Postural Features Research Articles

Voxelwise encoding models of body stimuli reveal a representational gradient from low-level visual features to postural features in occipitotemporal cortex

Previous research on body representation in the brain has focused on category-specific representation, using fMRI to investigate the response pattern to body stimuli in occipitotemporal cortex. But the central question of the specific computations involved in body selective regions has not been addressed so far. This study used ultra-high field fMRI and banded ridge regression to investigate the computational mechanisms of coding body images, by comparing the performance of three encoding models in predicting brain activity in occipitotemporal cortex and specifically in the extrastriate body area (EBA). Our results indicate that bodies are encoded in occipitotemporal cortex and in the EBA according to a combination of low-level visual features and postural features.

Shades of expansiveness: Postural expression of dominance, high-arousal positive affect, and warmth.

In addition to the face, bodily posture plays an important role in communicating affective states. Postural expansion-how much space the body takes up-has been much studied as expressing and signaling dominance and pride. The present research aimed to expand research on the range of affect dimensions and affect-laden personality characteristics that are expressed via expansiveness, investigating specific forms of expansiveness and their interactions with other postural elements (e.g., arm position). Using an innovative expression-production method, Study 1 (N = 146) characterized full-body expressions of dominance, joy, hope, and awe; results indicated joy is communicated most expansively and suggested a signature arm position for most feelings. Studies 2 and 3 (Ns = 352 and 183) revealed that other postural features interact with expansiveness to signal dominance (arms akimbo, head raised, stability), as distinct from high-arousal positive affect (arms high up, head raised) and warmth (arms high up, head raised, instability). Together, this research adds needed data on full-body expressions of positive affect states and provides systematic analysis of different affective messages and varieties of postural expansiveness. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

Application of action and posture feature information matching algorithm in college aerobics

With the increasingly rich recreational activities of college students, diversified learning needs and complex physical education resources bring challenges to college physical education. In order to optimize the teaching effect of calisthenics in colleges and universities, this paper proposes a matching method of posture features based on dynamic time warping. Firstly, the dynamic time warping algorithm is introduced, and then the matching model of posture features of calisthenics is constructed on this basis. Finally, the application effect of the model is tested and analyzed. The results show that the model can capture the video frame accurately, and its matching accuracy reaches 94.8%, which greatly improves the accuracy of aerobics action recognition. Good posture matching effect is conducive to teachers to obtain a clear learning situation of students, and provide a reference for adjusting the teaching progress and teaching methods of calisthenics. Under the teaching mode of this model, the average professional score of the students in calisthenics reaches 85 points, which is 25 points higher than that under the convolutional neural network model. It also proves the validity and feasibility of this method in the course of calisthenics in colleges and universities, which is beneficial to enhance the physical quality of college students and enrich the content of calisthenics teaching.

Restitution of the size of postural features in the frontal plane after loading with the weight of school items carried with the right and left hand in 7-year-old pupils of both sexes

Introduction. The analysis of the pupil’s environment is a set of stressors in the field of human ecology consisting not only of the genetic factor but also of the epigenetic one. Material and methods. The study of body posture was carried out in a group of 65 pupils at the age of 7, using the mora projection method in the following eight positions: (four positions for the right-hand thrust and four for the left-hand thrust): 1- habitual posture, 2 - posture after pulling a container with school supplies with one hand for 10 minutes, 3 – one minute after removing the load, 4 - two minutes after removing the load. The measurement of physical fitness was performed using the Sekita test. Results. The significance of differences between measurement 1, 2, 3, and 4 was analysed to determine the restitution of the size of traits after loading and their correlation with physical fitness to examine the relationship with the studied differences. Conclusions. (1) After removing the load, statistically significant restitution occurred after the first and second minute. Restitution was incomplete. (2) In right-hand carriage by boys, endurance significantly correlated with restitution, and among girls it was additionally speed and agility. As regards girls, physical fitness revealed more frequent relationships with restitution. (3) In left-hand carriage by boys, after the first minute, restitution correlated with endurance, power, agility and overall physical fitness, and after two minutes, additionally with strength, while among girls with strength, power, and endurance. After two minutes, restitution correlated with speed and agility in addition to the abovementioned postural features. As far as girls are concerned, physical fitness more often correlated with restitution. (4) Due to incomplete restitution after one and two minutes, asymmetrical carriage is not recommended to children aged 7 years. Physical fitness demonstrated by children does not lead to full restitution of the examined postural features, which suggests its low level and immature correctional and compensational processes.

Deep Clustering Efficient Learning Network for Motion Recognition Based on Self-Attention Mechanism

Multi-person behavior event recognition has become an increasingly challenging research field in human–computer interaction. With the rapid development of deep learning and computer vision, it plays an important role in the inference and analysis of real sports events, that is, given the video frequency of sports events, when letting it analyze and judge the behavior trend of athletes, often faced with the limitations of large-scale data sets and hardware, it takes a lot of time, and the accuracy of the results is not high. Therefore, we propose a deep clustering learning network for motion recognition under the self-attention mechanism, which can efficiently solve the accuracy and efficiency problems of sports event analysis and judgment. This method can not only solve the problem of gradient disappearance and explosion in the recurrent neural network (RNN), but also capture the internal correlation between multiple people on the sports field for identification, etc., by using the long and short-term memory network (LSTM), and combine the motion coding information in the key frames with the deep embedded clustering (DEC) to better analyze and judge the complex behavior change types of athletes. In addition, by using the self-attention mechanism, we can not only analyze the whole process of the sports video macroscopically, but also focus on the specific attributes of the movement, extract the key posture features of the athletes, further enhance the features, effectively reduce the amount of parameters in the calculation process of self-attention, reduce the computational complexity, and maintain the ability to capture details. The accuracy and efficiency of reasoning and judgment are improved. Through verification on large video datasets of mainstream sports, we achieved high accuracy and improved the efficiency of inference and prediction. It is proved that the method is effective and feasible in the analysis and reasoning of sports videos.

Personalized stability monitoring based on body postures of construction workers working at heights

Fall from heights accidents are one of the most frequent causes of death in the construction industry. Many fall-from-height accidents are related to stability issues and stability is critical for construction workers working at heights. Thus, stability monitoring of workers is important for proactive accident prevention. However, workers’ stability is highly personalized due to differences in workers’ physical characteristics and habits. Little attention has been paid to the personalized posture-based stability analysis of workers working at heights. This study proposes a personalized stability monitoring framework based on workers' body posture patterns when working at heights. The proposed method includes two main components: posture recognition and stability monitoring. First, OpenPose is used to extract the coordinates of workers’ posture key points from video clips. Two posture features, duration and count, are extracted to reflect workload and frequency. Secondly, a two-stage stability monitoring framework, including instability detection and instability evaluation, is designed based on the Gaussian model and Gaussian mixture model. Finally, the proposed framework is validated by on-site construction videos of workers working at height. The validation results showed the accuracy of 84.38% and the precision of 81.25% in identifying the stable status of a subject. The robustness of the personalised monitoring method was validated through comparisons with five other workers. The study provides a practical reference for active safety monitoring for workers with high fall-from-height risk. It also helps to extend personalized and adaptive behaviour-based safety training for construction workers.

Fatigue detection method for UAV remote pilot based on multi feature fusion

<abstract> <p>In recent years, UAV industry is developing rapidly and vigorously. However, so far, there is no relevant research on the fatigue detection method for UAV remote pilot, which is the core technology to ensure the flight safety of UAV. Aiming at this problem, a fatigue detection method for UAV remote pilot is proposed in this paper. Specifically, we first build a UAV operator fatigue detection database (OFDD). By analyzing the fatigue features in the database, we find that multiple facial features are highly correlated to the fatigue state, especially the head posture, and the temporal information is essential for distinguish between yawn and speaking in the study of UAV remote pilot fatigue detection. Based on these findings, a fatigue detection method for UAV remote pilots was proposed by efficiently locating the related facial regions, a multiple features extraction module to extract the eye, mouth and head posture features, and an efficient temporal fatigue decision module based on SVM. The experimental results show that this method not only performs well on the traditional driver dataset, but also achieves an accuracy rate of 97.05%; and it achieves the highest detection accuracy rate of 97.32% on the UAV remote pilots fatigue detection dataset OFDD.</p> </abstract>

Person Tracking by Fusing Posture Data From UAV Video and Wearable Sensors

In this article, a novel framework that fuses the posture data taken by a drone (or unmanned aerial vehicle, UAV) camera and the wearable sensors data recorded by smartwatches is proposed. The framework is designed for continuously tracking persons in a drone view by analyzing location-independent human posture features and correctly tagging smartwatch identities (IDs) and personal profiles to video human objects, thus conquering the former work in requiring ground markers. Person detection, ID assignment, and pose estimation are integrated into our framework to obtain recognized human postures. These recognized postures are then paired with those from the wearable sensors. Through fusing common postures, such as standing, walking, jumping, and falling down, person tracking accuracy by UAV up to 95.36% can be attained in our testing scenarios.

Recognizing elderly peoples by analyzing their walking pattern using body posture skeleton

The increasing age of the population has become a significant concern internationally. During the COVID-19 pandemic situation, it has been seen that the most sensitive and affected class of the population is the class of Elder’s. It is therefore necessary to track the movement and behavior of the old persons. This kind of monitoring could help them in providing assistance in their needy time. Our objective is to develop an approach to classify elderly people using skeleton data for their assistance. OpenPose algorithm is used here to detect human skeletons (joint positions) from the video sequences. OpenPose algorithm with a sliding window of size ‘N’ is used to achieve a real-time posture recognition framework. Posture features from each extracted skeleton are then used to build a classifier for recognizing elderly people. We also introduce here a new dataset that includes old person walk and young person walk video’s. The experimental outcomes reveal that the proposed method has achieved up to 98.45% training accuracy and 96.16% testing accuracy for deep feed-forward neural network (FFNN) classifier. This asserts the effectiveness of the approach.

Investigation of the Mediating Effect of Strategic Posture on the Relationship between Environmental Conditions and Firm Performance on the Logistics Sector

The effects of environmental conditions on firm performance are investigated in this study. Within the scope of the research, the relationships between the strategic posture and the performance of logistics companies in varying environmental conditions were examined. During this study, the interaction between variables was also investigated by predicting the presence of the mediating effect of strategic posture. In this context, a research model and related research hypotheses were developed. The created research model was comprised of the three-dimension of environmental conditions developed by Dess and Beard (1984), six dimensions of strategic stance developed by Venkatraman (1989), and firm performance variables. A survey related to the research was conducted with 264 people working in managerial positions in 218 logistics companies operating within the scope of the research to test the hypotheses in the research model. The analysis of the obtained data was performed by the Structural Equation Modeling (SEM) method utilizing the SPSS and AMOS software program. According to the analysis results, it was determined that the strategic posture variable has a full mediating effect between environmental conditions and firm performance. As a result, by enabling logistics companies to realize their strategic posture features, information was provided to guide them on how to improve their performance in changing environmental conditions.

Classroom Behavior Analysis and Evaluation in Physical Education by Using Structure Representation

Behavior analysis plays a critical role in physical education. This paper resorts to computer vision technology to establish a classroom behavior analysis system for physical education. First, the behavior video is collected by a Kinect camera. Then, the behavior is recognized based on the symbiotic relationship and geometric constraints between human posture and interactive objects. The human skeleton is used to describe the behavior subject and the local area boundary boxes are divided with each node in the skeleton as the center. The human posture features are used to learn a structural classification model to recognize human behavior sequence. Finally, the behavior recognition results are used to analyze physical education. The experimental results show that the proposed behavior analysis framework can accurately recognize human behavior during physical education classes.

Longitudinal Monitoring of Progressive Supranuclear Palsy using Body-Worn Movement Sensors.

We have previously shown that wearable technology and machine learning techniques can accurately discriminate between progressive supranuclear palsy (PSP), Parkinson's disease, and healthy controls. To date these techniques have not been applied in longitudinal studies of disease progression in PSP. We aimed to establish whether data collected by a body-worn inertial measurement unit (IMU) network could predict clinical rating scale scores in PSP and whether it could be used to track disease progression. We studied gait and postural stability in 17 participants with PSP over five visits at 3-month intervals. Participants performed a 2-minute walk and an assessment of postural stability by standing for 30seconds with their eyes closed, while wearing an array of six IMUs. Thirty-two gait and posture features were identified, which progressed significantly with time. A simple linear regression model incorporating the three features with the clearest progression pattern was able to detect statistically significant progression 3 months in advance of the clinical scores. A more complex linear regression and a random forest approach did not improve on this. The reduced variability of the models, in comparison to clinical rating scales, allows a significant change in disease status from baseline to be observed at an earlier stage. The current study sheds light on the individual features that are important in tracking disease progression. © 2022 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.

3D Human Motion Posture Tracking Method Using Multilabel Transfer Learning

To overcome the high position and posture angle tracking error, long tracking loss time and posture tracking update response time, and low fitness problem of traditional human motion posture tracking methods, in this paper, a three-dimensional (3D) human motion posture tracking method using multilabel transfer learning is proposed. According to the human structure composition and degree of freedom constraints, the 3D human joint skeleton model is constructed to generate the 3D human pose image and perform the noise reduction operation. The background difference is used to detect the 3D human moving target. Using multilabel transfer learning, human motion posture features are extracted from joint position and joint angle, and the estimation results of 3D human motion posture are obtained. The tracking error of human motion posture is corrected by three-step search, and the visual 3D human motion posture tracking results are output. The results show that, compared with the traditional human motion posture tracking method, the position and posture angle tracking errors of the proposed method are 2.18 mm and 0.178 deg, respectively. The tracking loss time and posture tracking update response time are shorter, which proves that the proposed method has more advantages in tracking accuracy and higher adaptability.

Comprehensive analysis of locomotion dynamics in the protochordate Ciona intestinalis reveals how neuromodulators flexibly shape its behavioral repertoire.

Vertebrate nervous systems can generate a remarkable diversity of behaviors. However, our understanding of how behaviors may have evolved in the chordate lineage is limited by the lack of neuroethological studies leveraging our closest invertebrate relatives. Here, we combine high-throughput video acquisition with pharmacological perturbations of bioamine signaling to systematically reveal the global structure of the motor behavioral repertoire in the Ciona intestinalis larvae. Most of Ciona's postural variance can be captured by 6 basic shapes, which we term "eigencionas." Motif analysis of postural time series revealed numerous stereotyped behavioral maneuvers including "startle-like" and "beat-and-glide." Employing computational modeling of swimming dynamics and spatiotemporal embedding of postural features revealed that behavioral differences are generated at the levels of motor modules and the transitions between, which may in part be modulated by bioamines. Finally, we show that flexible motor module usage gives rise to diverse behaviors in response to different light stimuli.

Bidirectional Posture-Appearance Interaction Network for Driver Behavior Recognition

Driver behavior recognition has become one of the most important tasks for intelligent vehicles. This task, however, is very challenging since the background contents in real-world driving scenarios are often very complex. More critically, the difference between driving behaviors is often very minor, making it extremely difficult to distinguish them. Existing methods often rely only on RGB frames (or skeleton data), which may fail to capture the minor differences between behaviors and appearance information of objects simultaneously and thus fail to achieve promising performance. To address the above issues, in this paper, we propose a bidirectional posture-appearance interaction network (BPAI-Net), which simultaneously considers RGB frames and skeleton ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">i.e.</i> , posture) data for driver behavior recognition. Specifically, we propose a posture-guided convolutional neural network (PG-CNN) and an appearance-guided graph convolutional network (AG-GCN) to extract appearance and posture features, respectively. To exploit the complementary information between appearance and posture, we use the appearance features from PG-CNN for guiding AG-GCN to exploit the contextual information ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">e.g.</i> , nearby objects) to enhance posture features. Then, we use the enhanced posture features from AG-GCN to help PG-CNN focus on critical local areas of video frames that are related to driver behaviors. In this sense, we are able to use the interaction between two modalities to extract more discriminative features and thus improve the recognition accuracy. Experimental results on Drive&Act dataset show that our method outperforms state-of-the-art methods by a large margin (67.83% vs. 63.64%). Furthermore, we collect a bus driver behavior recognition dataset and yield consistent performance gain against baseline methods, demonstrating the effectiveness of our method in real-world applications. The source code and trained models are available at github.com/SCUT-AILab/BPAI-Net/.

Scoliosis Detection Based on Feature Extraction from Region-of-Interest

In recent years, the incidence of scoliosis is rising among adolescents. Considering the radiation hazards of X-ray detection, this paper intends to develop an effective non-radiation detection method for scoliosis. The research method consists of the following steps: (1) Collect clear an image of the back of the patient with a high-resolution digital camera, and optimize the image through preprocessing; (2) Segment the region of interest (ROI) of the back and spine to reduce the complexity of subsequent calculations; (3) Extract the back contour and mark the feature points; (4) Extract features according to the grayscale change of the spine ROI, and fit the spine midline according to the feature points; (5) Evaluate the degree of scoliosis according to the symmetry of the posture features and the Cobb angle of the spine midline. Finally, experimental results were analyzed, which indicate that the proposed scoliosis detection method can preliminarily evaluate the posture features. The scoliosis detection error fell in the reasonable range (0-4 degrees), when the subjects had a Cobb angle between 0 and 30 degrees. Hence, our algorithm is accurate and effective, and provides a low-cost, efficient solution for scoliosis detection.

YogNet: A two-stream network for realtime multiperson yoga action recognition and posture correction

Yoga is a traditional Indian exercise. It specifies various body postures called asanas, practicing them is beneficial for the physical, mental, and spiritual well-being. To support the yoga practitioners, there is a need of an expert yoga asanas recognition system that can automatically analyze practitioner’s postures and could provide suitable posture correction instructions. This paper proposes YogNet, a multi-person yoga expert system for 20 asanas using a two-stream deep spatiotemporal neural network architecture. The first stream utilizes a keypoint detection approach to detect the practitioner’s pose, followed by the formation of bounding boxes across the subject. The model then applies time distributed convolutional neural networks (CNNs) to extract frame-wise postural features, followed by regularized long short-term memory (LSTM) networks to give temporal predictions. The second stream utilizes 3D-CNNs for spatiotemporal feature extraction from RGB videos. Finally, the scores of two streams are fused using multiple fusion techniques. A yoga asana recognition database (YAR) containing 1206 videos is collected using a single 2D web camera for 367 min with the help of 16 participants and contains four view variations i.e. front, back, left, and right sides. The proposed system is novel as this is the earliest two-stream deep learning-based system that can perform multi-person yoga asanas recognition and correction in realtime. Simulation result reveals that YogNet system achieved 77.29%, 89.29%, and 96.31% accuracies using pose stream, RGB stream, and via fusion of both streams, respectively. These results are impressive and sufficiently high for recommendation towards general adaption of the system.

Basketball Motion Posture Recognition Based on Recurrent Deep Learning Model

In order to improve the training effect of athletes and effectively identify the movement posture of basketball players, we propose a basketball motion posture recognition method based on recurrent deep learning. A one-dimensional convolution layer is added to the neural network structure of the deep recurrent Q network (DRQN) to extract the athlete pose feature data before the long short-term memory (LSTM) layer. The acceleration and angular velocity data of athletes are collected by inertial sensors, and the multi-dimensional motion posture features are extracted from the time domain and frequency domain, respectively, and the posture recognition of basketball is realized by DRQN. Finally, the new reinforcement learning algorithm is trained and tested in a time-series-related environment. The experimental results show that the method can effectively recognize the basketball motion posture, and the average accuracy of posture recognition reaches 99.3%.

Using Convolutional Neural Networks for the Assessment Research of Mental Health.

Existing mental health assessment methods mainly rely on experts' experience, which has subjective bias, so convolutional neural networks are applied to mental health assessment to achieve the fusion of face, voice, and gait. Among them, the OpenPose algorithm is used to extract facial and posture features; openSMILE is used to extract voice features; and attention mechanism is introduced to reasonably allocate the weight values of different modal features. As can be seen, the effective identification and evaluation of 10 indicators such as mental health somatization, depression, and anxiety are realized. Simulation results show that the proposed method can accurately assess mental health. Here, the overall recognition accuracy can reach 77.20%, and the F1 value can reach 0.77. Compared with the recognition methods based on face single-mode fusion, face + voice dual-mode fusion, and face + voice + gait multimodal fusion, the recognition accuracy and F1 value of proposed method are improved to varying degrees, and the recognition effect is better, which has certain practical application value.

The impact of a school backpack's weight, which is carried on the back of a 7-year-old students of both sexes, on the features of body posture in the frontal plane

BackgroundThe lifestyle of children has a significant impact on the future health of the whole society. Therefore, health education, prevention and monitoring of health determinants is important at every stage of ontogenesis. This requires a thorough knowledge of the schoolchild's environment, perceived as a wide set of stressors, including not only genetic but also epigenetic factors. One of them is the issue of the correct and abnormal body posture at school and on the way there. The goal of the study was to show the influence of the weight of the back carried container with school supplies on body posture.MethodThe research was carried out as part of a project that examined the impact of carrying weights, which are school supplies, by children on their posture. The research material consisted of data obtained from a group of 65 students (35 girls, 30 boys) aged 7 years. Body posture tests were carried out, using the projection moiré method in 4 positions: 1-habitual posture, 2-posture after 10-min of asymmetric axial load, 3-a posture after 1 min of the load removal, 4-a posture after two minutes of the load removal. Physical fitness was measured with the Sekita test. The obtained data were statistically analyzed.ResultsThe significance of differences between the 1st and 2nd measurements was analyzed to determine the impact of the backpack load and the correlation with physical fitness, and to study its influence on the value of the differences in posture features. Considering the differences in the volume of posture features among boys between the 1st and 2nd measurement, the Wilcoxon’s rank test showed a statistically significant difference in the range of all analyzed variables, except for the torso bend angle to the right (KNT+), where no statistically significant change was noted. A statistically significant difference in the volume of all analyzed variables was observed among the girls.ConclusionsCarrying school supplies on the back induces significant changes in the value of the features describing the body posture in the frontal plane. The greater weight of the container and carrying time, and intensity of physical effort is the greater the changes will be. Physical fitness has a various and sex-dependent influence on the value of changes in body posture features because of carrying school supplies. Among boys it significantly affects the asymmetry of the torso bend, shoulder height, the waist triangles height and width, whereas among girls it affects the asymmetry of the shoulders and the distance of the angles of the lower shoulder blades from the line of the spinous processes of the spine. Among boys the changes in the value of posture features are mostly influenced by endurance and speed, but strength, power and agility are of lower influence, whereas among girls only agility matters.