• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권7호
• /
• pp.3322-3337
• /
• 2018

Sleep mode detection is a significant power management and green computing feature. However, it is difficult for televisions and smart TVs to detect deactivation events because we can use these devices without the assistance of an input device. In this paper, we propose a robust method for smart TVs to detect deactivation events based on a visual combination of face and motion detection. The results of experiments conducted indicate that the proposed method significantly reduces incorrect face detection and human absence by means of motion detection. The results also show that the proposed method is robust and effective for smart TVs to reduce power consumption.

• 대한전자공학회논문지SP
• /
• 제47권2호
• /
• pp.20-32
• /
• 2010

기존 모션 캡쳐의 경우, 고가의 장비나 사용의 복잡도, 동작자의 움직임 제한 등 모션 캡쳐의 어려움이 있었다. 최근 실시간으로 모션 캡쳐가 가능한 컴퓨터 비젼 기반 시스템에 대한 연구가 활발히 진행되고 있다. 본 논문에서는 다시점 영상으로부터 쉽고, 빠르게 추출할 수 있는 피부색과 정확한 3차원 복원을 위한 2차원 영상 좌표 보정을 사용하여 효율적인 다시점 영상 분석 알고리즘을 제안한다. 동작자의 피부색을 검출하고, 카메라 보정 및 에피폴라 기하학 정보를 이용하여 보다 정확한 영상 분석, 그라고 칼만 필터(Kalman filter)를 사용한 추적 등을 통해 보다 안정적인 모션 캡쳐가 가능하게 된다. 실험결과를 통하여, 제안된 방법은 보다 정확한 위치 추정 및 살시간 모션 캡쳐를 위한 알고리즘임을 보여주고 있다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 Ⅳ
• /
• pp.1960-1963
• /
• 2003

For applications such as video surveillance and human computer interface, we propose an efficiently integrated method to detect and track faces. Various visual cues are combined to the algorithm: motion, skin color, global appearance and facial pattern detection. The ICA (Independent Component Analysis)-SVM (Support Vector Machine based pattern detection is performed on the candidate region extracted by motion, color and global appearance information. Simultaneous execution of detection and short-term tracking also increases the rate and accuracy of detection. Experimental results show that our detection rate is 91％ with very few false alarms running at about 4 frames per second for 640 by 480 pixel images on a Pentium IV 1㎓.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2013년도 춘계학술대회
• /
• pp.616-617
• /
• 2013

본 논문에서는 Kinect 센서를 사용하여 인체의 특정 동작들을 감지하여 휴머노이드 로봇을 제어하는 방법을 소개한다. Kinect 센서의 depth 센서의 출력을 처리하여 인체의 각 joint 부분을 나타내는 인체 모형을 완성하였다. 인체 모형의 각 부분의 거리 및 각도를 계산하여 특정 동작을 검출하였으며 로봇에게 제어 명령을 블루투스 무선통신을 사용하여 전송한다.

• International Journal of Contents
• /
• 제16권3호
• /
• pp.1-17
• /
• 2020

Human motion recognition is essential for user-centric services such as surveillance-based security, elderly condition monitoring, exercise tracking, daily calories expend analysis, etc. It is typically based on the movement data analysis such as the acceleration and angular velocity of a target user. The existing motion recognition studies are only intended to measure the basic information (e.g., user's stride, number of steps, speed) or to recognize single motion (e.g., sitting, running, walking). Thus, a new mechanism is required to identify the transition of single motions for assessing a user's consecutive motion more accurately as well as recognizing the user's body and surrounding situations arising from the motion. Thus, in this paper, we collect the human movement data through Android smartphones in real time for five targeting single motions and propose a mechanism to recognize a consecutive motion including transitions among various motions and an occurred situation, with the state transition model to check if a vulnerable (life-threatening) condition, especially for the elderly, has occurred or not. Through implementation and experiments, we demonstrate that the proposed mechanism recognizes a consecutive motion and a user's situation accurately and quickly. As a result of the recognition experiment about mix sequence likened to daily motion, the proposed adoptive weighting method showed 4% (Holding time=15 sec), 88% (30 sec), 6.5% (60 sec) improvements compared to static method.

• 한국멀티미디어학회논문지
• /
• 제21권1호
• /
• pp.51-60
• /
• 2018

We present a real-time interactive particle-art with human motion based on computer vision techniques. We used computer vision techniques to reduce the number of equipments that required for media art appreciations. We analyze pros and cons of various computer vision methods that can adapted to interactive digital media art. In our system, background subtraction is applied to search an audience. The audience image is changed into particles with grid cells. Optical flow is used to detect the motion of the audience and create particle effects. Also we define a virtual button for interaction. This paper introduces a series of computer vision modules to build the interactive digital media art contents which can be easily configurated with a camera sensor.

• 대한전자공학회논문지SP
• /
• 제45권6호
• /
• pp.44-56
• /
• 2008

기존 모션 캡쳐의 경우, 고가의 장비나 사용의 복잡도, 동작자의 움직임 제한 등 모션 캡쳐의 어려움이 있었다. 최근 실시간으로 모션 캡쳐가 가능한 컴퓨터 비젼 기반 시스템에 대한 연구가 활발히 진행되고 있다. 본 논문에서는 다시점 영상으로부터 쉽고, 빠르게 추출할 수 있는 피부색과 정확한 3차원 복원을 위한 2차원 영상 좌표 보정을 사용하여 효율적인 다시점 영상 분석 알고리즘을 제안한다. 동작자와 피부색을 검출하고, 카메라 보정 및 에피폴라 기하학 정보를 이용하여 보다 정확한 영상 분석, 그리고 칼만 필터(Kalman filter)를 사용한 추적 등을 통해 보다 안정적인 모션 캡쳐가 가능하게 된다. 실험결과를 통하여, 제안된 방법은 보다 정확한 위치 추정 및 실시간 모션 캡쳐를 위한 알고리즘임을 보여주고 있다.

• 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
• /
• 제13권3호
• /
• pp.188-194
• /
• 2004

With a remarkable advance in CMOS (complimentary metal-oxide-semiconductor) process technology, a variety of vision sensors with signal processing circuits for complicated functions are actively being developed. Especially, as the principles of signal processing in human retina have been revealed, a series of vision chips imitating human retina have been reported. Human retina is able to detect the edge and motion of an object effectively. The edge detection among the several functions of the retina is accomplished by the cells called photoreceptor, horizontal cell and bipolar cell. We designed a CMOS vision chip by modeling cells of the retina as hardwares involved in edge and motion detection. The designed vision chip was fabricated using $0.6{\mu}m$ CMOS process and the characteristics were measured. Having reliable output characteristics, this chip can be used at the input stage for many applications, like targe tracking system, fingerprint recognition system, human-friendly robot system and etc.

• 정보처리학회논문지B
• /
• 제11B권1호
• /
• pp.53-62
• /
• 2004

인간과 컴퓨터간의 상호작용에 있어서 감정처리는 매우 중요한 부결이다. 특히, 비디오 정보처리에 있어서 사용자의 감정을 처리할 수 있다면 비디오 검색이나 요약본 추출 등 다양한 응용분야에 활용이 가능하다. 비디오 데이터로부터 이러한 감정 처리를 하기 위해서는 감정에 관련된 특징들을 표현하고, 검출하는 것이 필요하다. 쉽게 추출이 가능한 색상이나 모션 등의 저급 특징들로부터 고급 개념인 감정을 검출하는 것은 매우 어려운 일이지만, 감정에 관련된 여러 장면으로부터 LDA(Linear Discriminant Analysis)와 같은 통계적인 분석을 통해 감정에 관련된 특징들을 검출하는 것은 가능하다. 본 논문에서는 색상, 모션 및 셧 길이 정보로부터 감정과의 관련된 특징을 표현하고 검출하는 방법을 제안한다. 제안된 특징을 사용하여 감정 검출에 관련된 실험을 한 결과 바람직한 결과를 얻었다.