Search

The computational problem of Human Pose Transfer (HPT) is addressed in this paper. HPT in recent days have become an emerging research topic which can be used in fields like fashion design, media production, animation, virtual reality. Given the image of a human subject and a target pose, the goal of HPT is to generate a new image of the human subject with the novel pose. That is, the pose of the target pose is transferred to the human subject. HPT has been carried out in two stages. In stage 1, a rough estimate is generated and in stage 2, the rough estimate is refined with a generative adversarial network. The novelty of this work is the way pose information is represented. Earlier methods used computationally expensive pose representations like 3D DensePose and 18-channel pose heatmaps. This work uses a 3-channel colour image of a stick figure to represent human pose. Different body parts are encoded with different colours. The convolutional neural networks will now have to recognize colours only, and since these colours encode body parts, eventually the network will also learn about the position of the body parts.

Movements of a person can be recorded with a mobile camera and visualized as sequences of stick figures for assessments in health and elderly care, physio-therapy, and sports. However, since the visualizations flicker due to noisy input data, the visualizations themselves and even whole assessment applications are not trusted in general. The present paper evaluates different filters for smoothing the movement visualizations but keeping their validity for a visual physio-therapeutic assessment. It evaluates variants of moving average, high-pass, and Kalman filters with different parameters. Moreover, it presents a framework for the quantitative evaluation of smoothness and validity. As these two criteria are contradicting, the framework also allows to weight them differently and to automatically find the correspondingly best-fitting filter and its parameters. Different filters can be recommended for different weightings of smoothness and validity. The evaluation framework is applicable in more general contexts and with more filters than the three filters assessed. However, as a practical result of this work, a suitable filter for stick figure visualizations in a mobile application for assessing movement quality could be selected and used in a mobile app. The application is now more trustworthy and used by medical and sports experts, and end customers alike.

Any activity, including science, and the doctor-patient relationship, depends on society. The institution of medicine is based on social relationships that are defined exclusively by experts, and this involves cultural definitions, values and techniques. The institutions define the right practices independently of the people involved. Social practices are full of conventions, uses, rituals, styles, modes, procedures, laws, etc. Institutional power defines the individual doctor-patient relationship. This scenario places limits on the positivist view of the patient-centered relationship. Social institutions make their social agents-doctors-first interested in outputs, products or results (cures, prescriptions, visits, demand, hospital admissions, diagnoses, morbidity, mortality), but not in social relationships, which they are frequently hidden or distorted. In this way, the doctor-patient relationship is frequently trivialized and treated in a child-like manner as a professional matter: it is presented in the biomedical literature as a stick figure; a "prehistoric" oversimplification that is little likes the current reality. The sociological approach brings doctor-patient relationship to the surface, making it visible, demystifying and problematizing it. The general practitioner should: 1. Go from medicalizing social relations, including the doctor-patient relationship, to socially contextualize medical practice and the doctor-patient relationship; And 2. Take charge of social problems from the consultation, understanding that social problems are part of the consultation and the doctor-patient relationship.

Due to its capabilities in analysing injury risk, the ability to analyse an athlete's ground reaction force and joint moments is of high interest in sports biomechanics. However, using force plates for the kinetic measurements influences the athlete's performance. Therefore, this study aims to use a feed-forward neural network to predict hip, knee and ankle joint moments as well as the ground reaction force from kinematic data during the execution and depart contact of a maximum effort 90° cutting manoeuvre. A total number of 525 cutting manoeuvres performed by 55 athletes were used to train and test neural networks. Either marker trajectories or joint angles were used as input data. The correlation coefficient between the measured and predicted data indicated strong correlations. By using joint angles as the input parameters, slightly but not significantly higher accuracy was found in joint moments predictions. The prediction of the ground reaction force showed significantly higher accuracy when using marker trajectories. Hence, the proposed feed-forward neural network method can be used to predict motion kinetics during a fast change of direction. This may allow for the simplification of cutting manoeuvres experimental set-ups for and through the use of inertial sensors. Graphical abstract The left part of the graphical abstract displays the angle progression of the hip, knee and ankle joint as an example of the kinematic input data and is supported by a stick figure of the motion task, a 90° cutting manoeuvre. This data is used to train a feed-forward neural network, which is displayed in the middle. The neural network's output is displayed on the right. As an example of the kinetic data, the joint moments of hip, knee and ankle joint are displayed and supported by a stick figure.

Comprehending the meaning of body postures is essential for social organisms such as humans. For example, it is important to understand at a glance whether two people seen at a distance are in a friendly or conflictual interaction. However, it is still unclear what fraction of the possible body configurations carry meaning, and what is the best way to characterize such meaning. Here, we address this by using stick figures as a low-dimensional, yet evocative, representation of body postures. We systematically scanned a set of 1,470 upper-body postures of stick figures in a dyad with a second stick figure with a neutral pose. We asked participants to rate the stick figure in terms of 20 emotion adjectives like sad or triumphant and in terms of eight active verbs that connote intent like to threaten and to comfort. The stick figure configuration space was dense with meaning: people strongly agreed on more than half of the configurations. The meaning was generally smooth in the sense that small changes in posture had a small effect on the meaning, but certain small changes had a large effect. Configurations carried meaning in both emotions and intent, but the intent verbs covered more configurations. The effectiveness of the intent verbs in describing body postures aligns with a theory, originating from the theater, called dramatic action theory. This suggests that, in addition to the well-studied role of emotional states in describing body language, much can be gained by using also dramatic action verbs which signal the effort to change the state of others. We provide a dictionary of stick figure configurations and their perceived meaning. This systematic scan of body configurations might be useful to teaching people and machines to decipher body postures in human interactions.

There is a sex bias for common overuse running injuries that are associated with sex-specific hip kinematics. Gait retraining programs aimed at altering hip kinematics may be more efficient if they incorporated an understanding of how hip kinematics are correlated with the movement of the remaining body segments. We applied a principal component analysis to structure the whole-body running kinematics of 23 runners (12 ♀) into k = 12 principal movements (PMk), describing correlated patterns of upper and lower body movements. We compared the time-dependent movement amplitudes with respect to each PMk between males and females using a waveform analysis and interpreted our findings according to stick figure animations. The movement amplitudes of two PMs (PM6 and PM8) showed statistically significant effects of “sex,” which were independent of running speed. According to PM8, females showed more hip adduction, which correlated with increased transverse rotation of the pelvis and upper body compared to men. We propose that increased hip adduction and upper body rotation in female runners may be a strategy to compensate for a less efficient arm and upper body swing compared to men. Gait interventions aimed at reducing hip adduction and running-related injuries in female runners should consider instructions for both upper and lower body to maximize training efficacy.

In this paper, a volume parametric model is computed from a piecewise smooth skeleton. Generating a volume model from a stick figure S defined in 3D is an intuitive process: given S whose topology is a pseudo-graph and whose edges are embedded as Bezier curves in R 3 , we propose a method for creating a thick volume parametric model “around” S. The volume model we generate is based on semi-simploidal sets, which guarantees a proper topology and provides a 3D parametric domain for Bezier spaces. This volume is a continuous piecewise Bezier representation which boundary corresponds to a B-Rep made of tensor product Bezier patches.

Choreography is a type of art in which movement is designed. Because it involves many complex movements, a lot of time is spent creating the choreography. In this study, we constructed a dataset of dance movements with more than 700,000 frames using dance videos of the “Odotte-mita” genre. Our dataset could have been very useful for recent research in motion generation, as there has been a lack of dance datasets. Furthermore, we verified the choreography of the dance generated by the deep learning method (acRNN) by physically repeating the dance steps. To the best of our knowledge, this is the first time such a verification has been attempted. It became clear that the choreography generated by machine learning had unique movements and rhythms for dancers. In addition, dancing machine-learning-generated choreography provided an opportunity to make new discoveries. In addition, the fact that the model was a stick figure made the choreography vague, and, although it was difficult to remember, it created varied dance steps.

In this paper, we present a novel approach to classify strokes in cricket batting. To classify front foot and back foot strokes, we created a feature space consisting of spatiotemporal time series obtained from generated stick Figure video overlays. Classification was performed using Long Short Term memory (LSTM) and Bidirectional LSTM networks. Both LSTM models accurately classified (100%) of all the videos from the testing split for a dataset created using publicly available videos (63 strokes). The presented approach has the potential to contribute to sport analytics and advance augment coaching systems and cricket viewing experience (including automated body segments annotations). Future work will include application in other sport disciplines and advancing prototype implementations on various platforms.

“I thought I would never go to Poland, where my mother and father’s entire family except for one brother were slaughtered.” As psychoanalysts, we know that trauma and its intergenerational aftermath do not become integrated or comprehended in a linear, organized way. Three summers ago, my brother and I traveled to our parents’ hometowns in Poland and Ukraine, 70 years after the Holocaust. With only a few addresses in hand, we went on a scavenger hunt of sorts, searching for places in my parents’ world that are no more. In this article, I examine how growing up as the child of parents who survived the Holocaust was intertwined with my evolution as a psychoanalyst. I explore the transformative nature of my trip and I offer reflections on my work with patients who have been part of my journey. I describe how my journey has filled out my previous scant, stick-figure-like images of my parents’ pasts and Holocaust histories.

Ultrasound is notoriously plagued by high user dependence. There is a steep drop-off in information in going from what the sonographer sees during image acquisition and what the interpreting radiologist is able to view at the reading station. One countermeasure is probe localization and tracking. Current implementations are too difficult and expensive to use and/or do not provide adequate detail and perspective. The aim of this work was to demonstrate that a protocol combining surface three-dimensional photographic imaging with traditional ultrasound images may be a solution to the problem of probe localization, this approach being termed surface point cloud ultrasound (SPC-US). Ultrasound images were obtained of major vessels in an ultrasound training phantom, while simultaneously obtaining surface point cloud (SPC) 3D photographic images, with additional scanning performed on the right forearm soft tissues, kidneys, chest, and pelvis. The resulting sets of grayscale/color Doppler ultrasound and SPC images are juxtaposed and displayed for interpretation in a manner analogous to current text-based annotation or computer-generated stick figure probe position illustrations. Clearly demonstrated is that SPC-US better communicates information of probe position and orientation. Overall, it is shown that SPC-US provides much richer image representations of probe position on the patients than the current prevailing schemes. SPC-US turns out to be a rather general technique with many anticipated future applications, though only a few sample applications are illustrated in the present work.

This research investigated the capabilities of Cycle-Consistent adversarial network (Cycle GAN) in the application of stick figure sketches to cartoon character translation. Few studies focused on the task of generating a variety of poses and facial expression of cartoon characters from simple sketches of stick figures, based on unpaired dataset samples. Furthermore, existing studies showed low performance in detecting rare pose features. In this research, two datasets have been created which consists of paired and unpaired images of manually drawn sketches and cartoon characters. The performance of Cycle GAN has been compared against a paired based model, Pix2Pix, by using qualitative and quantitative evaluation measurements. Results show that Pix2Pix outperforms Cycle GAN in accurately mapping cartoon characters to stick figures. Despite that, the Cycle GAN still managed to produce competing results.

The segmentation of objects and people in particular is an important problem in computer vision. In this paper, we focus on automatically segmenting a person from challenging video sequences in which we place no constraint on camera viewpoint, camera motion or the movements of a person in the scene. Our approach uses the most confident predictions from a pose detector as a form of anchor or keyframe stick figure prediction which helps guide the segmentation of other more challenging frames in the video. Since even state of the art pose detectors are unreliable on many frames -especially given that we are interested in segmentations with no camera or motion constraints -only the poses or stick figure predictions for frames with the highest confidence in a localized temporal region anchor further processing. The stick figure predictions within confident keyframes are used to extract color, position and optical flow features. Multiple conditional random fields (CRFs) are used to process blocks of video in batches, using a two dimensional CRF for detailed keyframe segmentation as well as 3D CRFs for propagating segmentations to the entire sequence of frames belonging to batches. Location information derived from the pose is also used to refine the results. Importantly, no hand labeled training data is required by our method. We discuss the use of a continuity method that reuses learnt parameters between batches of frames and show how pose predictions can also be improved by our model. We provide an extensive evaluation of our approach, comparing it with a variety of alternative grab cut based methods and a prior state of the art method. We also release our evaluation data to the community to facilitate further experiments. We find that our approach yields state of the art qualitative and quantitative performance compared to prior work and more heuristic alternative approaches. Propose a method for automatic segmentation of peopleNo constraints on camera or person in videosLearn model parameters without labeled segmented dataContribute labeled segmented video data for future researchProposed method performance favorable over other methods

A 2D human motion model developed based on polynomial regression data fit.Human motion modeled in three segments: backbone, upper body and lower body.Tolerance rate considers the acceptable range for reliable motion estimations.Classification accuracy for developed estimation model is on par with the actual. Motion estimation methods have been proposed via different approaches, such as silhouette based, model based and image based estimations. However, these methods are highly dependent on the quality of motion data for optimal classification accuracy. Further, because of the complexity of existing algorithms for motion estimation, there are difficulties in interpretation. Hence, the contribution of this work is to model simple human motions for the purpose of recognizing different activity behavior patterns for classification analysis. The model is made up of three body component integrations - Backbone (BB), Upper Body (UB) and Lower Body (LB) - to form a simple 2D human stick figure. Two case studies involving a publicly available video of walking, running and jumping motions as well as experimental captures of Yoga motions are studied. Video motions are simplified into time-step image snapshots, which are later translated into a numeric 2D coordinate system. Initially, the human pelvis is considered the origin of the stick figure. The stick model was drawn by integrating the BB, UB and LB components based on the 2D body joint coordinates. The motion estimation model applies the concept of polynomial fitting to the coordinates data. Computations on the polynomial fitting coefficient deviations at sequential time steps were performed to evaluate the estimation tolerance. A summation of the precedent time-step coordinates with the average deviation metric is used iteratively to estimate the joint coordinates of the stick figure in the subsequent time step to develop the entire motion model. Finally, the developed motion estimation mathematical model was compared to the actual motion phases for classification efficiencies using the Bayes, Lazy, Function, Meta, Misc, Rules and Trees classifiers. Our findings revealed the feasibility of using 2D stick-model matching estimation for human motion classification analysis.

We examined the informational value of biological motion from the arm in predicting the location of a thrown ball. In three experiments, participants were classified as being skilled and less skilled based on their actual performance on the task (i.e., using a within-task criterion). We then presented participants with a range of stick figure representations and required them to predict throw direction. In Experiment 1, we presented stick figure movies of a full body throwing action, right throwing arm plus left shoulder and throwing arm only. Participants were able to anticipate throw direction above chance under all conditions irrespective of perceptual skill level, with the perceptually skilled participants excelling under full body conditions. In Experiment 2, we neutralized dynamical differences in motion to opposing throw directions from the shoulder, elbow and wrist of the throwing arm. Neutralizing the wrist location negatively affected anticipation performance in all participants reducing accuracy to below chance. In Experiment 3, we presented movies of the motion wrist location alone and the upper section of the throwing arm (shoulder-elbow). Participants were able to successfully anticipate above chance in these latter two conditions. Our findings suggest that motion of the throwing arm contains multiple sources of information that can help facilitate the anticipation of goal-directed action. Perceptually skilled participants were superior in extracting informational value from motion at both the local and global levels when compared to less skilled counterparts.

As an important part of animation production, the existing method for drawing and rendering the CG animated characters according to motion information mostly relays on expensive manual processing. By adopting the conditional adversarial learning, an automatic animation rendering system for geometry structure attribute is proposed, using a deep convolution generative adversarial network called “pix2pixHD”. A training database containing a variety of motion stick figure is established for different virtual characters to achieve an end-to-end training system to verify this idea. The trained generator is the desired CG animation creator which shows great performance on visual quality and time efficiency proved by the experimental results.