Human Pose Estimation (HPE) is a technique in computer vision and AI for detecting and tracking human body parts and poses from images or videos. Widely used in augmented reality, animation, fitness applications, and surveillance, HPE methods using monocular cameras are highly versatile due to their applicability in standard video and CCTV footage. These methods have evolved from 2D to 3D pose estimation. However, current 3D HPE methods trained on laboratory-based motion capture data encounter challenges such as limited training data, depth perception ambiguity, left/right switching, and issues with occlusions when applied in real-world environments. This study compares two representative 3D HPE methods by assessing their strengths and weaknesses with real-world videos. Then, we propose data processing techniques to eliminate and correct anomalies like left/right inversion and false detections of joint positions in daily life motions. Finally, we obtain joint angle trajectories using an optimization method based on a 3D humanoid simulator, taking as input the joint coordinate data corrected by applying the proposed human joint data processing technique. The efficacy of the proposed 3D HPE method is verified by applying it to three-dimensional freehand gymnastics exercises and comparing the joint angle trajectories during the motion.

This paper presents preliminary research that investigates the relationship between the flow of a group of jazz musicians, quantified through multi-person pose synchronization, and their collective emotions. Building upon previous studies that measured the physical synchronicity of team members by tracking their body movements and measuring the difference in arm, leg, and head movements, we introduce a novel metric termed "team entanglement". We employ facial expression recognition to evaluate the musicians’ collective emotions. Through correlation and regression analysis, we establish that higher levels of synchronized body and head movements correspond to lower levels of disgust, anger, sadness and higher levels of joy among the musicians. Furthermore, we utilize a Convolutional Neural Network (CNN) based deep learning model to predict the collective emotions of the musicians. This model leverages 17 body synchrony keypoint vectors as features, resulting in a training accuracy of 61.47% and a test accuracy of 66.17%.

Existing methods for 3D human pose estimation mainly divide the task into two stages. The first stage identifies the 2D coordinates of the human joints in the input image, namely the 2D human joint coordinates. The second stage uses the results from the first stage as input to recover the depth information of human joints from the 2D human joint coordinates to achieve 3D human pose estimation. However, the recognition accuracy of the two-stage method relies heavily on the results of the first stage and includes too many redundant processing steps, which reduces the inference efficiency of the network. To address these issues, we propose the EDD, a fully End-to-end 3D human pose estimation method based on transformer architecture with Dual Decoders. By learning multiple human poses, the model can directly infer all 3D human poses in the image using a pose decoder, and then further optimize the recognition result using a joint decoder based on the kinematic relations between joints. With the attention mechanism, this method can adaptively focus on the most relevant features to the target joint, effectively overcoming the feature misalignment problem in the human pose estimation task and greatly improving the model performance. Any complex post-processing step, such as non-maximum suppression, is eliminated, further improving the efficiency of the model. The results show that the method achieves an accuracy of 87.4% on the MuPoTS-3D dataset, significantly improving the accuracy of end-to-end 3D human pose estimation methods.

This review paper provides a comprehensive overview of machine vision pose measurement algorithms. The paper focuses on the state-of-the-art algorithms and their applications. The paper is structured as follows: The introduction in Section 1 provides a brief overview of the field of machine vision pose measurement. Section 2 describes the commonly used algorithms for machine vision pose measurement. Section 3 discusses the factors that affect the accuracy and reliability of machine vision pose measurement algorithms. Section 4 presents the applications of machine vision pose measurement in various fields. The paper provides specific examples of how machine vision pose measurement is used in each of these fields. Finally, Section 5 summarizes the paper and provides future research directions. The paper highlights the need for more robust and accurate algorithms that can handle varying lighting conditions and occlusion. It also suggests that the integration of machine learning techniques may improve the performance of machine vision pose measurement algorithms. Overall, this review paper provides a comprehensive overview of machine vision pose measurement algorithms, their applications, and the factors that affect their accuracy and reliability. It provides a valuable resource for researchers and practitioners working in the field of computer vision.

A method of measuring the absolute pose parameters of a moving rigid body using a monocular camera is proposed, aiming at addressing calibration difficulties and inconsistencies of repeated measurements of the rigid-body pose for a camera having a varying focal length. The proposed method does not require calibration beforehand. Using more than six non-coplanar control points symmetrically arranged in the rigid-body and world coordinate systems, the matrices of rotation and translation between the camera and two coordinate systems are obtained and the absolute pose of the rigid body measured. In this paper, formulas of the absolute pose measurement of a moving rigid body are deduced systematically and the complete implementation is presented. Position and attitude measurement experiments carried out on a three-axis precision turntable show that the average absolute error in the attitude angle of a moving rigid body measured by an uncalibrated camera at different positions changes by no more than 0.2 degrees. Analysis of the three-dimensional coordinate errors of the centroid of a moving rigid body shows little deviation in measurements made at three camera positions, with the maximum deviation of the average absolute error being 0.53 cm and the maximum deviation of the standard deviation being 0.66 cm. The proposed method can measure the absolute pose of a rigid body and is insensitive to the position of the camera in the measurement process. This work thus provides guidance for the repeated measurement of the absolute pose of a moving rigid body using a monocular camera.

Human Pose Estimation (HPE) is a critical technology in computer vision with diverse applications ranging from healthcare to sports analysis. This project presents a method for detecting the 2D stance of multiple persons in an image using a nonparametric representation known as Part Affinity Fields (PAFs). By leveraging the first 10 layers of the VGG-19 convolutional neural network and training on the COCO dataset, our model effectively identifies and associates key points of the human body.The architecture employs a two-branch system that jointly learns part locations and their associations through sequential prediction. This enables the model to maintain real-time performance while achieving high accuracy, regardless of the number of persons in the image. To enhance accessibility, we developed a mobile application using Flutter and TensorFlow Lite, allowing real-time pose estimation via a mobile device’s front camera. The app provides immediate feedback on physical exercises and yoga poses, making it an invaluable tool for fitness enthusiasts and healthcare professionals. Visual outputs such as heatmaps and PAFs confirm the model’s capability to accurately localize and connect key points. Despite potential challenges such as data quality and hyperparameter tuning, the results indicate that our approach is both reliable and practical for real-world deployment. This project not only advances the state-of-the-art in HPE but also opens up possibilities for future enhancements, including integrating 3D pose estimation and applying the technology in augmented and virtual reality applications.

Object-level Simultaneous Localization and Mapping (SLAM) has gained popularity in recent years since it can provide a means for intelligent robot-to-environment interactions. However, most of these methods assume that the distribution of the errors is gaussian. This assumption is not valid under many circumstances. Further, these methods use a delayed initialization of the objects in the map. During this delayed period, the solution relies on the motion model provided by an Inertial Measurement Unit (IMU). Unfortunately, the errors tend to accumulate quickly due to the dead-reckoning nature of these motion models. Finally, the current solutions depend on a set of salient features on the object’s surface and not the object’s shape. This research proposes an accurate object-level solution to the SLAM problem with a 4.1 to 13.1 cm error in the position (0.005 to 0.021 of the total path). The developed solution is based on Rao-blackwellized Particle Filtering (RBPF) that does not assume any predefined error distribution for the parameters. Further, the solution relies on the shape and thus can be used for objects that lack texture on their surface. Finally, the developed tightly coupled IMU/camera solution is based on an undelayed initialization of the objects in the map.

Accurately estimating the pose of spacecraft is indispensable for space applications. However, such targets are generally non-cooperative, i.e., no markers are mounted on it and no parts for operation. Therefore, the detection and measurement of a non-cooperative target is very challenging. Stereovision sensors are important solutions in the near field. In this paper, a rectangular natural feature recognition and pose measurement method for non-cooperative spacecraft is proposed. Solar panels or the bodies of spacecraft are selected as detection objects and their image features are captured by stereo vision. These rectangle features are then reconstructed in 3D Cartesian space through parallelogram fitting on the image planes of two cameras. The vertexes are used to calculate the center position of the rectangle and the direction of the fixed coordinate system to solve the pose and attitude of the non-cooperative target. An experimental system is built to validate the effectiveness of the algorithm. The experimental results show that the average position measurement error of the algorithm is about 10mm and the average attitude measurement error is less than 1°. The results show that the proposed method has high accuracy and efficiency.

Pose estimation has various applications in analyzing human movement and behavior, including providing feedback to users about their movements so they could adjust and improve their movement skills. To investigate the current research status and possible gaps, we searched Scopus and Web of Science for articles that (1) human `body' pose estimation is used and (2) user movement is assessed and communicated. We used either a bottom-up or top-down approach to analyze 20 articles for methods used to estimate human pose, assess movement, provide feedback to users, as well as methods to evaluate them. Our review found that pose estimation systems typically used CNNs while movement assessment methods varied from mathematical formulas or models, rule-based approaches, to machine learning. Feedback was primarily presented visually in verbal forms and nonverbal forms. The experiments to evaluate each part ranged from the use of public datasets to human participants. We found that while there was an improvement, the majority of pose estimation challenges remain. The effectiveness and factors for choosing movement assessment methods for a new context are still unclear. In the end, we suggest that studies about feedback prioritization and erroneous feedback are needed.

Caring for dolphins is a delicate process that requires experienced caretakers to pay close attention to their behavioral characteristics. However, caretakers may sometimes lack experience or not be able to give their full attention, which can lead to misjudgment or oversight. To address these issues, a dolphin behavior analysis system has been designed to assist caretakers in making accurate assessments. The study utilized image preprocessing techniques to reduce sunlight reflection in the pool and enhance the outline of dolphins, making it easier to analyze their movements. The dolphins were divided into 11 keypoints using an open-source tool called DeepLabCut, which helped accurately mark various body parts for skeletal detection. The AquaAI Dolphin Decoder (ADD) was then used to analyze six dolphin behaviors. To improve behavior recognition accuracy, the Long Short-Term Memory (LSTM) neural network was introduced. The ADD and LSTM models were integrated to form the ADD-LSTM system. Several classification models, including unidirectional and bidirectional LSTM, GRU, and SVM, were compared. The results showed that the ADD module combined with a double-layer bidirectional LSTM method achieved high accuracy in dolphin behavior analysis. The accuracy rates for each behavior were over 90%.

The present work fronts the human pose estimation problem, developing a method that enables automated ergonomic risk assessment. A research methodology is developed to calculate joint angles from digital snapshots or videos by using computer vision and machine learning techniques to get a more accurate ergonomic risk assessment. Starting from an ergonomic analysis, the study explores the use of a semi-supervised training method to detect the skeletons of workers. The research methodology developed aims to infer the positions and angles of the joints, to calculate the criticality index based on the RULA scores and fuzzy rules. Then, to prevent work-related musculoskeletal disorders (WMSD), improve production capacity and decrease the ergonomic risk, the system uses joint with a collaborative robot to support the worker in carrying out the most critical operations. The method has been tested on a real industrial case in which manual assembly activities of electrical components are conducted. The approach developed can overcome the limitations of recent developments based on computer vision or wearable measurement, sensors by performing an assessment with an objective and flexible ap-proach to postural analysis development.

Automatic and real-time pose estimation is important in monitoring animal behavior, health and welfare. In this paper, we utilized pose estimation for monitoring farrowing process to prevent piglet mortality and preserve the health and welfare of sow. State-of-the-art Deep Learning (DL) methods have lately been used for animal pose estimation. The aim of this paper was to probe the generalization ability of five common DL networks (ResNet50, ResNet101, MobileNet, EfficientNet and DLCRNet) for sow and piglet pose estimation. These architectures predict body parts of several piglets and the sow directly from input video sequences. Real farrowing data from a commercial farm was used for training and validation of the proposed networks. The experimental results demonstrated that MobileNet was able to detect seven body parts of the sow with median test error of 0.61 pixels.

We propose Context-aware Feature Transformer Network (CaFTNet), a novel network for human pose estimation. To address the issue of limited modeling of global dependencies in convolutional neural networks, we design Transformerneck to strengthen the expressive power of features. Transformerneck directly substitutes the 3×3 convolution in bottleneck of HRNet with Contextual Transformer (CoT) block, while reducing the complexity of the network. Specifically, CoT first produces keys with static contextual information through 3×3 convolution. Then, relying on the query and contextualization keys, the dynamic contexts are generated through two concatenated 1×1 convolutions. Static and dynamic contexts are eventually fused as an output. Additionally, for the multi-scale networks, in order to further refine the features of the fusion output, we propose an Attention Feature Aggregation Module(AFAM). Technically, given an intermediate input, AFAM successively deduces attention maps along channel and spatial dimensions. Then, Adaptive refinement module(ARM) is exploited to activate the obtained attention maps. Finally, the input undergoes adaptive feature refinement through multiplication with the activated attention maps. Through the above studies, our lightweight network provides a powerful clue for detection of keypoints. Experiments are implemented on the COCO and MPII datasets. The model achieves 76.2 AP on the COCO val2017. Compared to other methods with the CNN as the backbone, CaFTNet reduces the number of parameters by 72.9 %. On the MPII, our method uses only 60.7% of the number of parameters, acquiring semblable results to other methods with the CNN as the backbone.

3D human pose estimation has made significant advancements through the integration of deep learning techniques. This survey provides a comprehensive review of recent 3D human pose estimation methods, with a focus on monocular images, videos, and multi-view cameras. Our approach stands out through a systematic literature review methodology, ensuring an up-to-date and meticulous overview. Unlike many existing surveys that categorize approaches based on learning paradigms, our survey offers a fresh perspective, delving deeper into the subject. For image-based approaches, we not only follow existing categorizations but also introduce and compare significant 2D models. Additionally, we provide a comparative analysis of these methods, enhancing the understanding of image-based pose estimation techniques. In the realm of video-based approaches, we categorize them based on the types of models used to capture inter-frame information. Furthermore, in the context of multi-person pose estimation, our survey uniquely differentiates between approaches focusing on relative poses and those addressing absolute poses. Our survey aims to serve as a pivotal resource for researchers, highlighting state-of-the-art deep learning strategies and identifying promising directions for future exploration in 3D human pose estimation.

As a typical visual positioning system, monocular ranging is widely used in various fields. However, when the distance increases, there is a greater error. YOLOv8 network has the advantages of fast recognition speed and high accuracy. This paper proposes a method by combining YOLOv8 network recognition with a monocular ranging method to achieve target localization and grasping for the NAO robots. By establishing a visual distance error compensation model and applying it to correct the estimation results of the monocular distance measurement model, the accuracy of the NAO robot's long-distance monocular visual positioning is improved. Additionally, a grasping control strategy based on pose interpolation is proposed. Throughout, the proposed method's advantage in measurement accuracy was confirmed via experiments, and the grasping strategy has been implemented to accurately grasp the target object.

Light pen 3D vision coordinate measurement systems are increasingly widely used due to their advantages, such as small size, convenient carrying and wide applicability. The posture of the light pen is an important factor affecting accuracy. The pose domain of the pen needs to be given so that the measurement system has a suitable measurement range to obtain more qualified parameters. The advantage of the self-calibration method is that the entire self-calibration process can be completed at the measurement site without any auxiliary equipment. After the system camera calibration is completed, we take several pictures of the same measurement point with different poses to obtain the conversion matrix of the picture, and then use spherical fitting, the generalized inverse method of least squares, and the principle of position invariance within the pose domain range. The combined stylus tip center self-calibration method calculates the actual position of the light pen probe. The experimental results show that the absolute error is stable below 0.0737 mm and that the relative error is stable below 0.0025 mm. The experimental results verify the effectiveness of the method; the measurement accuracy of the system can meet the basic industrial measurement requirements.

Global pose refinement is a significant challenge within Simultaneous Localization and Mapping (SLAM) frameworks. For LIDAR-based SLAM systems, pose refinement is integral to correcting drift caused by the successive registration of 3D point clouds collected by the sensor. A divergence between the actual and calculated platform path characterizes this error. In response to this challenge, we propose a linear, parameter-free model, which uses a closed circuit for global trajectory corrections. Our model maps rotations to quaternions and uses Spherical Linear Interpolation (SLERP) for transitions between them. The intervals are established from the constraint set by the Least Squares (LS) method on rotation closure and are proportional to the circuit's size. Translations are globally adjusted in a distinct linear phase. Additionally, we suggest a coarse-to-fine pairwise registration method, integrating Fast Global Registration and Generalized ICP with multiscale sampling and filtering. The proposed approach is tested on three varied datasets of point clouds, including Mobile Laser Scanners and Terrestrial Laser Scanners. These diverse datasets affirm the model's effectiveness in 3D pose estimation with substantial pose differences and efficient pose optimization in larger circuits.

Human pose estimation is a complex detection task in which the network needs to capture the rich information contained in the images. In this paper, we propose MSTPose (Multi-Scale Transformer for human Pose estimation). Specifically, MSTPose leverages a high-resolution Convolution neural network (CNN) to extract texture information from images. For the feature maps from three different scales produced by the backbone network, each branch performs the coordinate attention operations. The feature maps are then spatially and channel-wise flattened, combined with keypoint tokens generated through random initialization, and fed into a parallel Transformer structure to learn spatial dependencies between features. As the Transformer outputs one-dimensional sequential features, the mainstream two-dimensional heatmap method is abandoned in favor of one-dimensional coordinate vector regression. The experiments show that MSTPose outperforms other CNN-based pose estimation models and demonstrates clear advantages over CNN + Transformer networks of similar types.

To validate the accuracy and reliability of onboard sensors for object detection and localization in driver assistance, as well as autonomous driving applications under realistic conditions (indoors and outdoors), a novel tracking system is presented. This tracking system is developed to determine the position and orientation of a slow-moving vehicle (e.g. car during parking maneuvers), independent of the onboard sensors, during test maneuvers within a reference environment. One requirement is a 6 degree of freedom (DoF) pose with a position uncertainty below 5 mm (3σ), an orientation uncertainty below 0.3° (3σ) at a frequency higher than 20 Hz, and a latency smaller than 500 ms. To compare the results from the reference system with the vehicle’s onboard system, a synchronization via Precision Time Protocol (PTP) and a system interoperability to Robot Operating System (ROS) is implemented. The developed system combines motion capture cameras mounted in a 360° panorama view set-up on the vehicle with robotic total stations. A point cloud of the test site serves as a digital twin of the environment, in which the movement of the vehicle is simulated. Results have shown that the fused measurements of these sensors complement each other, so that the accuracy requirements for the 6 DoF pose can be met, while allowing a flexible installation in different environments.

The observation of moving bio-object s is currently a topic of great interest in both fundamental and practical research. To illustrate, when developing and testing pharmaceuticals and vaccines, it is imperative to study their impact on the physiological state and behavior of an animal or human subject. The advent of deep learning algorithms has enabled the automation of qualitative and quantitative analysis of the behavior of bio-objects recorded in video format. It is essential that video data undergoes the appropriate preprocessing prior to training deep learning models. It is essential to consider additional factors, such as the background noise in the frame, the rapidity of bio-object movement, and the necessity to reflect information about the previous (past) and subsequent (future) pose of the bio-object in a single video frame. Moreover, the preprocessed dataset should be suitable for verification by its experts. This paper proposes a method of data preprocessing for the identification of bio-object behavior, with the laboratory animal experiments involving video data collection serving as an illustrative example. The method is based on the combination of information about a behavior event presented in a sequence of frames, with the addition of the native image and further boundary extraction by Sobel filter. Consequently, the behavior event representation obtained is readily comprehensible for both human experts and neural networks of varying architectures. The paper presents the outcomes of training multiple neural networks on the acquired data set and proposes an effective neural network architecture (accuracy = 0.95) for the identification of discrete behavior events of bio-objects.

This paper proposes an algorithm for transmitting and reconstructing the estimated point cloud using temporally estimating a dynamic point cloud sequence. When a non-rigid 3D point cloud sequence (PCS) is input, the sequence is divided into groups of point cloud frames (PCF), and a key PCF is selected. After the 3D skeleton is predicted through 3D pose estimation, the motion of the skeleton is estimated by analyzing the joints and bones of the 3D skeleton. For the deformation of the non-rigid human PC, the 3D PC model is transformed into a mesh model, and the key PCF is rigged using the 3D skeleton. After deforming the key PCF into the target PCF utilizing the motion vector of the estimated skeleton, the residual PC between the motion compensation PCF and the target PCF is generated. If there is a key PCF, the motion vector of the target PCF, and a residual PC, the target PCF can be reconstructed. Just as compression is performed using pixel correlation between frames in a 2D video, this paper compresses 3D PCF by estimating the non-rigid 3D motion of a 3D object in a 3D PC. The proposed algorithm can be regarded as an extension of the 2D motion estimation of a rigid local region in a 2D plane to the 3D motion estimation of a non-rigid object (human) in 3D space. Experimental results show that the proposed method can successfully compress 3D PC sequences. If it is used together with a PC compression technique such as MPEG PCC (point cloud compression) in the future, a system with high compression efficiency may be configured.

Mobile Mapping System (MMS) plays a crucial role in generating high-precision 3D maps for various applications. However, the traditional MMS that uses tilted LiDAR (light detection and ranging) has limitations in capturing complete information of the environment. To overcome these limitations, we propose a panoramic vision-aided Cartographer simultaneous localization and mapping (SLAM) system for MMS, named "PVL-Cartographer". The proposed system integrates multiple sensors to achieve accurate and robust localization and mapping. It contains two sub-systems, early fusion and middle fusion. In the early fusion, range-maps are created from LiDAR points in a panoramic image space, facilitating the incorporation of visual features. The SLAM system works with both visual features with and without augmented ranges. In the middle fusion, a pose graph combines camera and LiDAR nodes, with IMU (Inertial Measurement Unit) data providing constraints between each node. Extensive experiments in challenging outdoor scenarios demonstrate the effectiveness of the proposed SLAM system in producing accurate results, even in conditions with limited features. Overall, our proposed PVL Cartographer system offers a robust and accurate solution for MMS localization and mapping.

Tracking the kinematics of human movement usually requires the use of equipment that constrains the user within a room (e.g., optical motion capture systems), or requires the use of a conspicuous body-worn measurement system (e.g., inertial measurement units (IMUs) attached to each body segment). This paper presents a novel Lie group constrained extended Kalman filter to estimate lower limb kinematics using IMU and inter-IMU distance measurements in a reduced sensor count configuration. The algorithm iterates through the prediction (kinematic equations), measurement (pelvis height assumption/inter-IMU distance measurements, zero velocity update for feet/ankles, flat-floor assumption for feet/ankles, and covariance limiter), and constraint update (formulation of hinged knee joints and ball-and-socket hip joints). The knee and hip joint angle root-mean-square errors in the sagittal plane for straight walking were 7.6±2.6∘ and 6.6±2.7∘, respectively, while the correlation coefficients were 0.95±0.03 and 0.87±0.16, respectively. Furthermore, experiments using simulated inter-IMU distance measurements show that performance improved substantially for dynamic movements, even at large noise levels (σ=0.2 m). However, further validation is recommended with actual distance measurement sensors, such as ultra-wideband ranging sensors.

Affective computing in general and human activity and intention analysis in particular, is a rapidly growing field of research. Head pose and emotion changes, present serious challenges when applied to player’s training and ludology experience in serious games or analysis of customer satisfaction regarding broadcast and web services or monitoring a driver’s attention. Given the increasing prominence and utility of depth sensors, it is now feasible to perform large-scale collection of three-dimensional (3D) data for subsequent analysis. Discriminative random regression forests was selected in order to rapidly and accurately estimate head pose changes in unconstrained environment. In order to complete the secondary process of recognising four universal dominant facial expressions (happiness, anger, sadness and surprise), emotion recognition via facial expressions (ERFE) was adopted. After that, a lightweight data exchange format (JavaScript Object Notation-JSON) is employed, in order to manipulate the data extracted from the two aforementioned settings. Motivated by the need of generating comprehensible visual representations from different sets of data, in this paper we introduce a system capable of monitoring human activity through head pose and emotion changes, utilising an affordable 3D sensing technology (Microsoft Kinect sensor).

Leader-follower autonomy (LFA) systems have so far only focused on vehicles following other vehicles. Though there have been several decades of research into this topic, there has not yet been any work on human-vehicle leader-follower systems. We present a system in which an autonomous vehicle — our ACTor 1 platform — can follow a human leader who controls the vehicle through gestures. We successfully developed a modular pipeline that uses artificial intelligence/deep learning to recognize hand-and-body gestures from a user in view of the vehicle’s camera and translate those gestures into physical action by the vehicle. We demonstrate our work using our ACTor 1 platform, a modified Polaris Gem 2 electric vehicle. This work has numerous applications, such as material transport in industrial contexts.

This work addresses the problem of automatic head pose estimation and its application in 3D gaze estimation using low quality RGB--D sensors without any subject cooperation or manual intervention. The previous works on 3D head pose estimation using RGB--D sensors require either an offline step for supervised learning or 3D head model construction which may require manual intervention or subject cooperation for complete head model reconstruction. In this paper, we propose a 3D pose estimator based on low quality depth data, which is not limited by any of the aforementioned steps. Instead, the proposed technique relies on modeling the subject's face in 3--D rather than the complete head, which in turn, relaxes all of the constraints with the previous works. The proposed method is robust, highly accurate and fully automatic. Moreover, it does not need any offline step. Unlike some of the previous works, the method only uses depth data for pose estimation. The experimental results on the Biwi head pose database confirm the efficiency of our algorithm in handling large pose variations and partial occlusion. We also evaluate the performance of our algorithm on IDIAP database for 3D head pose and eye gaze estimation.

Background. Pose estimation based on deep learning has been expected to be a breakthrough method to increase the accuracy of clinical photographic evaluation and to decrease interobserver errors. The purpose is to quantify pose estimation from photography of patients with adolescent idiopathic scoliosis (AIS) using open-source software packages and determine correlations between parameters obtained by radiography and photography. Methods. We included 12 consecutive patients with AIS treated with spinal correction surgery. Photographs were taken preoperatively using a tripod-mounted camera (iPhone 13Pro) on an X-ray tube head. To assess photographic parameters obtained by photography, we defined 17 points to analyze posture and define parameters. Results. In the sagittal plane, there was a significant correlation between the radiographic trunk tilt angle and the photographic sagittal trunk tilt angle of the shoulder–hip and ear–hip. In the coronal plane, there was a significant correlation between the radiographic clavicle angle and the photographic shoulder height angle, and the radiographic C7–CSVL and the photographic coronal trunk tilt angle. Conclusions. Posture analysis by photography using popular mobile devices has clinical utility for improving and promoting the screening and early detection of AIS because it is simple, without patient exposure to X-ray radiation.

Recent improvements in deepfake creation have made deepfake videos more realistic. Moreover, open-source software has made deepfake creation more accessible, which reduces the barrier to entry for deepfake creation. This could pose a threat to the people’s privacy. There is a potential danger if the deepfake creation techniques are used by people with an ulterior motive to produce deepfake videos of world leaders to disrupt the order of countries and the world. Therefore, research into the automatic detection of deepfaked media is essential for public security. In this work, we propose a deepfake detection method using upper body language analysis. Specifically, a many-to-one LSTM network was designed and trained as a classification model for deepfake detection. Different models were trained by varying the hyperparameters to build a final model with benchmark accuracy. We achieved 94.39% accuracy on the deepfake test set. The experimental results showed that upper body language can effectively detect deepfakes.

The human ankle is a complex joint, most commonly represented as talocrural and subtalar axes. It is difficult to locate and take in vivo measurements of the ankle joint. There are no instruments for patients lying on a bed or the floor; that can be used in outdoor or remote sites. We have developed a "Turmell-meter" to address these issues. We started with the study of ankle anatomy and anthropometry, then we used the product of exponentials’ formula to visualize the movements. Furthermore, we built a prototype using human proportions and statistics. For pose estimation, we used a trilateration method by applying tetrahedral geometry. Additionally, we computed the axis direction by fitting 3D circles, plotting the manifold and chart as an ankle joint model. We presented the results of simulations, a prototype comprising 45 parts, specifically designed draw-wire sensors, and electronics. Finally, we tested the device by capturing positions and fitting them into the bi-axial ankle model as a Riemannian manifold. The Turmell-meter is intended to be a hardware platform for human ankle joint axis estimation, it is adjustable and has an easy setup. The proposed model has the properties of a chart in a geometric manifold, we provided the details