3D Postures Research Articles

Characterization of Human Shoulder Joint Stiffness Across 3D Arm Postures and Its Sex Differences.

Understanding the characteristics of shoulder joint stiffness can offer insights into how the shoulder joint contributes to arm stability and assists in various arm postures and movements. This study aims to characterize posture-dependent shoulder stiffness in a three-dimensional (3D) space and investigate its potential sex differences. A multi-degree-of-freedom, parallel-actuated shoulder exoskeleton robot was used' to perturb the participant's shoulder joint and measure the resulting torque responses while participants relaxed their shoulder muscles. The group average results of 40 healthy individuals (20 males and 20 females) revealed that arm postures significantly affect shoulder stiffness, particularly in postures involving shoulder flexion/extension and horizontal flexion/extension. Shoulder stiffness consistently increased as the shoulder flexion angle decreased and the shoulder horizontal flexion/extension approached the limit of its range of motion. The comparative group results between males and females indicated that shoulder stiffness in males was greater than that in females across all 15 arm postures measured in this study. Even after normalizing the data by subject body mass, the female group showed significantly lower stiffness than the male group in 12 out of the 15 arm postures. The results highlight that 3D arm postures and sex significantly affect shoulder stiffness even under relaxed muscles. This study provides valuable foundations for future studies aimed at characterizing shoulder stiffness in the context of active muscles and dynamic movement tasks, evaluating changes in shoulder stiffness following neuromuscular injuries, and formulating rehabilitative training protocols for individuals suffering from shoulder problems.

Hirota [formula omitted]-operator forms, multiple soliton waves, and other nonlinear patterns of a 2D generalized Kadomtsev–Petviashvili equation

In the present paper, extensive research is conducted on a 2D generalized Kadomtsev–Petviashvili (2D-gKP) equation which models water waves with long wavelengths. The study starts by establishing Hirota D-operator forms of the governing equation using the Bell polynomial method (BPM). Through checking the three-soliton condition for the 2D-gKP equation, its integrability is then examined, and as a consequence, single-, double-, and (special) triple-soliton waves are derived from the modified Hirota method. In the end, after deriving lump and breather waves of the 2D-gKP equation through ansatz methods, a theoretical discussion along with its proof is presented. Attempts have been made to elucidate the physical features of nonlinear waves by displaying such waves in 2D and 3D postures. The paper’s findings contribute certainly to research on nonlinear waves of KP-type equations.

Mapping the landscape of social behavior.

Social interaction is integral to animal behavior. However, we lack tools to describe it with quantitative rigor, limiting our understanding of its principles and neuropsychiatric disorders, like autism, that perturb it. Here, we present a technique for high-resolution 3D tracking of postural dynamics and social touch in freely interacting animals, solving the challenging subject occlusion and part assignment problems using 3D geometric reasoning, graph neural networks, and semi-supervised learning. We collected over 140 million 3D postures in interacting rodents, featuring new monogenic autism rat lines lacking reports of social behavioral phenotypes. Using a novel multi-scale embedding approach, we identified a rich landscape of stereotyped actions, interactions, synchrony, and body contact. This enhanced phenotyping revealed a spectrum of changes in autism models and in response to amphetamine that were inaccessible to conventional measurements. Our framework and large library of interactions will greatly facilitate studies of social behaviors and their neurobiological underpinnings.

Three-Dimensional Posture Estimation of Vehicle Occupants Using Depth and Infrared Images.

Pose estimation is crucial for ensuring passenger safety and better user experiences in semi- and fully autonomous vehicles. Traditional methods relying on pose estimation from regular color images face significant challenges due to a lack of three-dimensional (3D) information and the sensitivity to occlusion and lighting conditions. Depth images, which are invariant to lighting issues and provide 3D information about the scene, offer a promising alternative. However, there is a lack of strong work in 3D pose estimation from such images due to the time-consuming process of annotating depth images with 3D postures. In this paper, we present a novel approach to 3D human posture estimation using depth and infrared (IR) images. Our method leverages a three-stage fine-tuning process involving simulation data, approximated data, and a limited set of manually annotated samples. This approach allows us to effectively train a model capable of accurate 3D pose estimation with a median error of under 10 cm across all joints, using fewer than 100 manually annotated samples. To the best of our knowledge, this is the first work focusing on vehicle occupant posture detection utilizing only depth and IR data. Our results demonstrate the feasibility and efficacy of this approach, paving the way for enhanced passenger safety in autonomous vehicle systems.

A leg model based on anatomical landmarks to study 3D joint kinematics of walking in Drosophila melanogaster.

Walking is the most common form of how animals move on land. The model organism Drosophila melanogaster has become increasingly popular for studying how the nervous system controls behavior in general and walking in particular. Despite recent advances in tracking and modeling leg movements of walking Drosophila in 3D, there are still gaps in knowledge about the biomechanics of leg joints due to the tiny size of fruit flies. For instance, the natural alignment of joint rotational axes was largely neglected in previous kinematic analyses. In this study, we therefore present a detailed kinematic leg model in which not only the segment lengths but also the main rotational axes of the joints were derived from anatomical landmarks, namely, the joint condyles. Our model with natural oblique joint axes is able to adapt to the 3D leg postures of straight and forward walking fruit flies with high accuracy. When we compared our model to an orthogonalized version, we observed that our model showed a smaller error as well as differences in the used range of motion (ROM), highlighting the advantages of modeling natural rotational axes alignment for the study of joint kinematics. We further found that the kinematic profiles of front, middle, and hind legs differed in the number of required degrees of freedom as well as their contributions to stepping, time courses of joint angles, and ROM. Our findings provide deeper insights into the joint kinematics of walking in Drosophila, and, additionally, will help to develop dynamical, musculoskeletal, and neuromechanical simulations.

Effects of three-dimensional femur and tibia postures on the parameters of standing long-leg radiographs for osteoarthritic knees in elderly female subjects

BackgroundLong-leg frontal radiographs of the lower extremities are used to assess knee osteoarthritis. Given the three-dimensional (3D) nature of alignment changes in osteoarthritis, postural alterations in the femur and tibia extend beyond the coronal plane (in-plane) to include the transverse and sagittal planes (out-of-plane). This study investigates the impact of these out-of-plane factors on in-plane knee alignment parameters observed in frontal radiographs. MethodsA total of 97 osteoarthritic knees in women were examined. Using a 3D-to-two-dimensional (2D) image matching technique, we evaluated the 3D postures of the femur and tibia in the standing position as viewed from frontal radiographs in the world coordinate system. Statistical analyses were conducted to explore associations between these 3D postures and 2D alignment parameters obtained from frontal radiographs under identical conditions. FindingsThe femur exhibited a medial inclination of 2.7°, a posterior inclination of 3.9°, and an internal rotation of 4.2°, whereas the tibia showed a lateral inclination of 6.4°, an anterior inclination of 6.7°, and an internal rotation of 6.7°. Both coronal and rotational postures of femur and tibia influenced the hip-knee-ankle angle, mechanical axis percentage, and medial proximal tibial angle. However, only coronal factors of tibia impacted tibial joint line obliquity relative to the floor. InterpretationAttention should be paid to the potential impact of the out-of-plane postures of the femur and tibia on parameters assessed in plain frontal radiographs of the lower extremities.

3D octopus kinematics of complex postures: Translation to long, thin, soft devices and their potential for clinical use.

Octopuses are capable of complex arm movements. Unfortunately, experimental barriers and lack of a robust analysis method made it difficult to quantify the three-dimensional (3D) kinematics of soft, flexible bodies, such as the octopus arm. This information is not only crucial for understanding the posture of the animal's arm but also for the development of similarly designed soft, flexible devices. The primary goal of this work was to create a method to comprehensively quantify complex, 3D postures of octopus (Octopus Bimaculoides) arms in a manner that is conducive and translatable to octopus arm-inspired devices for health monitoring and rehabilitation. In this study, 3D underwater motion capture was used to collect kinematic data on both live octopuses and disembodied arms that still had neural activity. A new method was developed to define how arm curvature and regional segments were oriented relative to each other in 3D. This included identification of the bend within a segment along with the computation of the relative orientation between segments, thus permitting the complete quantification of complex arm motions. By comparing vector-based and radius of curvature-based approaches to magnitude of curvature, it was clear that the vector-based approach was less dependent on the length of a segment and that its reported ranges of motion were translatable for outcome measures associated with clinical use. The new approach for the relative orientation of each segment of the octopus arm resulted in the capability of describing the octopus arm in many unique postures, such as straight, simple bending, and complex bending as it utilized the three rotational angles. This method and its application to octopus arms will yield new information that can be used to better communicate and track not only octopus arm movements but in the development of complex, segmented, soft-bodied devices that can be used in health monitoring and rehabilitation.

Analysis of the Motion Postures in Equestrian Sports Based on Multi-Sensor Data Fusion

Horse riding, in its essence, is both an art and a captivating sport. In these events, riders showcase their refined skills and deep bond with their horses, most notably through changes in physical positioning. This research aims to accurately capture and analyze the spatial postures of riders in equestrian sports, exploring the dynamic differences between professional and amateur riders. To achieve this, we employed a multi-sensor data fusion approach based on human kinetics theories, enhanced by an extended Kalman filter. This method, combined with an optical tracking system, enabled us to intricately compare and analyze the 3D postures of riders during walking and trotting phases. Our research captured these nuanced postural shifts using an inertial sensor network, yielding nine-axis motion data of riders during their performance. The accuracy of our fusion technique was validated using the optical tracking system. By analyzing the motion data, we discerned posture variations among the riders of differing expertise levels, even when executing the same riding technique. The insights from this research offer a quantifiable metric for refining equestrian training and contribute to understanding the complex dynamics of rider–horse interaction.

Improved REBA: deep learning based rapid entire body risk assessment for prevention of musculoskeletal disorders

Preventing work-related musculoskeletal disorders (WMSDs) is crucial in reducing their impact on individuals and society. However, the existing mainstream 2D image-based approach is insufficient in capturing the complex 3D movements and postures involved in many occupational tasks. To address this, an improved deep learning-based rapid entire body assessment (REBA) method has been proposed. The method takes working videos as input and automatically outputs the corresponding REBA score through 3D pose reconstruction. The proposed method achieves an average precision of 94.7% on real-world data, which is comparable to that of ergonomic experts. Furthermore, the method has the potential to be applied across a wide range of industries as it has demonstrated good generalisation in multiple scenarios. The proposed method offers a promising solution for automated and accurate risk assessment of WMSDs, with implications for various industries to ensure the safety and well-being of workers.

Real‐time ergonomic risk assessment in construction using a co‐learning‐powered 3D human pose estimation model

AbstractWork‐related musculoskeletal disorders pose significant health risks to construction workers, making it essential to monitor their postures and identify physical exposure to mitigate these risks. This study presents a novel framework for real‐time ergonomic risk assessment of workers in construction environments. Specifically, this study develops a lightweight human pose estimation (HPE) model with a residual log‐likelihood estimation head and adopts pose‐tracking technology to enable real‐time recognition of workers’ three‐dimensional (3D) postures. In particular, this study proposes a novel co‐learning method that enables the HPE model to learn two‐dimensional (2D) and 3D features from multi‐dimension datasets simultaneously, substantially enhancing the model's ability to capture 3D postures from 2D images. The proposed framework facilitates real‐time ergonomic risk assessment, reducing potential risks to construction workers and offering promising practical applications.

MPose: Environment- and subject-agnostic 3D skeleton posture reconstruction leveraging a single mmWave device

Human skeleton posture reconstruction is an essential component for human–computer interactions (HCI) in various application domains. Traditional approaches usually rely on either cameras or on-body sensors, which induce privacy concerns or inconvenient practical setups. To address these practical concerns, this paper proposes a low-cost contactless skeleton posture reconstruction system, mPose , which can reconstruct a user’s 3D skeleton postures using a single mmWave device. mPose does not require the user to wear any sensors and can enable a broad range of emerging mobile applications (e.g., VR gaming and pervasive user input) via mmWave-5G ready Internet of Things (IoT) devices. Particularly, the system extracts multi-dimensional spatial information from mmWave signals which characterizes the skeleton postures in a 3D space. To mitigate the impacts of environmental changes, mPose dynamically detects the user location and extracts spatial features from the mmWave signals reflected only from the user. Furthermore, we develop a deep regression method with a domain discriminator to learn a mapping between the spatial features and the joint coordinates of human body while removing subject-specific characteristics, realizing robust posture reconstruction across users. Extensive experiments, involving 17 representative body postures, 7 subjects, and 3 indoor environments, show that mPose outperforms contemporary state-of-the-art RF-based solutions with a lower average joint error of only ∼ 30 mm, while achieving transferability across environments and subjects at the same time.

3D Gesture Estimation from RGB Images Based on DB-InterNet

The booming of deep learning has made it possible to estimate 3D gestures from ordinary color images. However, the high accuracy of inferring 3D hand postures from RGB images is still not available due to the high flexibility of the gestures themselves. This paper aims to address the problem of low accuracy of keypoint coordinates position in InterNet gesture estimation network, by means of improving the confidence coordinate function, and selecting different suppression factor β according to different keypoints to fit t interacting hand estimation. By doing so, the maximum position coordinates are more precise and the keypoint prediction is more accurate. With respect to good measures, enhancing the representation capability of the model and employing dynamic activation function at different locations of the network to learn features in a dynamic way so as to boost the learning of hidden joints. In this way, different layers dynamically adjusted the segmental activation function according to the input to improve the performance of the model by dynamically learning features in a more flexible way. The experimental results indicate that compared with the baseline algorithm, the MPJPE and MRRPE of this algorithm are reduced by 0.73% and 2.04%, respectively, and the accuracy of single hand estimation is higher while the accuracy of interacting hand estimation is also effectively improved.

Improved Behavior Monitoring and Classification Using Cues Parameters Extraction from Camera Array Images

Behavior monitoring and classification is a mechanism used to automatically identify or verify individual based on their human detection, tracking and behavior recognition from video sequences captured by a depth camera. In this paper, we designed a system that precisely classifies the nature of 3D body postures obtained by Kinect using an advanced recognizer. We proposed novel features that are suitable for depth data. These features are robust to noise, invariant to translation and scaling, and capable of monitoring fast human bodyparts movements. Lastly, advanced hidden Markov model is used to recognize different activities. In the extensive experiments, we have seen that our system consistently outperforms over three depth-based behavior datasets, i.e., IM-DailyDepthActivity, MSRDailyActivity3D and MSRAction3D in both posture classification and behavior recognition. Moreover, our system handles subject's body parts rotation, self-occlusion and body parts missing which significantly track complex activities and improve recognition rate. Due to easy accessible, low-cost and friendly deployment process of depth camera, the proposed system can be applied over various consumer-applications including patient-monitoring system, automatic video surveillance, smart homes/offices and 3D games.

Three-Dimensional Input System Employing Pinching Gestures for Robot Design

Several studies of input interfaces capable of recognizing the gestures have been conducted but most of them use the user’s fingers to enter the position data. These finger-based input interfaces are difficult to provide a so-called click & drag function (as in a mouse) and some of them request for the user to take uncomfortable gestures. When people pinch any objects, however, basically their thumb and index finger come into contact with each other or separate them from each other. These pinching gestures provide superior benefits as the gestures, which may contribute to the input interfaces. This study proposes the method for detecting 3D finger positions and estimating 3D hand postures in pinching gestures based on information on depth images captured by a depth sensor, especially from the viewpoint of robot design. That produces benefits including button-clicking-like input operation by means of contact between the fingers; user’s comfortable gestures as in daily life; clicking action independent of input of positions and postures; and clear identification between ON and OFF. As the evaluation of the 3D input interface proposed here, the authors design real products with the system and a 3D printer, suggesting that the users can design precise and fine 3D objects with his/her comfortable daily gestures with highest usability.

Practical Human Sensing in the Light

StarLight is an infrastructure-based sensing system that reuses light emitted from ceiling LED panels to reconstruct fine-grained user skeleton postures continuously in real time. It leverages only a few (e.g., 20) photodiodes at optimized locations on the floor to capture low-level visual cues (light blockage information), with neither invasive cameras nor on-body sensors. It aggregates the blockage information of different light rays and identifies the best-fit 3D skeleton postures. Experiments show that StarLight achieves 13.6° mean angular error for five body joints and reconstructs a mobile skeleton at a high frame rate (40 FPS). StarLight presents a new unobtrusive sensing paradigm to augment today's mobile sensing for continuous and accurate behavioral monitoring.

Stereo-based palmprint recognition in various 3D postures

In order to increase performance in palmprint recognition systems, various devices are normally used to restrict the movement of the hand. These can cause problems, especially for those users with physical disabilities. They also cause significant hygiene problems in multi-user systems. Recently, studies on palmprint recognition systems have progressed towards the development of unconstrained, contactless and unrestricted background techniques. The most common problem encountered in these studies is the alignment arising from the free movement of the hand. Despite 3D hand-acquisition devices which offer extra recognition features to overcome this problem, the applicability of these devices is low because of their increased cost. In this study, a stereo camera was proposed. Although due to matching problems, it is difficult to achieve precise, distinct feature extraction in the unrestricted 3D environment used for palmprint recognition, the orientation of the hand in 3D space can be determined by obtaining depth information. In this study, the depth information was extracted by using the binocular stereo approach. First, the orientation of the hand was estimated by fitting a surface model associated with the eigenvectors of the depth information. Pose correction was then accomplished by establishing a relationship between the orientation and the images. The pose correction greatly relieved the perspective distortion that usually occurs within the various poses of the hands. Next, the region of interest was determined by performing segmentation on the corrected images using the Active Appearance Model (AAM). The palmprint features were then extracted via Gabor-based Kernel Fisher Discriminant Analysis. In order to demonstrate the performance of the proposed approach, a new dataset was compiled from stereo images within various scenarios collected from 138 different individuals. As a result of these experimental studies, the EER values, especially on the images captured from different hand orientations in 3D, were reduced from around 14–0.75%. With the help of this suggested approach, the palmprint recognition system was transformed into a more portable form by removing the closed-box mechanisms and equipment restricting movement of the hand. This system can automatically perform pose estimation, hand segmentation and recognition processes without any special intervention.

Improving posture classification accuracy for depth sensor-based human activity monitoring in smart environments

Smart environments and monitoring systems are popular research areas nowadays due to its potential to enhance the quality of life. Applications such as human behavior analysis and workspace ergonomics monitoring are automated, thereby improving well-being of individuals with minimal running cost. The central problem of smart environments is to understand what the user is doing in order to provide the appropriate support. While it is difficult to obtain information of full body movement in the past, depth camera based motion sensing technology such as Kinect has made it possible to obtain 3D posture without complex setup. This has fused a large number of research projects to apply Kinect in smart environments. The common bottleneck of these researches is the high amount of errors in the detected joint positions, which would result in inaccurate analysis and false alarms. In this paper, we propose a framework that accurately classifies the nature of the 3D postures obtained by Kinect using a max-margin classifier. Different from previous work in the area, we integrate the information about the reliability of the tracked joints in order to enhance the accuracy and robustness of our framework. As a result, apart from general classifying activity of different movement context, our proposed method can classify the subtle differences between correctly performed and incorrectly performed movement in the same context. We demonstrate how our framework can be applied to evaluate the user’s posture and identify the postures that may result in musculoskeletal disorders. Such a system can be used in workplace such as offices and factories to reduce risk of injury. Experimental results have shown that our method consistently outperforms existing algorithms in both activity classification and posture healthiness classification. Due to the low cost and the easy deployment process of depth camera based motion sensors, our framework can be applied widely in home and office to facilitate smart environments.

Human motion retrieval based on freehand sketch

ABSTRACTIn this paper, we present an integrated framework of human motion retrieval based on freehand sketch. With some simple rules, the user can acquire a desired motion by sketching several key postures. To retrieve efficiently and accurately by sketch, the 3D postures are projected onto several 2D planes. The limb direction feature is proposed to represent the input sketch and the projected‐postures. Furthermore, a novel index structure based on k‐d tree is constructed to index the motions in the database, which speeds up the retrieval process. With our posture‐by‐posture retrieval algorithm, a continuous motion can be got directly or generated by using a pre‐computed graph structure. What's more, our system provides an intuitive user interface. The experimental results demonstrate the effectiveness of our method. © 2014 The Authors. Computer Animation and Virtual Worlds published by John Wiley & Sons, Ltd.

Nonlinear Synchronization for Automatic Learning of 3D Pose Variability in Human Motion Sequences

A dense matching algorithm that solves the problem of synchronizing prerecorded human motion sequences, which show different speeds and accelerations, is proposed. The approach is based on minimization of MRF energy and solves the problem by using Dynamic Programming. Additionally, an optimal sequence is automatically selected from the input dataset to be a time-scale pattern for all other sequences. The paper utilizes an action specific model which automatically learns the variability of 3D human postures observed in a set of training sequences. The model is trained using the public CMU motion capture dataset for the walking action, and a mean walking performance is automatically learnt. Additionally, statistics about the observed variability of the postures and motion direction are also computed at each time step. The synchronized motion sequences are used to learn a model of human motion for action recognition and full-body tracking purposes.

The impact of computer display height and desk design on 3D posture during information technology work by young adults

Computer display height and desk design to allow forearm support are two critical design features of workstations for information technology tasks. However there is currently no 3D description of head and neck posture with different computer display heights and no direct comparison to paper based information technology tasks. There is also inconsistent evidence on the effect of forearm support on posture and no evidence on whether these features interact. This study compared the 3D head, neck and upper limb postures of 18 male and 18 female young adults whilst working with different display and desk design conditions. There was no substantial interaction between display height and desk design. Lower display heights increased head and neck flexion with more spinal asymmetry when working with paper. The curved desk, designed to provide forearm support, increased scapula elevation/protraction and shoulder flexion/abduction.