• Journal of Broadcast Engineering
• /
• v.23 no.5
• /
• pp.598-605
• /
• 2018

Behavior awareness is a technology that recognizes human behavior through data and can be used in applications such as risk behavior through video surveillance systems. Conventional behavior recognition algorithms have been performed using the 2D camera image device or multi-mode sensor or multi-view or 3D equipment. When two-dimensional data was used, the recognition rate was low in the behavior recognition of the three-dimensional space, and other methods were difficult due to the complicated equipment configuration and the expensive additional equipment. In this paper, we propose a method of recognizing human behavior using only CCTV images without additional equipment using only RGB and depth information. First, the skeleton extraction algorithm is applied to extract points of joints and body parts. We apply the equations to transform the vector including the displacement vector and the relational vector, and study the continuous vector data through the RNN model. As a result of applying the learned model to various data sets and confirming the accuracy of the behavior recognition, the performance similar to that of the existing algorithm using the 3D information can be verified only by the 2D information.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.31 no.7 s.262
• /
• pp.764-776
• /
• 2007

On the human-rifle system, the human body is affected by the firing impact. The firing impact will reduce the firing accuracy and change the initial shooting posture. Therefore the study of biomechanical characteristics using human-rifle modeling and numerical investigation is needed. The musculoskeletal model is developed by finite element method using beam and spar elements. In this study structural analysis has been performed in order to investigate the human body impact by firing of 5.56mm small caliber machine gun. The firing experiments with the standing shooting postures were performed to verify analytical results. The result if this study shows analytical displacements of the human-rifle system and experimental displacements of the real firing. As the results, the analytical displacement and stress of human body are presented.

• Journal of the Korean Society for Precision Engineering
• /
• v.21 no.12
• /
• pp.182-191
• /
• 2004

This study is focused on the development of a child human model, which is composed of skin, skeleton, joints and muscle, etc. The dimension of child outer skin is referred to anthropometric data from KRISS (Korea Research Institute of Standards and Science). The positions of joint and mass properties of body segments are calculated from ATB(Articulated Total Body) program, GEBOD. The properties of bones and muscles are obtained by the way of scaling from adult human model. To verify the developed human model, ROM simulation and sled test is conducted. Developed human model can be effectively applied to the evaluation of human injury in crash situation and development of child restraint system. The explicit finite element program $PAM-CRASH^TM$ was used to simulate six-year old child human model.

• Journal of Biomedical Engineering Research
• /
• v.20 no.4
• /
• pp.485-493
• /
• 1999

Human can generate various posture and motion with nearly 350 muscle pairs. From the viewpoint of mechanisms, the human skeleton mechanism represents great kinematic and dynamical complexity. Physical and behavioral fidelity of human motion requires dynamically accurate modeling and controling. This paper describes a mathematical modeling, and dynamic simulation of human body. The human dynamic model is simplified as a rigid body consisting of 18 actuated degrees of freedom for the real time computation. Complex kinematic chain of human body is partitioned as 6 serial kinematic chains that is, left arm, right arm, support leg, free leg, body, and head. Modeling is developed based on Newton-Euler formulation. The validity of proposed dynamic model, which represents mathematically high order differential equation, is verified through the dynamic simulation.

• Journal of the Korean Society for Precision Engineering
• /
• v.24 no.11
• /
• pp.116-125
• /
• 2007

Human muscle skeletal model was developed for biomechanical study. The human model was consists with 19 bone-skeleton and 122 muscles. Muscle number of upper limb, trunk and lower limb part are 28, 60, 34 respectively. Bone was modeled with 3D beam element and muscle was modeled with spar element. For upper limb muscle modelling, rectus abdominis, trapezius, deltoideus, biceps brachii, triceps brachii muscle and other main muscles were considered. Lower limb muscle was modeled with gastrocenemius, gluteus maximus, gluteus medius and related muscles. The biomechanical stress and strain analysis of human was conducted by proposed finite element analysis model under Kumdo head hitting motion. In this study structural analysis has been performed in order to investigate the human body impact by Kumdo head hitting motion. As the results, the analytical displacement, stress and strain of human body are presented.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2002.05a
• /
• pp.34-38
• /
• 2002

A virtual human which can evaluate Kansei such as comfort, pain, etc. when the virtual human uses some product is developed. In this paper, method of the evaluation of Kansei by the virtual human is presented. The body of our virtual human is modeled as an uniform non-linear elastic one with a skeleton. The deformation of the body on the contact with some product is simulated using a FEM analysis, and by using of the simulated results (load distribution, strain, etc.) on the contact surface the Kansei is predicted. As examples of the application, comfort of buttocks on seating and pain of arm on hanging of bag are shown. This virtual human can apply for the design of virtual products and also the simulation of medical care.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.2
• /
• pp.1019-1031
• /
• 2017

In this study, we propose a new method for simulating water responding to human motion. Motion data obtained from motion-capture devices are represented as a jointed skeleton, which interacts with the velocity field in the water simulation. To integrate the motion data into the water simulation space, it is necessary to establish a mapping relationship between two fields with different properties. However, there can be severe numerical instability if the mapping breaks down, with the realism of the human-water interaction being adversely affected. To address this problem, our method extends the joint velocity mapped to each grid point to neighboring nodes. We refine these extended velocities to enable increased robustness in the water solver. Our experimental results demonstrate that water animation can be made to respond to human motions such as walking and jumping.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.4
• /
• pp.586-594
• /
• 2018

In this paper, we propose a livestock theft detection system through moving object classification and tracking method. To do this, first, we extract moving objects using GMM(Gaussian Mixture Model) and RGB background modeling method. Second, it utilizes a morphology technique to remove shadows and noise, and recognizes moving objects through labeling. Third, the recognized moving objects are classified into human and livestock using skeletal features and color similarity judgment. Fourth, for the classified moving objects, CAM (Continuously Adaptive Meanshift) Shift and Kalman Filter are used to perform tracking and overlapping judgment, and risk is judged to generate a notification. Finally, several experiments demonstrate the feasibility and applicability of the proposed method.

• Proceedings of the Korea Contents Association Conference
• /
• 2007.11a
• /
• pp.899-902
• /
• 2007

Maya is known as the best program in the 3D graphic. Currently maya program is used from movie and TV program production. In this paper, we study skeleton setup techniques using support joint. This techniques are useful generation and development of various behavior of human body.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2012.05a
• /
• pp.123-126
• /
• 2012

In general, there are 3 subjects of discussion in education field; namely past, present and future. Related with those facts, there is several information or knowledge that relatively hard to be presented in the real world. In this matter, digital content shows its contribution especially in the education field. Digital content can virtually represent the information or knowledge that seems to be difficult to be visualized in the real world before. In this project, researcher develops a mobile device's application that consist the skeleton's 3D virtual content. This application is expected to solve the above explained problem that usually appears during learning human skeleton in senior high-school's biology class. Besides, the application of digital content will make the learning process become easier because the student will have a visual learning tool. Last, the mobile device that is used in this prototype has offer an important beneficial namely mobility beneficial, so that the user can access the content anytime and anywhere.