Motion segmentation plays an important role in human motion analysis. Understanding the intrinsic features of human activities represents a challenge for modern science. Current solutions usually involve computationally demanding processing and achieve the best results using expensive, intrusive motion capture devices. In this thesis, research has been carried out to develop a series of methods for affordable and effective human motion assessment in the context of stand-up physical exercises. The objective of the research was to tackle the needs for an autonomous system that could be deployed in nursing homes or elderly people's houses, as well as rehabilitation of high profile sport performers. Firstly, it has to be designed so that instructions on physical exercises, especially in the case of elderly people, can be delivered in an understandable way. Secondly, it has to deal with the problem that some individuals may find it difficult to keep up with the programme due to physical impediments. They may also be discouraged because the activities are not stimulating or the instructions are hard to follow. In this thesis, a series of methods for automatic assessment production, as a combination of worded feedback and motion visualisation, is presented. The methods comprise two major steps. First, a series of key body poses are identified upon a model built by a multi-class classifier from a set of frame-wise features extracted from the motion data. Second, motion alignment (or synchronisation) with a reference performance (the tutor) is established in order to produce a second assessment model. Numerical assessment, first, and textual feedback, after, are delivered to the user along with a 3D skeletal animation to enrich the assessment experience. This animation is produced after the demonstration of the expert is transformed to the current level of performance of the user, in order to help encourage them to engage with the programme. The key body pose identification stage follows a two-step approach: first, the principal components of the input motion data are calculated in order to reduce the dimensionality of the input. Then, candidates of key body poses are inferred using multi-class, supervised machine learning techniques from a set of training samples. Finally, cluster analysis is used to refine the result. Key body pose identification is guaranteed to be invariant to the repetitiveness and symmetry of the performance. Results show the effectiveness of the proposed approach by comparing it against Dynamic Time Warping and Hierarchical Aligned Cluster Analysis. The synchronisation sub-system takes advantage of the cyclic nature of the stretches that are part of the stand-up exercises subject to study in order to remove out-of-sequence identified key body poses (i.e., false positives). Two approaches are considered for performing cycle analysis: a sequential, trivial algorithm and a proposed Genetic Algorithm, with and without prior knowledge on cyclic sequence patterns. These two approaches are compared and the Genetic Algorithm with prior knowledge shows a lower rate of false positives, but also a higher false negative rate. The GAs are also evaluated with randomly generated periodic string sequences. The automatic assessment follows a similar approach to that of key body pose identification. A multi-class, multi-target machine learning classifier is trained with features extracted from previous motion alignment. The inferred numerical assessment levels (one per identified key body pose and involved body joint) are translated into human-understandable language via a highly-customisable, context-free grammar. Finally, visual feedback is produced in the form of a synchronised skeletal animation of both the user's performance and the tutor's. If the user's performance is well below a standard then an affine offset transformation of the skeletal motion data series to an in-between performance is performed, in order to prevent dis-encouragement from the user and still provide a reference for improvement. At the end of this thesis, a study of the limitations of the methods in real circumstances is explored. Issues like the gimbal lock in the angular motion data, lack of accuracy of the motion capture system and the escalation of the training set are discussed. Finally, some conclusions are drawn and future work is discussed.

The purpose of this paper is to examine and compare two simple motion capturesystems. The first system consists of two cameras, and the second system consists of acamera with a depth sensor. The problem with both systems is their limited field ofview. If the actor is facing a camera, that camera will not be able to see an arm if thatarm is placed behind the back.My method in order to do this examination, was to record a number of different typesof motions with both systems, and then evaluate and compare the generated data fromthe two systems. This was done partly by applying it to a 3D character, and partly byinvestigating how good incomplete data could be repaired. Some motions wasrecorded multiple times, each with a different angle. The examination has resulted indifferent conclusions about the two systems.The process of using two cameras was very time consuming and the actor had to standfacing the cameras more or less. The depth sensing camera was shown to be able tohandle a wider range of motions, and the angle relative to the cameras wasn't aslimited. Some advantages could be found compared to the depth sensing camera,which had troubles handling certain types of arm and head rotations. This waspossible to handle with two cameras. / Validerat; 20140627 (global_studentproject_submitter)

<p>Motion Capture is an essential part of a world full of digital effects in movies and games. Understanding the pipelines between software is a crucial component of this research. Methods that create the motion capture structure today are reviewed, and how they are implemented in order to create the movements that we see in modern games and movies.</p>

Motion Capture is an essential part of a world full of digital effects in movies and games. Understanding the pipelines between software is a crucial component of this research. Methods that create the motion capture structure today are reviewed, and how they are implemented in order to create the movements that we see in modern games and movies.

This paper presents to find a solution, by designing a tool that could be used as a framework for the development of Motion Capture applications (Mocap) which is using with inertial Measurement Units (IMUs). Our main objective is how to find a tool that would be extremely fascinated and improved the accessibility to the development of Motion Capture applications. the methodology we applied for the literature review and we described and presented the factors about relevance of the technology and a different area of use and application, as well as to discover characteristics that need to be considered for the creation of a tool that could be utilized in the development of Mocap Applications. The second part of our thesis is certainly based on the design science research methodology; an artifact is planned through a designing a tool and prototype. We created a framework known as IMOTRAF which stands for Inertial Motion Tracking Framework that targeted more platforms than aREST framework, is to facilitate The Mocap application using by IMUs. The IMOTRAF framework should only focus in MCU/IMU platform. Throughout the collection data for the empirical analysis, we have learnt two protocols commonly used in wireless communication such as MQTT and Firmata. In this thesis we have implemented and tested to a new artifact that is made possible to connect many devices simultaneously via WIFI using by Firmata protocol.

Animals have evolved over billions of years and understanding these complex and intertwined systems have potential to advance the technology in the field of sports science, robotics and more. As such, a gait analysis using Motion Capture (MOCAP) technology is the subject of a number of research and development projects aimed at obtaining quantitative measurements. Existing MOCAP technology has limited the majority of studies to the analysis of the steady-state locomotion in a controlled (indoor) laboratory environment. MOCAP systems such as the optical, non-optical acoustic and non-optical magnetic MOCAP systems require predefined capture volume and controlled environmental conditions whilst the non-optical mechanical MOCAP system impedes the motion of the subject. Although the non-optical inertial MOCAP system allows MOCAP in an outdoor environment, it suffers from measurement noise and drift and lacks global trajectory information. The accuracy of these MOCAP systems are known to decrease during the tracking of the transient locomotion. Quantifying the manoeuvrability of animals in their natural habitat to answer the question “Why are animals so manoeuvrable?” remains a challenge. This research aims to develop an outdoor MOCAP system that will allow tracking of the steady-state as well as the transient locomotion of an animal in its natural habitat outside a controlled laboratory condition. A number of researchers have developed novel MOCAP systems with the same aim of creating an outdoor MOCAP system that is aimed at tracking the motion outside a controlled laboratory (indoor) environment with unlimited capture volume. These novel MOCAP systems are either not validated against the commercial MOCAP systems or do not have comparable sub-millimetre accuracy as the commercial MOCAP systems. The developed DGPS/MEMS-IMU multi-receiver fusion MOCAP system was assessed to have global trajectory accuracy of _0:0394m, relative limb position accuracy of _0:006497m. To conclude the research, several recommendations are made to improve the developed MOCAP system and to prepare for a field-testing with a wild animal from a family of a terrestrial megafauna.

Industrial robots are delivering more and more manipulation services in manufacturing. However, when the task is complex, it is difficult to programme a robot to fulfil all the requirements because even a relatively simple task such as a peg-in-hole insertion contains many uncertainties, e.g. clearance, initial grasping position and insertion path. Humans, on the other hand, can deal with these variations using their vision and haptic feedback. Although humans can adapt to uncertainties easily, most of the time, the skilled based performances that relate to their tacit knowledge cannot be easily articulated. Even though the automation solution may not fully imitate human motion since some of them are not necessary, it would be useful if the skill based performance from a human could be firstly interpreted and modelled, which will then allow it to be transferred to the robot. This thesis aims to reduce robot programming efforts significantly by developing a methodology to capture, model and transfer the manual manufacturing skills from a human demonstrator to the robot. Recently, Learning from Demonstration (LfD) is gaining interest as a framework to transfer skills from human teacher to robot using probability encoding approaches to model observations and state transition uncertainties. In close or actual contact manipulation tasks, it is difficult to reliabley record the state-action examples without interfering with the human senses and activities. Therefore, wearable sensors are investigated as a promising device to record the state-action examples without restricting the human experts during the skilled execution of their tasks. Firstly to track human motions accurately and reliably in a defined 3-dimensional workspace, a hybrid system of Vicon and IMUs is proposed to compensate for the known limitations of the individual system. The data fusion method was able to overcome occlusion and frame flipping problems in the two camera Vicon setup and the drifting problem associated with the IMUs. The results indicated that occlusion and frame flipping problems associated with Vicon can be mitigated by using the IMU measurements. Furthermore, the proposed method improves the Mean Square Error (MSE) tracking accuracy range from 0.8˚ to 6.4˚ compared with the IMU only method. Secondly, to record haptic feedback from a teacher without physically obstructing their interactions with the workpiece, wearable surface electromyography (sEMG) armbands were used as an indirect method to indicate contact feedback during manual manipulations. A muscle-force model using a Time Delayed Neural Network (TDNN) was built to map the sEMG signals to the known contact force. The results indicated that the model was capable of estimating the force from the sEMG armbands in the applications of interest, namely in peg-in-hole and beater winding tasks, with MSE of 2.75N and 0.18N respectively. Finally, given the force estimation and the motion trajectories, a Hidden Markov Model (HMM) based approach was utilised as a state recognition method to encode and generalise the spatial and temporal information of the skilled executions. This method would allow a more representative control policy to be derived. A modified Gaussian Mixture Regression (GMR) method was then applied to enable motions reproduction by using the learned state-action policy. To simplify the validation procedure, instead of using the robot, additional demonstrations from the teacher were used to verify the reproduction performance of the policy, by assuming human teacher and robot learner are physical identical systems. The results confirmed the generalisation capability of the HMM model across a number of demonstrations from different subjects; and the reproduced motions from GMR were acceptable in these additional tests. The proposed methodology provides a framework for producing a state-action model from skilled demonstrations that can be translated into robot kinematics and joint states for the robot to execute. The implication to industry is reduced efforts and time in programming the robots for applications where human skilled performances are required to cope robustly with various uncertainties during tasks execution.

Special effects (SFX) for film, television, and any type of video are usually digital, practical, or a mix of both. Animatronics is the use of robotics to mimic living movements, which is often used in the SFX industry. Currently, there is a gap between practical and digital effects, which means that post-production of practical effects leads to an inefficient workload. A robot is recorded on video, and if any digital enhancements or corrections are needed, the digital artists must start from nothing but the recorded video. Since the practical effects – controlling the animatronic- are using RC signals to manipulate servomotors, there is movement information that could be used to “record” movement into a digital space. This thesis project aims to create a way to bridge the gap between digital and physical by translating RC signals into digital animation. The RC signals used in this project were sent via a Taranis remote control, mixed using Open-TX software, and then translated into a digital animation rig in the 3D software Blender.

This thesis focuses on addressing the limitations of existing human motion prediction models by extending the prediction horizon to very long-term forecasts. The objective is to develop a model that achieves one of the best stable prediction horizons in the field, providing accurate predictions without significant error increase over time. Through the utilization of quantization based models our research successfully achieves the desired objective with the proposed aligned version of Mean Per Joint Position Error. The first of the two proposed models, an attention-based Vector Quantized Variational AutoEncoder, demonstrates good performance in predicting beyond conventional time boundaries, maintaining low error rates as the prediction horizon extends. While slight discrepancies in joint positions are observed, the model effectively captures the underlying patterns and dynamics of human motion, which remains highly applicable in real-world scenarios. Furthermore, our investigation into a correlation-based Vector Quantized Variational AutoEncoder, as an alternative to attention-based one, highlights the challenges in capturing complex relationships and meaningful patterns within the data. The correlation-based VQ-VAE’s tendency to predict flat outputs emphasizes the need for further exploration and innovative approaches to improve its performance. Overall, this thesis contributes to the field of human motion prediction by extending the prediction horizon and providing insights into model performance and limitations. The developed model introduces a novel option to consider when contemplating long-term prediction applications across various domains and sets the foundation for future research to enhance performance in long-term scenarios. / Denna avhandling fokuserar på att hantera begränsningarna i befintliga modeller för förutsägelse av mänskliga rörelser genom att utöka förutsägelsehorisonten till mycket långsiktiga prognoser. Målet är att utveckla en modell som uppnår en av de bästa stabila prognoshorisonterna inom området, vilket ger korrekta prognoser utan betydande felökning över tiden. Genom att använda kvantiseringsbaserade modeller uppnår vår forskning framgångsrikt det önskade målet med den föreslagna anpassade versionen av Mean Per Joint Position Error. Den första av de två föreslagna modellerna, en uppmärksamhetsbaserad Vector Quantized Variational AutoEncoder, visar goda resultat när det gäller att förutsäga bortom konventionella tidsgränser och bibehåller låga felfrekvenser när förutsägelsehorisonten förlängs. Även om små avvikelser i ledpositioner observeras, fångar modellen effektivt de underliggande mönstren och dynamiken i mänsklig rörelse, vilket förblir mycket tillämpligt i verkliga scenarier. Vår undersökning av en korrelationsbaserad Vector Quantized Variational AutoEncoder, som ett alternativ till en uppmärksamhetsbaserad sådan, belyser dessutom utmaningarna med att fånga komplexa relationer och meningsfulla mönster i data. Den korrelationsbaserade VQ-VAE:s tendens att förutsäga platta utdata understryker behovet av ytterligare utforskning och innovativa metoder för att förbättra dess prestanda. Sammantaget bidrar denna avhandling till området för förutsägelse av mänskliga rörelser genom att utöka förutsägelsehorisonten och ge insikter om modellens prestanda och begränsningar. Den utvecklade modellen introducerar ett nytt alternativ att ta hänsyn till när man överväger långsiktiga prediktionstillämpningar inom olika områden och lägger grunden för framtida forskning för att förbättra prestanda i långsiktiga scenarier.

[ES] La cirugía laparoscopia está considerada uno de los principales avances quirúrgicos en las últimas décadas. Esta técnica ha demostrado numerosas ventajas comparadas con la cirugía convencional abierta y ha sido extensamente usada para procesos quirúrgicos en el área abdominal. Para el paciente, la cirugía laparoscópica supone diversas ventajas, como por ejemplo menor dolor post operativo, tiempos de recuperación menores, menor riesgo de infección, o reducción del trauma. Para el cirujano en cambio, la situación es completamente diferente, esta práctica requiere mayor esfuerzo, concentración y estrés mental que la práctica convencional abierta. Además fuerza al cirujano a adoptar posiciones no-neutras en falanges, manos, muñecas, y brazos. Estas posturas no-neutras son la principal causa de fatiga muscular y aumentan el riesgo de problemas musculo-esqueléticos. Estos problemas han sido ampliamente estudiados por diferentes equipos de investigación, los cuales están tratando de mejorar la experiencia del cirujano en el quirófano. El enfoque utilizado en este estudio es diferente del utilizado anteriormente por la mayoría de estos equipos, los cuales suelen propones soluciones basadas en cambios ergonómicos con la intención de mejorar la geometría del mango de pistola convencional, ya que se considera ergonómicamente deficiente. El problema con este enfoque, es que las deficiencias no se encuentran únicamente en el mango, sino en la utilización de un punto de entrada fijo que fuerza a los cirujanos a mantener posiciones desfavorables. En este trabajo, se introduce el concepto "Libertad Postural" en el ámbito de la cirugía, este se basa en la hipótesis de que, si las herramientas no forzaran la posición de los cirujanos, estos mantendrían posiciones más favorables y cercanas al rango de posiciones neutras durante los procesos laparoscópicos. Los beneficios de este concepto han sido demostrados por medio de análisis de movimiento y de electromiografía de superficie, los cuales indican que la "Libertad Postural" es causante de un claro aumento de las posiciones neutras y de la reducción de la fatiga muscular, y han sido testeados por cirujanos en entornos simulados, los cuales encuentran beneficioso utilizar la "Libertad Postural" como característica base de este nuevo diseño de herramienta laparoscópica. En la sección final de este trabajo se propone un diseño que implementa el concepto de libertad postura con el cual se reduciría la fatiga muscular y los problemas musculo esqueléticos asociados a la práctica laparoscópica. Este diseño tiene la característica de actuar como una nueva sección del brazo, siendo una articulación que soporta los giros y grandes desplazamientos que normalmente tienen que desarrollar los brazos del cirujano. Además, esta solución es económica y fácil de fabricar, lo cual permitiría su uso por cirujanos de todo el mundo. / [CA] La cirurgia laparoscòpia està considerada un dels principals avanços quirúrgics en les últimes dècades. Aquesta tècnica ha demostrat nombrosos avantatges comparats amb la cirurgia convencional oberta i ha sigut extensament usada per a processos quirúrgics en l'àrea abdominal. Per al pacient, la cirurgia laparoscòpica suposa diversos avantatges, com per exemple menor dolor post operatiu, temps de recuperació menors, menor risc d'infecció, o reducció del trauma. Per al cirurgià en canvi, la situació és completament diferent, aquesta pràctica requereix major esforç, concentració i estrés mental que la pràctica convencional oberta. A més força al cirurgià a adoptar posicions no-neutres en falanges, mans, nines, i braços. Aquestes postures no-neutres són la principal causa de fatiga muscular i augmenten el risc de problemes musculo-esquelètics. Aquests problemes han sigut àmpliament estudiats per diferents equips d'investigació, els quals estan tractant de millorar l'experiència del cirurgià en el quiròfan. L'enfocament utilitzat en aquest estudi és diferent de l'utilitzat anteriorment per la majoria d'aquests equips, els quals solen proposes solucions basades en canvis ergonòmics amb la intenció de millorar la geometria del mànec de pistola convencional, ja que es considera ergonòmicament deficient. El problema amb aquest enfocament, és que les deficiències no es troben únicament en el mànec, sinó en la utilització d'un punt d'entrada fix que força als cirurgians a mantindre posicions desfavorables. En aquest treball, s'introdueix el concepte "Llibertat Postural" en l'àmbit de la cirurgia, aquest es basa en la hipòtesi que, si les eines no forçaren la posició dels cirurgians, aquests mantindrien posicions més favorables i pròximes al rang de posicions neutres durant els processos laparoscòpics. Els beneficis d'aquest concepte han sigut demostrats per mitjà d'anàlisi de moviment i de electromiografía de superfície, els quals indiquen que la "Llibertat Postural" és causant d'un clar augment de les posicions neutres i de la reducció de la fatiga muscular, i han sigut testats per cirurgians en entorns simulats, els quals troben beneficiós utilitzar la "Llibertat Postural" com a característica base d'aquest nou disseny d'eina laparoscòpica. En la secció final d'aquest treball es proposa un disseny que implementa el concepte de llibertat postura amb el qual es reduiria la fatiga muscular i els problemes *musculo esquelètics associats a la pràctica laparoscòpica. Aquest disseny té la característica d'actuar com una nova secció del braç, sent una articulació que suporta els girs i grans desplaçaments que normalment han de desenvolupar els braços del cirurgià. A més, aquesta solució és econòmica i fàcil de fabricar, la qual cosa permetria el seu ús per cirurgians de tot el món. / [EN] Laparoscopic surgery is considered one of the main surgical advances in the last decades, this technique has demonstrated numerous advantages compared to open conventional surgery and it is widely used in abdominal procedures around the world. For the patient, laparoscopic surgery suppose less post-operative pain, shorter recovery time, lower risk of infection, and reduction of the trauma among other benefits. For the surgeon, the situation is completely different, this practice requires more effort, concentration and mental stress than conventional open procedures. It forces the surgeon to adopt non-neutral postures with phalanges, hands, wrists, and arms being this non-neutral postures the main cause of muscular fatigue and high risk of musculoskeletal disorders. The poor ergonomic postures accelerate muscle fatigue and pain because, outside the neutral range, muscles require more energy to generate the same contractile force than in neutral position. This increase of muscular fatigue is associated with the potential to commit errors that may harm the patient during the surgery. Because this problem is widely studied and different research centers are already trying to improve their surgeons experience in the operation room, the approach used during this work is different than most of the ones presented in previous works. Generally, the solutions proposed are based on ergonomic changes in the handle shape of the instrument, because the conventional pistol-grip handle is considered ergonomically poor. But the problem is not only in the shape of the handle but also in the fixed point of entrance that force the positions for the surgeon despite the handle¿s shape. In this work, the concept of postural freedom in laparoscopic surgery is introduced and evaluated. The postural freedom concept is based on the hypothesis that the surgeon involuntarily would maintain neutral postures if the instrument does not force him or her to reach extreme position with the upper limbs. The benefits of this concept has been demonstrated, by means of electromyography and motion capture. It reduces the localized muscular fatigue and increases the number of neutral postures during laparoscopic simulations. In the final section it is proposed a design that implements the postural freedom concept with, according on the results, the potential to reduce the localized muscular fatigue and the musculoskeletal problems associated to the practice. The design proposed here acts as a new section on the arm, being an articulation that support the turns and big displacements that currently suffer the surgeon¿s body. The solution is affordable and easy to manufacture and could be used by surgeons worldwide. / Pace Bedetti, HM. (2019). The effect of "Postural Freedom" in laparoscopic surgery [Tesis doctoral]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/122312