scholarly journals Human Motion Gesture Recognition Based on Computer Vision

Complexity ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Rui Ma ◽  
Zhendong Zhang ◽  
Enqing Chen

Human motion gesture recognition is the most challenging research direction in the field of computer vision, and it is widely used in human-computer interaction, intelligent monitoring, virtual reality, human behaviour analysis, and other fields. This paper proposes a new type of deep convolutional generation confrontation network to recognize human motion pose. This method uses a deep convolutional stacked hourglass network to accurately extract the location of key joint points on the image. The generation and identification part of the network is designed to encode the first hierarchy (parent) and the second hierarchy (child) and show the spatial relationship of human body parts. The generator and the discriminator are designed as two parts in the network, and they are connected together in order to encode the possible relationship of appearance and, at the same time, the possibility of the existence of human body parts and the relationship between each part of the body and its parental part coding. In the image, the key nodes of the human body model and the general body posture can be identified more accurately. The method has been tested on different data sets. In most cases, the results obtained by the proposed method are better than those of other comparison methods.

Author(s):  
WARREN LONG ◽  
YEE-HONG YANG

Motion provides extra information that can aid in the recognition of objects. One of the most commonly seen objects is, perhaps, the human body. Yet little attention has been paid to the analysis of human motion. One of the key steps required for a successful motion analysis system is the ability to track moving objects. In this paper, we describe a new system called Log-Tracker, which was recently developed for tracking the motion of the different parts of the human body. Occlusion of body parts is termed a forking condition. Two classes of forks as well as the attributes required to classify them are described. Experimental results from two gymnastics sequences indicate that the system is able to track the body parts even when they are occluded for a short period of time. Occlusions that extend for a long period of time still pose problems to Log-Tracker.


2016 ◽  
Vol 248 ◽  
pp. 155-160
Author(s):  
Andrzej Kot ◽  
Agata Nawrocka

Harmonious cooperation of the skeletal, muscular and nervous systems, forming a human motion organ, is responsible for all undertaken movement activities. Motion organ in the illustrated embodiment responsible not only for two basic motion activities, locomotion and manipulation, but also for maintaining the posture of the human body. Standing posture control makes a particular dimension of physical activity, because correct, stable posture determines the ability to perform most human movements. In the case of a man to maintain a balance in a standing position seems to be something obvious and does not require much effort, but with the advent of lesions or aging we begin to see how complex it is the process of balance control. The changes lead to impaired balance control which in turn can lead to the appearance of postural instability and in extreme circumstances, even to collapse. Maintaining a stable posture it is primarily associated with motor control provided by the human nervous system. The nervous system acts as an posture control system and most of all giving to a body well-defined silhouette. This control relies heavily on the integration of information from the human receptor system. Muscle, joint, tendon and skin receptors communicate first to the brain information about the movement and position of individual body parts and then feedback these signals to the muscles, causing reflex reactions allowing for correction of posture and thus return the center of gravity to a position that maintaining equilibrium. Subdivide those human body into segments linked closely with the system osteoarthritis limbs and trunk can create a system of interconnected pendulums with many degrees of freedom. In the case of standing it will be largely complicated inverted pendulums system by which activities phenomena associated with maintaining balance and locomotion can be modeled. If additionally in an upright position, taking into account the natural motion restrictions movements in all joints except the ankles will be blocked, the body will be a close approximation behave like a rigid body. So we can assume that for supporting the human body at the ankle, it will behave like an inverted pendulum. The article presents the ways of describing the equilibrium of man as an inverted pendulum.


2019 ◽  
Vol 8 (3) ◽  
pp. 1014-1024

In this paper, a computational model is proposed to mimic an action’s semantic, procedural and skill learning’s by an abstract modeling of cortical columns of the Neocortex, Basal ganglia and Cerebellum brain region. In proposed work, the action semantic Learning makes a robot capable to learn an action in terms of their body parts movement sequence that allows it to recognize the learnt action by seeing as well. Whereas in procedural, it allows to learn tasks in the form of action’s hierarchy and makes it capable to capture the environmental features as a context for action’s activations. The skill memory also been added in the proposed work which allows an agent to translate the action as per the current demand of the action. Also, the model has used Vnect model of computer vision to map the human motion into sequence of 3D skeleton of human body, therefore the model can learn by seeing, like humans. In experimental work, the model is tested on vague samples of few actions, where the model is found robust in action recognition task and performed well as per the expectations


Author(s):  
Bu S. Park ◽  
Sunder S. Rajan ◽  
Leonardo M. Angelone

We present numerical simulation results showing that high dielectric materials (HDMs) when placed between the human body model and the body coil significantly alter the electromagnetic field inside the body. The numerical simulation results show that the electromagnetic field (E, B, and SAR) within a region of interest (ROI) is concentrated (increased). In addition, the average electromagnetic fields decreased significantly outside the region of interest. The calculation results using a human body model and HDM of Barium Strontium Titanate (BST) show that the mean local SAR was decreased by about 56% (i.e., 18.7 vs. 8.2 W/kg) within the body model.


2017 ◽  
Vol 2017 (2) ◽  
Author(s):  
Kwan Tze-wan

AbstractIn the Shuowen, one of the earliest comprehensive character dictionaries of ancient China, when discussing where the Chinese characters derive their structural components, Xu Shen proposed the dual constitutive principle of “adopting proximally from the human body, and distally from things around.” This dual emphasis of “body” and “things around” corresponds largely to the phenomenological issues of body or corporeality on the one hand, and lifeworld on the other. If we borrow Heidegger’s definition of Dasein as Being-in-the world, we can easily arrive at a reformulation of Xu Shen’s constitutive principle of the Chinese script as one that concerns “bodily Dasein.” By looking into various examples of script tokens we can further elaborate on how the Chinese make use not only of the body in general but various body parts, and how they differentiate their life world into material nature, living things, and a multifaceted world of equipment in forming a core basis of Chinese characters/components, upon which further symbolic manipulation such as “indication”, “phonetic borrowing”, semantic combination, and “annotative derivation”, etc. can be based. Finally, examples will be cited to show how in the Chinese scripts the human body (and its parts) might interact with other’s bodies (and their parts) or with “things around” (whether nature, living creatures, or artifacts) in various ways to cover the social, environmental, ritual, technical, economical, and even intellectual aspects of human experience. Bodily Dasein, so to speak, provides us with a new perspective of understanding and appreciating the entire scope of the Chinese script.


Author(s):  
Cristóbal Pera

ABSTRACTIf the human body is really a fabric, should surgeons be considered architects, as some surgeons describe themselves today? The author raises and analyzes this question, and he concludes that vsurgeons cannot be considered as such: the architect is the creator of his work —fabric or building—, but the surgeon is not the creator of this complex biological fabric —vulnerable and subject to deterioration and with an expiration date— which is the human body. This body is the object upon which his hands and instruments operate. The surgeon cures and heals wounds, immobilizes and aligns fractured bones in order to facilitate their good and timely repair, and cuts open the body’s surface in order to reach its internal organs. He also explores the body with his hands or instruments, destroys and reconstructs its ailing parts, substitutes vital organs taken from a donor’s foreign body, designs devices or prostheses, and replaces body parts, such as arteries and joints, that are damaged or worn out. In today’s culture, dominated by the desire to perfect the body, other surgeons keep retouching its aging façade, looking for an iconic and timeless beauty. This longing can drive, sometimes, to surgical madness. The surgeon is not capable of putting into motion, from scratch, a biological fabric such as the human body. Thus, he can’t create the subject of his work in the way that an architect can create a building. In contrast, the surgeon restores the body’s deteriorated or damaged parts and modifies the appearance of the body’s façade.RESUMEN¿Si el cuerpo humano fuera realmente una fábrica, podría el cirujano ser considerado su arquitecto, como algunos se pregonan en estos tiempos? Esta es la cuestión planteada por el autor y, a tenor de lo discurrido, su respuesta es negativa: porque así como el arquitecto es el artífice de su obra —fábrica o edificio— el cirujano no es el artífice de la complejísima fábrica biológica —vulnerable, deteriorable y caducable— que es el cuerpo humano, la cual le es dada como objeto de las acciones de sus manos y de sus instrumentos. El cirujano cura y restaña sus heridas, alinea e inmoviliza sus huesos fracturados para que su reparación llegue a buen término, penetra por sus orificios naturales o dibuja sobre la superficie corporal incisiones que le permitan llegar a sus entrañas, las explora con sus manos o mediante instrumentos, destruye y reconstruye sus partes enfermas, sustituye órganos vitales que no le ayudan a vivir por los extraídos de cuerpos donantes, y concibe, diseña y hace fabricar artefactos o prótesis, como recambio fragmentos corporales deteriorados o desgastados, como arterias o articulaciones. Otros cirujanos, en la predominante cultura de la modificación del cuerpo, retocan una y otra vez su fachada envejecida ineludiblemente por el paso del tiempo, empeñados en la búsqueda incesante de una belleza icónica y mediática e intemporal, una pretensión que puede conducir, y a veces conduce, al desvarío quirúrgico. En definitiva, el cirujano es incapaz de poner de pie, ex novo, una fábrica biológica como la del cuerpo humano y, por lo tanto, no puede ser su artífice, como lo es el arquitecto de su edificio. A lo sumo, es el restaurador de sus entrañas deterioradas y el modificador de su fachada, de su apariencia.


Electronics ◽  
2020 ◽  
Vol 9 (1) ◽  
pp. 159
Author(s):  
Paulo J. S. Gonçalves ◽  
Bernardo Lourenço ◽  
Samuel Santos ◽  
Rodolphe Barlogis ◽  
Alexandre Misson

The purpose of this work is to develop computational intelligence models based on neural networks (NN), fuzzy models (FM), support vector machines (SVM) and long short-term memory networks (LSTM) to predict human pose and activity from image sequences, based on computer vision approaches to gather the required features. To obtain the human pose semantics (output classes), based on a set of 3D points that describe the human body model (the input variables of the predictive model), prediction models were obtained from the acquired data, for example, video images. In the same way, to predict the semantics of the atomic activities that compose an activity, based again in the human body model extracted at each video frame, prediction models were learned using LSTM networks. In both cases the best learned models were implemented in an application to test the systems. The SVM model obtained 95.97% of correct classification of the six different human poses tackled in this work, during tests in different situations from the training phase. The implemented LSTM learned model achieved an overall accuracy of 88%, during tests in different situations from the training phase. These results demonstrate the validity of both approaches to predict human pose and activity from image sequences. Moreover, the system is capable of obtaining the atomic activities and quantifying the time interval in which each activity takes place.


2017 ◽  
Vol 17 (07) ◽  
pp. 1740039 ◽  
Author(s):  
ZHENGWEI MA ◽  
LELE JING ◽  
FENGCHONG LAN ◽  
JINLUN WANG ◽  
JIQING CHEN

Finite element modeling has played a significant role in the study of human body biomechanical responses and injury mechanisms during vehicle impacts. However, there are very few reports on similar studies conducted in China for the Chinese population. In this study, a high-precision human body finite element model of the Chinese 50th percentile male was developed. The anatomical structures and mechanical characteristics of real human body were replicated as precise as possible. In order to analyze the model’s biofidelity in side-impact injury prediction, a global technical standard, ISO/TR 9790, was used that specifically assesses the lateral impact biofidelity of anthropomorphic test devices (ATDs) and computational models. A series of model simulations, focusing on different body parts, were carried out against the tests outlined in ISO/TR 9790. Then, the biofidelity ratings of the full human body model and different body parts were evaluated using the ISO/TR 9790 rating method. In a 0–10 rating scale, the resulting rating for the full human body model developed is 8.57, which means a good biofidelity. As to different body parts, the biofidelity ratings of the head and shoulder are excellent, while those of the neck, thorax, abdomen and pelvis are good. The resulting ratings indicate that the human body model developed in this study is capable of investigating the side-impact responses of and injuries to occupants’ different body parts. In addition, the rating of the model was compared with those of the other human body finite element models and several side-impact dummy models. This allows us to assess the robustness of our model and to identify necessary improvements.


2019 ◽  
Vol 24 (3) ◽  
pp. 592-599
Author(s):  
Hamid Gheibollahi ◽  
Masoud Masih-Tehrani ◽  
Mohammadmehdi Niroobakhsh

In this study, adding a headrest to the conventional vehicle driver seat is investigated to improve the driver comfort and decrease the driver damages. For this purpose, a conventional biomechanical human body model of wholebody vibrations is provided and modified by adding a head degree of freedom to the body model and a headrest to the seat model. The basic model is in the sitting posture, lumped parameters and has nine DOFs for the human body, on contrary to the proposed model which has ten DOFs. The new human body DOF is the twisting motion of the head and neck. This new DOF is generated because of headrest adding to the driver’s seat. To determine the head discomforts, the Seat to Head (STH) indexes are studied in two directions: horizontal and vertical. The Genetic Algorithm (GA) is used to optimize the STH in different directions. The optimization variables are stiffness and damping parameters of the driver’s seat which are 12 for the basic model and are 16 for a new seat. The integer programming is used for time reduction. The results show that new seat (equipped by headrest) has very better STH in both directions.


Sign in / Sign up

Export Citation Format

Share Document