Motion pattern-based crowd scene classification using histogram of angular deviations of trajectories

Automated crowd behaviour analysis and monitoring is a challenging task due to the unpredictable nature of the crowd within a particular scene and across different scenes. The prior knowledge of the type of scene under consideration is a crucial mid-level information, which could be utilized to develop robust crowd behaviour analysis systems. In this paper, we propose an approach to automatically detect the type of a crowded scene based on the global motion patterns of the objects within the scene. Three different types of scenes whose global motion pattern characteristics vary from uniform to non-uniform are considered in this work, namely structured, semi-structured, and unstructured scenes, respectively. To capture the global motion pattern characteristics of an input crowd scene, we first extract the motion information in the form of trajectories using a key-point tracker and then compute the average angular orientation feature of each trajectory. This paper utilizes these angular features to introduce a novel feature vector, termed as Histogram of Angular Deviations (HAD), which depicts the distribution of the pair-wise angular deviation values for each trajectory vector. Since angular deviation information is resistant to changes in scene perspectives, we consider it as a key feature for distinguishing the scene types. To evaluate the effectiveness of the proposed HAD-based feature vector in classifying the crowded scenes, we build a crowd scene classification model by training the classical machine learning algorithms on the publicly available Collective Motion Database. The experimental results demonstrate the superior crowd classification performance of the proposed approach as compared to the existing methods. In addition to this, we propose a technique based on quantizing the angular deviation values to reduce the feature dimension and subsequently introduce a novel crowd scene structuredness index to quantify the structuredness of an input crowded scene based on its HAD.

Turning a Telecom Fiber-Optic Cable into an Ultradense Seismic Array for Rapid Postearthquake Response in an Urban Area

Aftershock-monitoring networks deployed in the epicentral area of a damaging earthquake play important roles in earthquake early warning and ShakeMap estimation, which contribute to hazard mitigation. Using distributed acoustic sensing (DAS) technology with dark fiber can significantly reduce deployment time and cost, and improve spatial sampling, both of which help capture more aftershocks. In this study, we used a 7.6 km dark fiber in Tangshan, China, to monitor seismicity after the 12 July 2020 Ms 5.1 earthquake. The DAS array detected dozens of earthquakes missed by the local permanent network that doubled the number of aftershocks. The relocated aftershocks are distributed mainly north of the DAS array, and the ground-motion pattern changes also hint small-scale features. Our successful results demonstrate the feasibility of using DAS and dark fiber for rapid postearthquake response.

Linear Relationships Among the Hand and Clubhead Motion Characteristics in Golf Driving in Skilled Male Golfers

The purpose of this study was to investigate the linear relationships among the hand/clubhead motion characteristics in golf driving in skilled male golfers (n = 66; handicap ≤ 3). The hand motion plane (HMP) and functional swing plane (FSP) angles, the HMP–FSP angle gaps, the planarity characteristics of the off-plane motion of the clubhead, and the attack angles were computed from the drives captured by an optical motion capture system. The HMP angles were identified as the key variables, as the HMP and FSP angles were intercorrelated, but the plane angle gaps, the planarity bias, and the attack angles showed correlations to the HMP angles primarily. Three main swing pattern clusters were identified. The parallel HMP–FSP alignment pattern with a small direction gap was associated with neutral planarity and planar swing pattern. The inward alignment pattern with a large inward direction gap was characterized by flat planes, follow-through-centric planarity, spiral swing pattern, and inward/downward impact. The outward alignment pattern with a large outward direction gap was associated with steep planes, downswing-centric planarity, reverse spiral swing, and outward/upward impact. The findings suggest that practical drills targeting the hand motion pattern can be effective in holistically reprogramming the swing pattern.

Left Ventricular Systolic Motion Pattern Differs Among Patients With Left Bundle Branch Block Patterns

Purpose:The study aimed to investigate left ventricular (LV) motion pattern in patients with LBBB patterns including patients with pacemaker rhythm (PM), type B Wolff-Parkinson-White syndrome (B-WPW), premature ventricular complexes originating from the right ventricular outflow tract (RVOT-PVC), and complete left bundle branch block (CLBBB).Methods: Two-dimensional speckle tracking was used to evaluate peak value and time to peak value of the LV twist, LV apex rotation, and LV base rotation in patients with PM, B-WPW, RVOT-PVC, and CLBBB with normal LV ejection fraction, and in age-matched control subjects.Results: The LV motion patterns were altered in all patients compared to the control groups. Patients with PM and CLBBB had a similar LV motion pattern with a reduced peak value of LV apex rotation and LV twist. Patients with B-WPW demonstrated the opposite trend in the reduction of LV rotation peak value, which was more dominant in the basal layer. The most impairment in the LV twist/rotation peak value was identified in patients with RVOT-PVC. Compared to the control group, the apical-basal rotation delay was prolonged in patients with CLBBB, followed by those with B-WPW, RVAP, and RVOT-PVC.Conclusion: The LV motion patterns were different among patients with different patterns of LBBB. CLBBB and PM demonstrated a reduction in LV twist/rotation that was pronounced in the apical layer, B-WPW showed a reduction in the basal layer, and RVOT-PVC in both layers. CLBBB had the most pronounced LV apical-basal rotation dyssynchrony.

Human Motion Representation and Motion Pattern Recognition Based on Complex Fuzzy Theory

With the development of science and technology, the introduction of virtual reality technology has pushed the development of human-computer interaction technology to a new height. The combination of virtual reality and human-computer interaction technology has been applied more and more in military simulation, medical rehabilitation, game creation, and other fields. Action is the basis of human behavior. Among them, human behavior and action analysis is an important research direction. In human behavior and action, recognition research based on behavior and action has the characteristics of convenience, intuition, strong interaction, rich expression information, and so on. It has become the first choice of many researchers for human behavior analysis. However, human motion and motion pictures are complex objects with many ambiguous factors, which are difficult to express and process. Traditional motion recognition is usually based on two-dimensional color images, while two-dimensional RGB images are vulnerable to background disturbance, light, environment, and other factors that interfere with human target detection. In recent years, more and more researchers have begun to use fuzzy mathematics theory to identify human behaviors. The plantar pressure data under different motion modes were collected through experiments, and the current gait information was analyzed. The key gait events including toe-off and heel touch were identified by dynamic baseline monitoring. For the error monitoring of key gait events, the screen window is used to filter the repeated recognition events in a certain period of time, which greatly improves the recognition accuracy and provides important gait information for motion pattern recognition. The similarity matching is performed on each template, the correct rate of motion feature extraction is 90.2%, and the correct rate of motion pattern recognition is 96.3%, which verifies the feasibility and effectiveness of human motion recognition based on fuzzy theory. It is hoped to provide processing techniques and application examples for artificial intelligence recognition applications.

Biomechanics of the Canine Elbow Joint

The canine elbow joint is a complex joint, whose musculoskeletal anatomy is well investigated. During the last 30 years kinematic analysis has gained importance in veterinary research and kinematics of the healthy and medial coronoid disease affected canine elbow joint are progressively investigated. Video-kinematographic analysis represents the most commonly used technique and multiple studies have investigated the range of motion, angular velocity, duration of swing and stance phase, stride length and other kinematic parameters, mostly in the sagittal plane only. However, this technique is more error-prone and data gained by video-kinematography represent the kinematics of the whole limb including the soft tissue envelope. A more precise evaluation of the in vivo bone and joint movement can only been achieved using fluoroscopic kinematography. Based on recent studies significant differences in the motion pattern between healthy joints and elbows with medial coronoid disease could be detected. Thereby not only adaptive changes, caused by pain and lameness, could be described, but primary changes in the micromotion of the joint forming bones could be found, which potentially represent new factors in the pathogenesis of medial coronoid disease. This chapter gives a review of current literature on elbow joint kinematics, with particular focus onto pathologic biomechanics in dysplastic canine elbows.

Performance Analysis of Road Intersections under Heterogeneous Traffic Conditions: A Review

The rapid growth of traffic in most countries exceeds the current transport system's threshold level and requires a more efficient and practical approach to be addressed. As the renovation of urban transportation infrastructure is not feasible, alternatives to the problem are urgently needed. This paper addresses the Performance Analysis of Road Intersections under Heterogeneous Traffic Conditions. At whatever point two or significantly more streets converge or cross, users of these streets should change their mobility to prevent a collision. This adjustment can take the form of a speed drop or a change in their motion pattern. In several regions of the world, traffic is a mixture of large distribution of various vehicle kinds. Hence users of a signalized crossroads in vehicles are a heterogeneous mix. The current study has involves review based on 5 selected papers analysing findings and drawing conclusion along with posing future questions.

Classification method of marine target motion pattern based on spatial-temporal trajectories

Classifying the motion pattern of marine targets is of important significance to promote target surveillance and management efficiency of marine area and to guarantee sea route safety. This paper proposes a moving target classification algorithm model based on channel extraction-segmentation-LCSCA-lp norm minimization. The algorithm firstly analyzes the entire distribution of channels in specific region, and defines the categories of potential ship motion patterns; on this basis, through secondary segmentation processing method, it obtains several line segment trajectories as training sample sets, to improve the accuracy of classification algorithm; then, it further uses the Leastsquares Cubic Spline Curves Approximation (LCSCA) technology to represent the training sample sets, and builds a motion pattern classification sample dictionary; finally, it uses lp norm minimized sparse representation classification model to realize the classification of motion patterns. The verification experiment based on real spatial-temporal trajectory dataset indicates that, this method can effectively realize the motion pattern classification of marine targets, and shows better time performance and classification accuracy than other representative classification methods.