wireless ultrasonic sensor network is proposed and investigated. A methodology has been developed to extract spatial-temporal gait parameters including stride length, stride duration, stride velocity, stride cadence, and stride symmetry from 3D foot displacements estimated by the combination of spherical positioning technique and unscented Kalman filter. The performance of this system is validated against a camera-based system in the laboratory with 10 healthy volunteers. Numerical results show the feasibility of the proposed system with average error of 2.7% for all the estimated gait parameters. The influence of walking speed on the measurement accuracy of proposed system is also evaluated. Statistical analysis demonstrates its capability of being used as a gait assessment tool for some medical applications.

Abstract: A motion detection device specifies a movement of at least one of a subject and a sporting gear as an indicator of a trigger signal, using an output from an inertial sensor. The movement of at least one of the subject and the sporting gear is specified in the output from the inertial sensor. The trigger signal is generated according to the specified movement. The subject causes the trigger signal to be generated at proper timing through his or her own movement.

Abstract: In computer vision related applications, video analysis of human walking motion is currently one of the most active research topics. The task of analyzing human walking can be divided into three distinct subtasks – human detection or segmentation, motion tracking and walking pose analysis. Typically, the analysis of the human walking starts with the extraction of motion information, detection of the presence of humans in the sequences of frames and then followed by analysis of events related to walking. This paper presents a survey of different methodologies used for human walking motion analysis, approaches used for human detection or segmentation, various tracking methods, approaches for pose estimation and pose analysis. The common data sets available for building robust, automatic and intelligent systems to understand “walking” motion are also included. Finally, uses of unsupervised techniques for analysing human walking are highlighted. Human walking motion is a subset of a broad topic of human motion analysis.

Abstract: There has been an increasing use of pre-recorded motion capture data for animating virtual characters and synthesising different actions; it is although a necessity to establish a resultful method for indexing, classifying and retrieving motion. In this paper, we propose a method that can automatically extract motion qualities from dance performances, in terms of Laban Movement Analysis (LMA), for motion analysis and indexing purposes. The main objectives of this study is to analyse the motion information of different dance performances, using the LMA components, and extract those features that are indicative of certain emotions or actions. LMA encodes motions using four components, Body, Effort, Shape and Space, which represent a wide array of structural, geometric, and dynamic features of human motion. A deeper analysis of how these features change on different movements is presented, investigating the correlations between the performers' acting emotional state and its characteristics, thus indicating the importance and the effect of each feature for the classification of the motion. Understanding the quality of the movement helps to apprehend the intentions of the performer, providing a representative search space for indexing motions.

Abstract: This study investigated the reliability of the recently released low-cost NaturalPoint OptiTrack 250e camera system across different measurement designs. Results are compared to an already well-established motion capture system from Vicon Motion Systems Ltd (Oxford, UK). The OptiTrack performed well across measurement conditions. Provided with the AMASS software kit from C-Motion (Germantown, MD, USA), nine distances from three rigid bodies (ten markers) were used to calculate measurement accuracy. Independent t-tests, a one-way multivariate analysis of variance, intra-class correlation coefficients, and the standard error of measurement were computed for all conditions to evaluate the differences and the reliability of the systems. The results suggest that the NaturalPoint OptiTrack 250e camera system is a reliable working system that can certainly be used in biomechanics and other related fields.

Abstract: A methodology for motion analysis and hand tracking based on adaptive probabilistic models is presented. This is done by integrating a deterministic clustering framework and a particle filter together in real time. The skin color of a human hand is firstly segmented. A Bayesian classifier and an adaptive process are utilized for determining skin color probabilities. The methodology enables us to deal with luminance changes. After that, we determine the probabilities of the fingertips by using semicircle models for fitting curves to fingertips. Following this, the deterministic clustering algorithm is utilized to search for regions of interest, and then the Sequential Monte Carlo is also performed to track the fingertips efficiently. Representative experimental results are also included to ensure workability of the proposed framework. Several issues about using the presented method in embedded systems are discussed. The method presented can be used to further develop the associated applications of embedded robotic and virtual reality.

Abstract: Motion analysis for moving object from UAV aerial images is still an unsolved issue in computer vision research field due to fast abrupt motion of object and UAV, low resolution, noisy imagery, cluttered background, low contrast and small target size. The main reason for the inability to handle motion is the weakness of existing approaches for moving object detection. This paper presents critical analysis of the various methods used for motion analysis which states lack of relevancy with motion analysis along with some unsolved problems need to be solved for optimum performance of moving objects detection from UAV aerial images. The overall reviews proposed in this paper have been extensively studied in various research papers which can significantly contribute to computer vision research and can be potential for future development and direction for future research.

Abstract: Laser pointers are one of the most widely used interactive and pointing devices in different human-computer interaction systems. Existing approaches to vision-based laser spot tracking are designed for controlled indoor environments with the main assumption that the laser spot is very bright, if not the brightest, spot in images. In this work, we are interested in developing a method for an outdoor, open-space environment, which could be implemented on embedded devices with limited computational resources. Under these circumstances, none of the assumptions of existing methods for laser spot tracking can be applied, yet a novel and fast method with robust performance is required. Throughout the paper, we will propose and evaluate an efficient method based on modified circular Hough transform and Lucas–Kanade motion analysis. Encouraging results on a representative dataset demonstrate the potential of our method in an uncontrolled outdoor environment, while achieving maximal accuracy indoors. Our dataset and ground truth data are made publicly available for further development.

Abstract: Previous work demonstrated that Kinect sensor can be very useful for fall detection. In this work we present a novel approach to fall detection that allows us to achieve reliable fall detection in larger areas through person detection and tracking in dense depth map sequences acquired by an active pan-tilt 3D camera. We demonstrate that both high sensitivity and specificity can be obtained using dense depth images acquired by a ceiling mounted Kinect and executing the proposed algorithms for lying pose detection and motion analysis. The person is extracted using depth region growing and person detection. Language: en

Abstract: Tracking-based video surveillance approaches use a pipe line of processes from capture of frames up to video analysis. All these processes consume too much computational cost and generally it is concentrated in the last step of this framework. Particularly for this step, our paper proposes a method for abnormal motion analysis that ensures efficiency in the inferences with less computational effort. For this, we use a region-based model that uses a mobile grid of subregions constructed from scene's ROI (region of interest). In order to avoid the implementation of the complete framework, we have replaced the previous steps with annotated datasets from the real world. From these annotations, we seek a size of subregion that produces the best result in the abnormal motion detection using GMM (Gaussian Mixture Models) and ROC (Receiver Operating Characteristic) curves. The method proved efficient and useful for abnormal motion analysis, especially in tracking-based approaches. 

Abstract: Summarization of soccer videos has been widely studied due to its worldwide viewers and potential commercial applications. Most existing methods focus on searching for highlight events in soccer videos such as goals, penalty kicks and generating a summary as a list of such events. However, besides highlight events, scenes of intensive competition between players of two teams and emotional moments are also interesting. In this paper, we propose a soccer summarization system which is able to capture highlight events, scenes of intensive competition, and emotional moments. Based on the flow of soccer games, we organize a video summary as follows: first, scenes of intensive competition, second, what events happened, third, who were involved in the events, and finally how players or audience reacted to the events. With this structure, the generated summary is more complete and interesting because it provides both game play and emotional moments. Our system takes broadcast video as input, and divides it into multiple clips based on cinematographic features such as sport video production techniques, the transition of shots, and camera motions. Then, the system evaluates the interest level of each clip to generate a summary. Experimental results and subjective evaluation are carried out to evaluate the quality of the generated summary and the effectiveness of our proposed interest level measure.

Abstract: We present a novel methodology for the analysis of complex object shapes in motion observed by multiple video cameras. In particular, we propose to learn local surface rigidity probabilities (i.e., deformations), and to estimate a mean pose over a temporal sequence. Local deformations can be used for rigidity-based dynamic surface segmentation, while a mean pose can be used as a sequence keyframe or a cluster prototype and has therefore numerous applications, such as motion synthesis or sequential alignment for compression or morphing. We take advantage of recent advances in surface tracking techniques to formulate a generative model of 3D temporal sequences using a probabilistic framework, which conditions shape fitting over all frames to a simple set of intrinsic surface rigidity properties. Surface tracking and rigidity variable estimation can then be formulated as an Expectation-Maximization inference problem and solved by alternatively minimizing two nested fixed point iterations. We show that this framework provides a new fundamental building block for various applications of shape analysis, and achieves comparable tracking performance to state of the art surface tracking techniques on real datasets, even compared to approaches using strong kinematic priors such as rigid skeletons.

Abstract: This study aims to develop a controller for use in the online simulation of two interacting characters. This controller is capable of generalizing two sets of interaction motions of the two characters based on the relationships between the characters. The controller can exhibit similar motions to a captured human motion while reacting in a natural way to the opponent character in real time. To achieve this, we propose a new type of physical model called a coupled inverted pendulum on carts that comprises two inverted pendulum on a cart models, one for each individual, which are coupled by a relationship model. The proposed framework is divided into two steps: motion analysis and motion synthesis. Motion analysis is an offline preprocessing step, which optimizes the control parameters to move the proposed model along a motion capture trajectory of two interacting humans. The optimization procedure generates a coupled pendulum trajectory which represents the relationship between two characters for each frame, and is used as a reference in the synthesis step. In the motion synthesis step, a new coupled pendulum trajectory is planned reflecting the effects of the physical interaction, and the captured reference motions are edited based on the planned trajectory produced by the coupled pendulum trajectory generator. To validate the proposed framework, we used a motion capture data set showing two people performing kickboxing. The proposed controller is able to generalize the behaviors of two humans to different situations such as different speeds and turning speeds in a realistic way in real time.

Abstract: Multidimensional wave digital filters (MDWDF) exhibit the same desirable properties as 1D WDFs, most notably including passivity and therefore guaranteed stability as well as high robustness. A possible application for such MDWDFs may be found in motion analysis of image sequences by means of filters with fan-shaped transfer functions, where content with specific movement information can be extracted. For that matter, a parallel filter bank is needed to differentiate object motion into separate classes. In this paper, a new specialized MDWDF fan filter structure is introduced, possessing both reduced computational complexity and memory requirements compared to existing approaches. Additionally, part of the processing can be shared among all bands, further increasing efficiency.