• 한국멀티미디어학회논문지
• /
• 제21권4호
• /
• pp.478-484
• /
• 2018

The choice of the motion features influences the result of the human action recognition method directly. Many factors often influence the single feature differently, such as appearance of the human body, environment and video camera. So the accuracy of action recognition is restricted. On the bases of studying the representation and recognition of human actions, and giving fully consideration to the advantages and disadvantages of different features, the Dense Trajectories(DT) algorithm is a very classic algorithm in the field of behavior recognition feature extraction, but there are some defects in the use of optical flow images. In this paper, we will use the improved Dense Trajectories(iDT) algorithm to optimize and extract the optical flow features in the movement of human action, then we will combined with Support Vector Machine methods to identify human behavior, and use the image in the KTH database for training and testing.

• ETRI Journal
• /
• 제40권4호
• /
• pp.511-521
• /
• 2018

The ability to realize human-motion imitation using robots is closely related to developments in the field of artificial intelligence. However, it is not easy to imitate human motions entirely owing to the physical differences between the human body and robots. In this paper, we propose a work chain-based inverse kinematics to enable a robot to imitate the human motion of upper limbs in real time. Two work chains are built on each arm to ensure that there is motion similarity, such as the end effector trajectory and the joint-angle configuration. In addition, a two-phase filter is used to remove the interference and noise, together with a self-collision avoidance scheme to maintain the stability of the robot during the imitation. Experimental results verify the effectiveness of our solution on the humanoid robot Nao-H25 in terms of accuracy and real-time performance.

• International Journal of Internet, Broadcasting and Communication
• /
• 제12권4호
• /
• pp.83-92
• /
• 2020

A recent study to determine the fall is focused on analyzing fall motions using a recurrent neural network (RNN), and uses a deep learning approach to get good results for detecting human poses in 2D from a mono color image. In this paper, we investigated the improved detection method to estimate the position of the head and shoulder key points and the acceleration of position change using the skeletal key points information extracted using PoseNet from the image obtained from the 2D RGB low-cost camera, and to increase the accuracy of the fall judgment. In particular, we propose a fall detection method based on the characteristics of post-fall posture in the fall motion analysis method and on the velocity of human body skeleton key points change as well as the ratio change of body bounding box's width and height. The public data set was used to extract human skeletal features and to train deep learning, GRU, and as a result of an experiment to find a feature extraction method that can achieve high classification accuracy, the proposed method showed a 99.8% success rate in detecting falls more effectively than the conventional primitive skeletal data use method.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2007년도 제38회 하계학술대회
• /
• pp.1777-1778
• /
• 2007

In this paper, We design and implement a humanoid robot, With Educational purpose, which can collaborate and communicate with human. We present an affective human-robot communication system for a humanoid robot, D2, which we designed to communicate with a human through dialogue. D2 communicates with humans by understanding and expressing emotion using facial expressions, voice, gestures and posture. Interaction between a human and a robot is made possible through our affective communication framework. The framework enables a robot to catch the emotional status of the user and to respond appropriately. As a result, the robot can engage in a natural dialogue with a human. According to the aim to be interacted with a human for voice, gestures and posture, the developed Educational humanoid robot consists of upper body, two arms, wheeled mobile platform and control hardware including vision and speech capability and various control boards such as motion control boards, signal processing board proceeding several types of sensors. Using the Educational humanoid robot D2, we have presented the successful demonstrations which consist of manipulation task with two arms, tracking objects using the vision system, and communication with human by the emotional interface, the synthesized speeches, and the recognition of speech commands.

• 한국의류학회지
• /
• 제42권2호
• /
• pp.211-223
• /
• 2018

In global apparel product development, flat is one of the most important key factor for technical design communication. Proportionally correct flats based on correct scaled human body figures are imperative to be successful in the fashion business. In this study the researchers were to develop body templates for flats for Korean women body types using data from 'Size Korea 2004 (5th)', which is a Korean government apparel sizing project to analyze women's body measurements (age range 7-49). We measured 13 height measurements, 6 width measurements, 8 circumference measurements, 6 length measurements, 3 angle measurements and 5 body measurements. A body figure (i.e., schema) for each group was created by Pattern Design Software (PAD) System 4.1. Muscle was added to the schema created by Adobe Illustrator to ensure a better visualization and convenience for industry uses for flats. Developed body figure template of representative type had the largest difference in height level compared to exiting figures. It had a bigger head, lower crotch level, and longer crotch depth and hip length than existing figures.

• Journal of information and communication convergence engineering
• /
• 제12권2호
• /
• pp.104-108
• /
• 2014

The field of body sensor networks has attracted interest of many researchers due to its potential to revolutionize medicine. These sensors are usually implanted inside the human body and communicate among themselves. In the process of receiving, processing, or transmitting data, these devices produce heat. This heat damages the tissues surrounding the devices in the case of prolonged exposure. In this paper, to reduce this damages, we have improved and evaluated two protocols-the least temperature routing protocol and adaptive least temperature routing protocol-by implementing clustering as well as a leadership rotation algorithm. We used Castalia to simulate a basic body area network cluster composed of 6 nodes. A throughput application was used to simulate all the nodes sending data to one sink node. Simulations results shows that improved communication protocol with leadership rotation algorithm significantly reduce the energy consumption as compared to a scheme without leadership rotation algorithm.

• 복식
• /
• 제31권
• /
• pp.5-16
• /
• 1997

This paper studies in terms of nonverbal communication the roles of Gut-clothinbgs used in Jin-Do Sit-gim Gut are classified as follows: 1) The message communicated through the ordinary clothings of a shaman is that he or she is waiting to serve as a presider of a Gut ceremony actiong as a mediator between the spirtual and the human world. 2) The shaman clothings representing many kinds of spirits are visualized figures which are closely related to the common wishes of most people in society e. g. physical and material well-being longevity fertility. 3) The clothings serve as a body figure in the Gut are classified into 5 groups. (1) Laid-on clothings give the message that the body is standing still. (2) Wrapped clothings serve as an incarnated body of the dead. (3) Spread clothings represent a lying body. (4) Oscillated clothings are the symbols of a spirit which moves from this world to another. (5) Burned clothings mean that the spirit has attained a complete seperation from this world.

• 한국인터넷방송통신학회논문지
• /
• 제15권2호
• /
• pp.263-267
• /
• 2015

현 지뢰탐지기는 탐지를 실시한 곳과 실시하지 않은 지역을 구분할 수 없고, 많은 인력과 시간이 낭비되는 문제점이 있으며, 사용자가 센서 헤드부를 일정한 속도로 움직이지 않거나, 너무 빨리 움직이는 경우 지뢰를 정확히 탐지하기가 곤란하다. 따라서 단방향 초음파 센싱신호를 통한 지뢰탐지 오류 문제점을 개선하고자, Human Body 안테나부, 메인마이크로프로세서 유닛부, 스마트 안경부, 바디장착형 LCD모니터부, 무선데이터 송수신부, 벨트형 전원공급부, 블랙박스형 카메라부, 보안통신 헤드셋으로 구성하여 전투복을 착용한 상태에서 신체의 머리, 몸통, 팔, 허리, 다리에 탈 부착식으로 장착, Superhigh Frequency RF Beam을 통해 지뢰를 탐지하는 Human Body 안테나부를 적용, 지뢰의 금속 비금속이 아닌, 지상(하)에 매설된 기폭제를 전방위($360^{\circ}$)로 탐지할 수 있고, 지뢰의 거리 위치 형태 재질을 2D 또는 3D 영상으로 스마트 안경 및 신체장착형 LCD모니터부에 실시간 표출시킬 수 있으며, 이로 인해 전투병이 지상(하)에 있는 지뢰를 회피, 신속하게 기동할 수 있다. 아울러 휴대용 배터리와 벨트형 전원공급부의 Twin-Self Supplements of electricity을 통해 별도의 충전 없이 3~7일간 전투를 수행할 수 있으며, 원격지의 전투상황을 원격지 전투지휘서버에서 실시간 모니터링할 수 있고, 전투병 1:1로 전투정보를 공유할 수 있어, 전투현장에 있는 것과 같은 생동감 있게 전투상황을 원격지휘할 수 있는 스마트전투시스템을 구축할 수 있는 Smart Wearable Minefield Detection System을 제안하고자 한다.

• 전자공학회논문지SC
• /
• 제44권5호
• /
• pp.38-44
• /
• 2007

본 논문은 초음파 거리를 이용하여 캡슐 내시경의 3차원 위치 측정 방법과 자세각을 측정하는 방법을 제시하였다. 인체의 불규칙한 초음파 전달 특성들에 의해 발생되는 측정 에러를 줄이기 위해서 제안된 트랙킹 시스템은 초음파센서들을 사용하였다. 캡슐 내시경과 바인더 시스템까지의 거리 정보를 이용하여 캡슐 내시경의 3-D 위치 정보와 자세 정보를 추적하는 방법을 제안한다. 제안된 방법은 Matlab으로 랜덤 오차를 포함하여 시뮬레이션 하였다. 3-D 위치 측정 결과는 평균오차 0.8mm, 자세 측정 결과는 평균 오차 $0.2^{\circ}$의 결과를 얻었다. 캡슐 내시경의 위치 정보와 자세 정보를 이용하여 의사들이 정확한 발병 위치를 진단 할 수 있도록 하였다.

• 대한산업공학회지
• /
• 제38권2호
• /
• pp.133-143
• /
• 2012

The study on social robots has been actively conducted in the robot research community. In the area of robot design, however, there are few studies regarding robot motions that are one of the methods for interaction between humans and robots. This is a preliminary study to find preferred human motions that can be applied to social robots. We conducted a two-phased empirical study about preferred human motions. In the first phase, four representative human motions, such as 'greeting', 'I don't know', 'positive answer', and 'giving', were captured through 28 body makers and video recording. 10 young and 6 elderly Singaporeans participated in the motion capture process. In the second phase, the communication efficiency, emotion, and satisfaction of the human motions recorded in the first phase were measured by a questionnaire and 31 young Koreans, 35 young Singaporeans participated to investigate cultural differences. We drew the conclusion that motions used in the same culture are efficient in communication and also give friendliness and satisfaction. In addition, regardless of user's culture, young people's motions and female motions were preferred in terms of communication efficiency, emotional aspect, satisfaction.