• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.764-767
• /
• 2009

Motion capture systems allow to measure the precise position of markers on the human body in real time. These captured motion data, the marker position data, have to be fitted by a human skeleton model to represent the motion of the human. Typical human skeleton models approximate the joints using a ball joint model. However, because this model cannot represent the human skeleton precisely, errors between the motion data and the movements of the simplified human skeleton model happen. We propose in this paper a method for measuring a translation component of wrist, and elbow joints on upper limb using optical motion capture system. Then we study the errors between the ball joint model and acquired motion data. In addition, we discuss the problem to estimate motion of human joint using optical motion capture system.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권2호
• /
• pp.1118-1133
• /
• 2017

Computer vision-based human activity recognition (HAR) has become very famous these days due to its applications in various fields such as smart home healthcare for elderly people. A video-based activity recognition system basically has many goals such as to react based on people's behavior that allows the systems to proactively assist them with their tasks. A novel approach is proposed in this work for depth video based human activity recognition using joint-based motion features of depth body shapes and Deep Belief Network (DBN). From depth video, different body parts of human activities are segmented first by means of a trained random forest. The motion features representing the magnitude and direction of each joint in next frame are extracted. Finally, the features are applied for training a DBN to be used for recognition later. The proposed HAR approach showed superior performance over conventional approaches on private and public datasets, indicating a prominent approach for practical applications in smartly controlled environments.

• 정보처리학회논문지B
• /
• 제18B권4호
• /
• pp.193-200
• /
• 2011

본 논문은인간-컴퓨터 인터페이스, 가상현실의 의학 응용, 환자의 원격 모니터링과 같은 실시간 응용 분야에 적합한 인체 운동의 시각적 해석 알고리즘 (visual analyzer algorithm)을 제안한다. 본 알고리즘을 사용할 때의 비용을 줄이기 위해서, 단수의 카메라를 사용하도록 설계한다. 그리고 제안한 알고리즘을 좀 더 편리하게 사용할 수 있도록 하기 위해서 광학적 표시자의 사용을 피한다. 제안하는 알고리즘이 실시간 사용에 편리하도록 하기 위해서, 폐쇄적 형태가 되도록 설계한다. 폐쇄적 형태의 알고리즘을 설계하기 위해서, 인체의 각 관절을 기존의 3차원 관절 모델 대신 어떤 형태의 근사화도 사용하지 않고도 2차원 관절 모델로 공식화하는 아이디어를 제안한다. 그리고 이 폐쇄적 형태의 알고리즘이 높은 정확도를 갖게 하기 위해서, 계산 알고리즘을 최적화 문제로 공식화한다. 이렇게 해서 설계된 알고리즘을 인체의 각 관절에 차례대로 적용한다.

• 센서학회지
• /
• 제26권6호
• /
• pp.391-396
• /
• 2017

Human body motion detection is important in several industry sectors, such as entertainment, healthcare, rehabilitation, and so on. In this paper, we first discuss commercial human motion detection technologies (optical markers, MEMS acceleration sensors, infrared imaging, etc.) and then explain recent advances in the development of flexible and stretchable strain sensors for human motion detection. In particular, flexible and stretchable strain sensors that are fabricated using carbon nanotubes, silver nanowires, graphene, and other materials are reviewed.

• 한국항해항만학회지
• /
• 제38권6호
• /
• pp.645-653
• /
• 2014

A Bridge Navigational Watch Alarm System (hereafter 'BNWAS') is to monitor and detect if an officer of watch(hereafter 'OOW') keeps a sharp lookout on the bridge. The careless lookout of an OOW could lead to marine accidents. For this reason on June 5th, 2009, IMO decided that a ship is equipped with a BNWAS. However, an existing BNWAS gives the OOW a lot of inconvenience and stress in its operation. It requires that the OOW should press reset buttons to confirm their alert watch on the bridge at every three to twelve minute. Many OOWs have complained that at some circumstances they cannot focus on their bridge activities including watch-keeping due to a lots of resetting inputs of BNWAS. Accordingly, IMO has allowed the use of a motion sensor as a resetting device. The motion sensor detects the movements of human body on the bridge and subsequently sends reset signals directly to BNWAS automatically. As a result, OOWs can work uninterrupted. However, some of classification societies and flag authorities have a slightly different stance on the use of motion sensor as a resetting method for BNWAS. The reason is that the motion sensor may trigger false reset signals caused by the motion of objects on the bridge, especially a slight movement such as toss and turn of human body which can extend the period of careless watch. As a basic study to minimize the false reset signals, this paper proposes a simple configuration of BNWAS, which consists of only three motion sensors associated with 'AND' and 'OR' logic gates. Additionally, several considerations are also proposed for the implementation of motion sensors. This study found that the proposed configuration which consists of three motion sensors is better than an existing one by reducing false reset signals caused by a slight movement of human body in one's sleep. The proposed configuration in this paper filters false reset signals and is simple to be implemented on existing vessels. In addition, it can be easily installed just by a basic electrical knowledge.

• 센서학회지
• /
• 제29권5호
• /
• pp.312-322
• /
• 2020

As the use of mobile devices increase, there is public interest in the utilization of the human motion generated mechanical energy. The human motion generated mechanical energies vary depending on the body region, type of motion, etc., and an appropriate device has to be designed to utilize them effectively. In this work, a device based on the principles of triboelectric generation and inertia was assessed in order to utilize the multi-axial mechanical energies generated by human motions. To improve the output performance we confirm the changes in the output that vary with the structural design, the reasons for such changes, and variations in performance based on the parts of the human body. In addition, the level of electrical energy generated based on motion type was measured; a maximum voltage of 30 V and a current of 2 ㎂ were generated. Finally, the proposed device was utilized in LEDs used for lighting, thus demonstrating that multi-axial mechanical energies can be harvested effectively. Based on the results, we expect that the developed device can be utilized as a sensor to detect mechanical energies, to sense changes in motion, or as a generator for auxiliary power supply for mobile devices.

• 한국소음진동공학회논문집
• /
• 제21권10호
• /
• pp.897-904
• /
• 2011

When whole-body is exposed to vertical vibration, asymmetry shape of human body affects the response on the translational(fore-aft, lateral, vertical) and rotational(roll, pitch, yaw) motion. While the translational motion has been studied with various titles, it has been rare to study the rotational motion of human body exposed to vertical excitation because of lack of experimental equipment. This study was performed by using a 6-axis force plate installing strain gage type sensors for the rotational response. Sixteen male subjects were exposed to vertical vibration on rigid seat in order to investigate apparent mass of three translational motion and apparent eccentric mass of three rotational motion. Random signal was generated to make excitation vibration which was on an effective frequency range of 3~40 Hz, and magnitude of 0.224 m/$s^2$ r.m.s. The frequency range and magnitude used was selected for the vibration of passenger vehicle on idling condition. As the result, cross-axis apparent masses of fore-and-aft and lateral direction were not significant showing 20 % and 3 % of vertical apparent mass relatively. And apparent eccentric mass of pitch motion was dominant when compared to that of roll and yaw motion, which is reasoned by asymmetry direction of human body sitting on a seat.

• 한국정밀공학회지
• /
• 제24권11호
• /
• 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.

• 복식
• /
• 제60권10호
• /
• pp.133-145
• /
• 2010

The study used four basic formats classified based on the four principles on costumes discussed in the paper 'Human Beings and Arts Phenomena' by Oskar Schlemmer who studied the relationships between stage space and the human body as an analysis tool with regard to analyses on the abstraction of human body in contemporary dance costume. Abstraction of human body expressed in costume for contemporary dance is as follows: Expansions caused by unclear boundary between spaces and costumes, and the principles of three-dimensional abstract spaces based on a geometric cube change heads, trunks, arms and legs to achieve expansions. Similar mechanical shape is a type of shape made in a succession of functional principles of human body in relationships with spaces. As mechanical mechanism is added to the geometric transformation of a specific part of human body, mechanicalness is contained in it. Motion organisms are geometric simplification of moving traces in a space based on conversion into mechanical organisms based on principles of motion, and as mechanical rotation, consecutive speed caused by refraction and directionality are suggested, mobility is achieved. Immaterial shape is based on change into a metaphysical form, and it is converted into animals, plants or a third life that symbolize body parts. It has metaphysical significance in each body part and extends sensibility. As a result of the study, development into abstract succession and a techno art mode has been confirmed. Combination of geometric cubic figures with the organic human body and configuration of the human body pursued by Oskar Schlemmer's geometric abstraction through the proactive accommodation of mechanical aesthetics has been succeeded and expressed in the contemporary dance costumes.

• 한국정보통신학회논문지
• /
• 제16권6호
• /
• pp.1179-1186
• /
• 2012

본 논문에서는 인체의 조인트와 조인트의 움직임 정보를 이용하여 인간의 행동을 인식하는 알고리즘을 제안한다. 제안방법은 입력되는 비디오에서 객체를 추출하고 인체의 비율정보를 이용하여 조인트를 자동추출하며 각 조인트에 블록매칭 기법을 적용하여 조인트의 움직임 정보를 얻는다. 제안방법은 움직임이 있는 조인트, 조인트의 움직임의 방향벡터와 조인트의 x와 y좌표의 증가(+)와 감소(-)를 부호로 나타낸 것을 행동 인식을 위한 기본 파라메터로 사용한다. 제안된 방법은 웹카메라에서 입력되는 영상에서 8가지 행동에 대해 실험하였으며 인간의 행동 인식률에 있어 좋은 결과를 보였다.