Les atteintes posturales sont des conséquences connues du vol spatial. Un des facteurs de stabilité orthostatique et postural est le tonus musculaire, qui chute en microgravité. Les études sur les effets cardiovasculaires, neuromusculaires et posturaux de la microgravité sont nombreuses ; pourtant, le rôle des troubles neuromusculaires et cardiovasculaires dans l’atteinte orthostatique et posturale reste peu connu. Notre but était d’étudier des altérations vasculaires et neuromusculaires induites par la microgravité, ainsi que les liens entre eux. Nos études chez l’homme comprenaient un vol spatial de 6 mois, un alitement antiorthostatique de 21 jours et une immersion sèche de 3 à 5 jours. Ces conditions diffèrent par le niveau de stimulation d’appui. L'état cardiovasculaire a été évalué par des tests orthostatiques, neuromusculaire - par myotonométrie et la stabilité posturale - par stabilométrie. Notre travail montre qu’un vol de longue durée induit des troubles bien plus profonds que la microgravité simulé plus courte. De plus, l'immersion sèche induit des troubles plus graves que l'alitement, malgré sa durée plus courte. Nos données suggèrent que c'est la décharge d’appui qui définit la profondeur des perturbations. Le rôle principal de la diminution du tonus des muscles posturaux est mis en avant. Cette diminution se produit par voie réflexe par diminution d’afferentation des zones d’appui. Elle pourrait être responsable de l’intolérance orthostatique via la diminution de l'efficacité de la pompe musculaire favorisant le retour veineux, et de l’instabilité posturale - via l'augmentation des seuils de recrutement des motoneurones posturaux. / Postural and orthostatic impairment are both acknowledged consequences of spaceflight. One of the factors for orthostatic and postural stability is muscle tone, which decreases within the onset of microgravity. Studies of cardiovascular, neuromuscular and postural effects of microgravity are numerous ; yet the role of neuromuscular and vascular disorders in orthostatic and postural impairment remains unclear. We aimed to investigate vascular and neuromuscular alterations induced by microgravity, as well as their relationships. We studied healthy men exposed to 6-mo spaceflight, 21-day head-down bedrest and 3-to 5-day dry immersion. These conditions differ by the level of support unloading. Cardiovascular state was assessed by orthostatic tests, neuromuscular - by myotonometry, postural stability - by stabilometry. We found that long-term spaceflight induced much deeper disorders than relatively short-term modeled microgravity. Furthermore, immersion induced more severe disorders than bedrest, despite its shorter duration. Our data, along with literature, suggest that it is the support unloading that defines the depth of disturbances. The leading role in development of postural disorders under gravitational unloading belongs to decrease in postural muscle tone. This decrease occurs mainly by a reflex mechanism (decrease in support afferentation). It might be responsible for orthostatic impairment - via decrease in the efficiency of muscle pump promoting venous return, and for postural impairment - via increase in recruitment thresholds of postural motoneurons.

Made available in DSpace on 2016-06-02T20:18:19Z (GMT). No. of bitstreams: 1 4848.pdf: 2222922 bytes, checksum: cfbc4d52ea6d0f3d385cdda225ec2ba8 (MD5) Previous issue date: 2012-11-12 / Financiadora de Estudos e Projetos / Postural stability is an important ability of the human body in standing position as well as in dynamic activities like locomotion. It influences all motor and muscle aspects related to the execution of a motor task and is achieved by appropriate support conditions, coordinated muscle activity and proprioceptive information. The center of pressure behavior can be studied under different conditions, providing information on how the body reacts to postural instabilities. Thus the main purpose of this study is to propose a methodology for the study of the center of pressure behavior in order to evaluate static and dynamic equilibrium conditions of the human body. In order to achieve the goals, the structure of this thesis is composed of three studies. The equilibrium control during single leg ballet poses and the anticipatory postural adjustments prior to the first step in gait were discussed in the first and second study respectively. In the third study, methodological aspects were reviewed and a data processing standardization to study the center of pressure behavior during gait initiation was proposed. Dynamometry with force platforms was the measurement method used for all studies. The results allow to identify balance control strategies in ballet dancers and anticipatory postural adjustments existing during the transition from standing still to the cyclic gait steps. Some clinical applications of the results are presented and also directions for future studies. / A estabilidade postural é uma capacidade necessária ao corpo humano na posição parada em pé e nas atividades dinâmicas, como a locomoção, que influencia todos os aspectos motores e musculares relacionados à realização de uma tarefa. Esta é garantida através de formas de apoio, de ação coordenada dos músculos e atividade proprioceptiva, formando a base essencial para a realização de movimentos. O comportamento do centro de pressão pode ser estudado em diferentes condições, fornecendo informações sobre como o corpo reage a instabilidades posturais. Assim, o objetivo principal deste estudo é propor uma metodologia para o estudo do comportamento do centro de pressão tanto em condições estáticas quanto dinâmicas. A fim de alcançar os objetivos, a estrutura desta tese é composta de três estudos. São discutidos em estudos independentes os processos de controle do equilíbrio durante atividades estáticas, como as poses unipodais do ballet, e também dinâmicas, como os ajustes posturais antecipatórios prévios à inicialização do passo. No primeiro estudo foram estudados aspectos relacionados ao controle da estabilidade e de estratégias para a manutenção do equilíbrio durante três posições de apoio unipodal do ballet, executadas em posição de meia-ponta. No segundo estudo, avaliou-se os ajustes posturais antecipatórios em diferentes faixas etárias e foram discutidas suas relações com o processo de inicialização do passo em condições fisiológicas e patológicas. No terceiro estudo, sugeriu-se uma padronização metodológica para o cálculo das variáveis examinadas nos estudos que envolvem o comportamento do centro de pressão na inicialização do passo. A dinamometria com plataformas de força foi o método de medição empregado para todos os estudos. Os resultados permitem determinar estratégias para o controle do equilíbrio em bailarinas e para os ajustes posturais antecipatórios que ocorrem na transição da posição em pé parada para a marcha cíclica. São apresentadas algumas implicações clínicas dos resultados e perspectivas para estudos futuros.

Made available in DSpace on 2016-12-06T17:07:16Z (GMT). No. of bitstreams: 1 Joao Otacilio.pdf: 1115427 bytes, checksum: b2c572e56990d8fc350a9e27e16cffbe (MD5) Previous issue date: 2008-04-25 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / The aim of this study was to examine the influence of the rearfoot eversion motion on the biomechanical variables of the walking related with the plantar pressure distribution and the center of pressure (COP). Twenty-one male subjects (mean age 27 years ± 8 years, height 1.78m ± 0.6m and body mass 76kg ± 10kg) have participated of the study. Subjects were separate into two groups considering the Maximum Rearfoot Eversion Angle: Normal Group (n-11) - which had an angle < 8° and Overpronation Group (n=10) - which had an angle &#8805; 8°. The experimental data acquisition consisted in the evaluation of the barefoot gait in a straight line on a EVA walkway (flat stuff), and a controlled speed of 5 km / h ± 5%. The variables examined were: Maximum Rearfoot Eversion Angle, Media Plantar Pressure, Plantar Pressure Peak, Contact Area, Relative Load, Mean Velocity of the COP and Medial and Lateral displacement of the COP. The kinematic data has been acquired by the Spica Technology Corporation video system with two video cameras synchronized with a sampling rate of 955 Hz. For the kinetic data acquisition was used the Novel Emed-XR system with a sampling rate of 100 Hz. The Shapiro-Wilk test has been applied for the statistical analysis to verify the normality of the data and the statistical test One-Way ANOVA was used to compare the kinetic variables intra-group in different regions of the foot. The Student t-test was used to compare these inter-groups variables and the Pearson statistical test to check possible correlation between the Maximum Rearfoot Eversion Angle and kinetic variables. The level of significance adopted was 0.05. Analyzing the variables Media Plantar Pressure, Plantar Pressure Peak and Relative Load between different regions of the foot intra-groups, had been observed that both groups has shown a similar pattern of distribution of plantar pressure, but differentiating themselves only by the intensities of these variables. Plantar Pressure Peak and Contact Area variables have been compared among themselves in different regions of the foot inter-groups and, it was observed that the Normal Group showed higher mean values significant statistically, especially on the region of the heel and mid-foot. There was no significant statistically difference on the regions examined when the variables Media Plantar Pressure, Relative Load, Mean Velocity of the COP and Medial and Lateral displacement of the COP were compared between Normal Group and Overpronation Group. Analyzing possible correlations between the Maximum Rearfoot Eversion Angle and kinetic variables can be observed that the variables Media Plantar Pressure, Plantar Pressure Peak, Contact Area and Relative Load have shown positive significant statistically correlations with the Maximum Rearfoot Eversion Angle mainly in the mid-foot. However, there were no correlations on the variables of Mean Velocity of the COP and Medial and Lateral Displacement of the COP. These results suggest that the increase in the rearfoot eversion angle (overpronation) affects considerably some biomechanical variables such as the distribution of plantar pressure during the gait. This study demonstrates the importance of the analysis of the distribution of pressure on the clinical and preventive situation, since it has a great potential to predict abnormal movements during the locomotion. / Esta pesquisa teve como objetivo analisar a influência do movimento de eversão do calcanhar sobre as variáveis biomecânicas da marcha relativas à distribuição de pressão plantar (DPP) e o centro de pressão (COP). Participaram do estudo 21 sujeitos do sexo masculino (média de idade 27 anos ± 8 anos, estatura de 178cm ± 6cm e massa corporal de 76kg ± 10kg). Os sujeitos foram divididos em dois grupos, considerando o Ângulo Máximo de Eversão do Calcanhar: Grupo Normal (n=11) - sujeitos que apresentavam Ângulo Máximo de Eversão do Calcanhar < 8° e Grupo Overpronado (n=10) - sujeitos que apresentavam Ângulo Máximo de Eversão do Calcanhar &#8805; 8°. A coleta de dados consistiu - se em avaliar o andar de forma descalça em linha reta sobre uma passarela de EVA sem qualquer inclinação em relação à linha do horizonte e com uma velocidade controlada de 5km/h ± 5%. As variáveis analisadas foram: Ângulo Máximo de Eversão do Calcanhar, Pressão Plantar Média, Pico de Pressão Plantar, Área de contato, Carga Relativa, Velocidade Média do COP e Deslocamento Medial e Lateral do COP. Para a aquisição dos dados cinemáticos foi utilizado o sistema Spica Technology Corporation com duas câmeras de vídeo sincronizadas, com taxa de amostragem de 955Hz. Para a aquisição dos dados cinéticos utilizou-se o sistema Novel Emed- XR com taxa de amostragem de 100Hz. Na análise estatística foi aplicado o teste de Shapiro-Wilk para verificar a normalidade dos dados. Para comparar as variáveis cinéticas intra-grupo nas diferentes regiões do pé, foi utilizado o teste ANOVA One-Way. Já comparando estas variáveis inter-grupos, foi utilizado o teste t de Student para amostras independentes. Para verificar possíveis correlações entre o Ângulo Máximo de Eversão do Calcanhar e as variáveis cinéticas analisadas, utilizou-se o teste de Pearson. O nível de significância adotado foi de 0,05. Ao comparar as variáveis Pressão Plantar Média , Pico de Pressão Plantar e Carga Relativa entre as diferentes regiões do pé intra-grupo, pode-se observar que ambos os grupos apresentaram um padrão de distribuição de pressão plantar semelhante, diferenciando-se apenas pelas intensidades dessas variáveis. Já ao comparar as variáveis Pico de Pressão Plantar e Área de Contato nas diferentes regiões do pé intergrupos, observou-se que o Grupo Normal apresentou maiores valores médios, estatisticamente significativos, principalmente na região do calcanhar e do médio pé. Em relação às variáveis Pressão Plantar Média , Carga Relativa , Velocidade Média do COP e Deslocamento Medial e Lateral do COP não foram encontradas diferenças estatisticamente significativas ao comparar o Grupo Normal e o Grupo Overpronado em nenhuma das regiões analisadas. Ao analisar possíveis correlações entre o Ângulo Máximo de Eversão do Calcanhar e as variáveis cinéticas, pode-se observar que as variáveis Pressão Plantar Média , Pico de Pressão Plantar , Área de Contato e Carga Relativa apresentaram correlações positivas estatisticamente significativas com o Ângulo Máximo de Eversão do Calcanhar , principalmente na região do médio pé. Já as variáveis Velocidade Média do COP e Deslocamento Medial e Lateral do COP não apresentaram correlações estatisticamente significativas. Assim, é possível concluir que o aumento do ângulo de eversão do calcanhar (overpronação) afetou consideravelmente algumas variáveis biomecânicas da distribuição de pressão plantar durante a marcha. Isso demonstra a importância da análise da distribuição de pressão plantar no quadro clínico e preventivo, pois a mesma possui um grande potencial para predizer movimentos anormais durante a locomoção.

Submitted by Luciana Ferreira (lucgeral@gmail.com) on 2015-10-21T12:02:13Z No. of bitstreams: 2 Dissertação - Renata da Costa Barbosa - 2014.pdf: 2041466 bytes, checksum: b05943f80e79bca8b9f3398d1706e187 (MD5) license_rdf: 23148 bytes, checksum: 9da0b6dfac957114c6a7714714b86306 (MD5) / Approved for entry into archive by Luciana Ferreira (lucgeral@gmail.com) on 2015-10-21T12:10:02Z (GMT) No. of bitstreams: 2 Dissertação - Renata da Costa Barbosa - 2014.pdf: 2041466 bytes, checksum: b05943f80e79bca8b9f3398d1706e187 (MD5) license_rdf: 23148 bytes, checksum: 9da0b6dfac957114c6a7714714b86306 (MD5) / Made available in DSpace on 2015-10-21T12:10:02Z (GMT). No. of bitstreams: 2 Dissertação - Renata da Costa Barbosa - 2014.pdf: 2041466 bytes, checksum: b05943f80e79bca8b9f3398d1706e187 (MD5) license_rdf: 23148 bytes, checksum: 9da0b6dfac957114c6a7714714b86306 (MD5) Previous issue date: 2014-11-28 / Understanding how the postural control system is impaired with aging can help identify elderly at risk of falling. In order to study the postural control, center of pressure (CP) behavior can be analyzed. Classical descriptors are commonly used for the CP analysis, however, modern descriptors have been developed aiming to provide more information about the underlying processes involved in the postural control. Aims: Analyze and compare classical and modern descriptors used to analyze the postural control in elderly subjects in quiet standing posture, using data acquired from a force platform in horizontal and inclined surfaces. Methods: The study sample consisted of 17 elderly subjects who remained on a force platform in the upright posture for 70 seconds. The data acquisition was performed with the platform on a horizontal surface and again on a surface inclined at 14 degrees with dorsiflexion and later with plantar flexion of the ankle. For each slope, the procedure was repeated three times with eyes open (EO ) and three times with eyes closed (EC). The initial 10 seconds were discarded and then, CP times series were analyzed in the anteroposterior (AP) and mediolateral (ML) directions. The classical descriptors used were in the time in the frequency domain and the modern descriptors were: Detrended Fluctuations Analysis (DFA), Stabilogram Diffusion Analysis (SDA) and the Sway Density Curve (SDC). Results: In the classical analysis, the results showed significant differences in all comparisons made and, in the modern analysis, the variables provided by the SDA and SDC also showed significant differences between comparisons, however, the DFA did not provide any difference between the conditions. Conclusion: Results provided by the classical variables and by the SDA and the SDC suggest a lower stability of elderly subjects in the inclined surface with dorsiflexion followed by plantar flexion and the eyes closed condition. More studies with the modern descriptors are necessary to better understand their results. / Entender como o sistema de controle postural é comprometido com o processo de envelhecimento pode contribuir na identificação de idosos com risco de quedas. Para estudar o controle postural pode-se analisar o comportamento do Centro de Pressão (CP). Descritores clássicos comumente são utilizados para a análise do CP, no entanto, descritores modernos têm sido desenvolvidos, com o intuito de fornecer mais informações sobre os processos subjacentes ao controle postural. Objetivos: Analisar e comparar descritores clássicos e modernos para análise do controle postural em sujeitos idosos na postura ereta quieta, utilizando dados adquiridos na plataforma de força no plano e com inclinação. Métodos: A amostra do estudo foi composta por 17 indivíduos idosos que permaneceram sobre uma plataforma de força na postura ortostática por 70 segundos. A aquisição dos dados foi realizada com uma plataforma sobre uma superfície horizontal e depois sobre uma superfície inclinada a 14 graus nas posições de flexão dorsal e flexão plantar do tornozelo. Para cada inclinação, o procedimento foi repetido três vezes com os olhos abertos (OA) e três vezes com os olhos fechados (OF). Depois de descartados os 10 s iniciais, foram analisadas as séries temporais do CP na direção anteroposterior (AP) e mediolateral (ML). Foram utilizados alguns descritores clássicos no domínio do tempo e da frequência e os descritores modernos: Detrended Fluctuation Analysis (DFA), Stabilogram Diffusion Analysis (SDA) e pela Sway Density Curve (SDC). Resultados: Na análise clássica os resultados indicaram diferenças significativas em todas as comparações realizadas, na análise moderna, as variáveis fornecidas pela SDA e pela SDC também apresentaram diferenças significativas entre as comparações, porém, a DFA não conseguiu apontar tais diferenças. Conclusão: Os resultados fornecidos pelas variáveis clássicas, SDA e a SDC sugerem uma menor estabilidade de sujeitos idosos na superfície inclinada com flexão dorsal seguida da flexão plantar e na condição de olho fechado. Ainda são necessários a realização de mais estudos utilizando tais descritores para uma melhor compreensão de seus resultados.

A manutenção do equilíbrio depende da ativação sinérgica de músculos dos dois hemicorpos, e há evidências de que essa coordenação é mediada por circuitos medulares, que estão sob controle supra-segmentar. O objetivo desse trabalho é descrever mecanismos neurofisiológicos e biomecânicos envolvidos no controle postural de sujeitos saudáveis frente a uma perturbação provocada por uma contração reflexa, enfatizando-se os mecanismos associados à coordenação entre membros. A perturbação postural ocorreu em resposta a um estímulo elétrico unilateral no nervo tibial. Devido a restrições em estudos anteriores, utilizou-se uma ampla abordagem (múltiplos músculos, reflexos cruzados) e estimulação precisamente controlada. Os resultados mostraram um complexo padrão de ativação dos músculos dos membros inferiores bilateralmente. Logo após o estímulo, foram encontradas respostas de curta e média latência em músculos da perna e da coxa. Posteriormente, foram observadas algumas ações musculares de longa latência nos músculos mais distais, que provavelmente foram ativadas em resposta às oscilações posturais. As respostas musculares iniciais sugerem que as informações aferentes e os reflexos medulares possuem uma função muito importante na regulação da coordenação entre membros, durante a manutenção da postura ereta quieta. / Balance depends on the synergic activation of muscles bilaterally, and there is evidence that this coordination is mediated by spinal circuits, which are under supra-spinal control. The objective of this study is to describe neurophysiologic and biomechanical mechanisms involved in the postural control of healthy subjects submitted to a disturbance provoked by a muscular reflex contraction. The postural perturbation was caused by a unilateral electric stimulation to the popliteal fossa. The analysis emphasizes the mechanisms associated with interlimb coordination. In this work, methodological approaches expanded those of previous work, the recordings being done bilaterally and the stimulus being precisely controlled. The results showed a complex pattern of bilateral muscular activation. Short and medium latency responses were found in the leg and thigh muscles. These were followed by some muscular activity at longer latencies, probably occurring due to the postural oscillations. The initial muscular responses suggest that the afferent inflow and the spinal cord reflexes have an important function in the between-limb coordination during the standing posture.

INTRODUCTION: La stimulation vestibulaire galvanique (GVS) est utilisée pour évaluer l’intégrité du système vestibulaire et améliorer notre compréhension des mécanismes de l‘équilibre. Néanmoins les réponses évoquées montrent une grande variabilité interindividuelle ce qui rend la compréhension du rôle du système vestibulaire difficile. OBJECTIF: Développer un protocole d’évaluation d’un seuil vestibulaire objectif spécifique à la personne. MÉTHODES: Dix-huit sujets sains droitiers se tenaient debout sur une plate-forme de force, les yeux fermés, la tête vers l’avant. L’accélération de la tête était enregistrée lorsque la GVS (durée: 200 ms) était appliquée à des intensités de 1 à 4,5mA. Des courbes de recrutement ont été générées afin de déterminer le seuil objectif (T). Puis, les participants ont été stimulés à différentes intensités relatives au seuil (0,5T; 0,75T; 1T et 1,5T). L’aire de l’ellipse de confiance (AE) à 95%, la vitesse de déplacement du centre de pression (CoP) et l’activité électromyographique du soléaire (SOL) ont été mesurées. RÉSULTATS: 1) Un seuil objectif a été déterminé pour chaque sujet basé sur l’accélération de la tête. 2) L’aire de l’ellipse, pendant la stimulation, corrélait avec l’intensité de stimulation (r=0,95; p=0,03). 3) L’amplitude de la 1ère phase du patron triphasique de la vitesse de déplacement du CoP corrélait aussi avec l’intensité de stimulation (r=0,98; 0,04). 4) En plus, l’amplitude de la réponse musculaire à moyenne latence induite par la GVS sur le SOL montrait une corrélation significative avec l’intensité de stimulation (r=0,7; p=0,045). DISCUSSION: Un seuil objectif vestibulaire peut être identifié par un accéléromètre. Les réponses vestibulaires mesurées par l’AE et le CoP sont proportionnelles aux intensités de stimulation relatives au seuil objectif déterminé. / INTRODUCTION: Galvanic vestibular stimulation (GVS) is used to assess the integrity of the vestibular system and to improve our understanding of the mechanisms of balance. However, the GVS-induced responses show great inter-individual variability, which makes it difficult to understand the contribution of the vestibular system in maintaining balance. OBJECTIVE: To develop a protocol identifying an objective vestibular threshold for GVS in order to limit this variability observed on GVS-induced responses. METHODS: Eighteen healthy right-handed subjects stood on a force platform, eyes closed, head forward. The head acceleration was recorded when the GVS (duration: 200 ms) was applied at intensities varying between 1 and 4.5mA. Recruitment curves were reconstructed to determine the objective threshold (T). Then, the participants were stimulated at different intensities relative to threshold (0.5T; 0.75T; 1T and 1.5T). The 95% confidence ellipse area, the velocity of the center of pressure (CoP) displacement and the electromyographic activity of the soleus muscle (SOL) were measured. RESULTS: 1) An objective threshold was determined for each subject based on the acceleration of the head. 2) The area of the ellipse, during stimulation, correlated with the stimulation intensity (r = 0.95; p = 0.03). 3) The amplitude of the 1st peak of the three-phase CoP velocity pattern also correlated with the stimulation intensity (r = 0.98; 0.04). 4) In addition, the amplitude of the medium latency response induced by the GVS on the SOL showed a significant correlation with the stimulation intensity (r = 0.7; p = 0.045). DISCUSSION: An objective vestibular threshold can be identified by an accelerometer. The vestibular responses measured by the ellipse area and the CoP are proportional to the stimulation intensities relative to the determined objective threshold.

Mechanical overburdening is a major risk factor that provokes non-infectious claw diseases. Moreover, lameness-causing lesions often remain undetected and untreated. Therefore, prevention of claw tissue overburdening is of interest, especially by analyzing harmful effects within dairy cows’ housing environment. However, objective “on-cow” methods for bovine gait analysis are underdevel- oped. The purpose of the study was to apply an innovative mobile pressure sensor system attached at the claws to perform pedobarometric gait analysis. A further goal was the supplementation with accelerative data, generated simultaneously by use of two inertial measurement units (IMUs), attached at metatarsal level. IMU data were analyzed with an automatic step detection algorithm. Gait analysis was performed in ten dairy cows, walking and trotting on concrete flooring and rubber mats. In addition to the basic applicability of the sensor systems and with the aid of the automatic step detection algorithm for gait analysis in cows, we were able to determine the impact of the gait and flooring type on kinematic and kinetic parameters. For pressure sensor output, concrete was associated with significantly (p < 0.001) higher maximum and average pressure values and a significantly smaller contact area, compared to rubber mats. In contrast to walking, trotting led to a significantly higher force, especially under the medial claw. Further, IMU-derived parameters were significantly influenced by the gait. The described sensor systems are useful tools for detailed gait analysis in dairy cows. They allow the investigation of actors which may affect claw health negatively.

No description available.

No description available.

The deep learning technique Human Pose Estimation (or Human Keypoint Detection) is a promising field in tracking a person and identifying its posture. As posture and balance are two closely related concepts, the use of human pose estimation could be applied to fall prevention. By deriving the location of a persons Center of Mass and thereafter its Center of Pressure, one can evaluate the balance of a person without the use of force plates or sensors and solely using cameras. In this study, a human pose estimation model together with a predefined human weight distribution model were used to extract the location of a persons Center of Pressure in real time. The proposed method utilized two different methods of acquiring depth information from the frames - stereoscopy through two RGB-cameras and with the use of one RGB-depth camera. The estimated location of the Center of Pressure were compared to the location of the same parameter extracted while using the force plate Wii Balance Board. As the proposed method were to operate in real-time and without the use of computational processor enhancement, the choice of human pose estimation model were aimed to maximize software input/output speed. Thus, three models were used - one smaller and faster model called Lightweight Pose Network, one larger and accurate model called High-Resolution Network and one model placing itself somewhere in between the two other models, namely Pose Residual Network. The proposed method showed promising results for a real-time method of acquiring balance parameters. Although the largest source of error were the acquisition of depth information from the cameras. The results also showed that using a smaller and faster human pose estimation model proved to be sufficient in relation to the larger more accurate models in real-time usage and without the use of computational processor enhancement. / Djupinlärningstekniken Kroppshållningsestimation är ett lovande medel gällande att följa en person och identifiera dess kroppshållning. Eftersom kroppshållning och balans är två närliggande koncept, kan användning av kroppshållningsestimation appliceras till fallprevention. Genom att härleda läget för en persons tyngdpunkt och därefter läget för dess tryckcentrum, kan utvärdering en persons balans genomföras utan att använda kraftplattor eller sensorer och att enbart använda kameror. I denna studie har en kroppshållningsestimationmodell tillsammans med en fördefinierad kroppsviktfördelning använts för att extrahera läget för en persons tryckcentrum i realtid. Den föreslagna metoden använder två olika metoder för att utvinna djupseende av bilderna från kameror - stereoskopi genom användning av två RGB-kameror eller genom användning av en RGB-djupseende kamera. Det estimerade läget av tryckcentrat jämfördes med läget av samma parameter utvunnet genom användning av tryckplattan Wii Balance Board. Eftersom den föreslagna metoden var ämnad att fungera i realtid och utan hjälp av en GPU, blev valet av kroppshållningsestimationsmodellen inriktat på att maximera mjukvaruhastighet. Därför användes tre olika modeller - en mindre och snabbare modell vid namn Lightweight Pose Network, en större och mer träffsäker modell vid namn High-Resolution Network och en model som placerar sig någonstans mitt emellan de två andra modellerna gällande snabbhet och träffsäkerhet vid namn Pose Resolution Network. Den föreslagna metoden visade lovande resultat för utvinning av balansparametrar i realtid, fastän den största felfaktorn visade sig vara djupseendetekniken. Resultaten visade att användning av en mindre och snabbare kroppshållningsestimationsmodellen påvisar att hålla måttet i jämförelse med större och mer träffsäkra modeller vid användning i realtid och utan användning av externa dataprocessorer.