• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2008년도 하계종합학술대회
• /
• pp.925-926
• /
• 2008

This paper presents an object tracking method using motion vectors generated in the MPEG4 encoding process and the snake algorithm for active contours. This paper shows the possibility of realtime object tracking during MPEG4 encoding process in a conventional surveillance system. The experiments is performed on a PC platform to prove the effectiveness of the method.

• 한국멀티미디어학회:학술대회논문집
• /
• 한국멀티미디어학회 2000년도 추계학술발표논문집
• /
• pp.357-360
• /
• 2000

현재 컴퓨터 비젼(computer vision) 기술의 응용은 여러 방면에서 이루어지고 있다. 이중 움직임 검출(motion detection)과 추적(tracking)기술을 이용하여 교통 감시 환경에서 필요로 하는 정보를 얻을 수 있는 연구가 활발하다. 특히 입력되어지는 영상으로부터 차량의 추적을 위한 다양한 방법이 제시되고 있다. 본 논문에서는 컴퓨터 비젼 기술을 이용하여 입력영상으로부터 움직이는 차량의 동작을 분할(segmentation)하고, 칼만 필터(Kalman filter)를 이용한 효율적인 추적과 동시에 배경영상의 도로를 일정구간으로 나누어, 그 구간 내에서의 교통 요소 중 하나인 움직이는 차량의 속도를 측정 할 수 있는 방법들 제안한다.

• 한국정밀공학회지
• /
• 제12권8호
• /
• pp.140-146
• /
• 1995

In case the uncertainty existing in a system is assumed to satisfy the matching condition and to be come-bounded. Y. H. Chen proposed an adaptive robust control algorithm which introduced adaptive sheme for a design parameter into robust deterministic controls. In this paper, the adaptive robust control algorithm is applied to the position tracking control of direct drive robots, and simulation and experimental studies are conducted to evaluate control performance.

• 한국통신학회논문지
• /
• 제22권10호
• /
• pp.2236-2245
• /
• 1997

직접위성방송(DBS)은 정보화사회를 위한 실질적인 서비스 분야로써 각광을 받고 있으며, 특히 해상에 까지 광범위한 방송서비스를 제공할 수 있는 매우 유용한 매체이다. 그러나 해상에서의 DBS 수신장치는 선박의 운항이나 피칭(pitching), 로링(rolling), 요잉(yawing) 등의 동요에 관계없이 위성을 계속 추적하기 위한 복잡한 안테나 제어장치가 필요하다. 이 연구는 소형 선박에서 무궁화위성의 DBS를 수신하기 위한 장치의 개발을 목표로 하고 있으며, 한반도 주위의 해역을 항해하는 소형 선박에서 쉽게 탑재하고 사용할 수 있도록 소형, 경량, 저가격화에 중점을 두었다. 그러므로 한반도 연.근해에서 무궁화위성의 추적조건을 분석하고 이에 적합한 Az/El 2축 마운트를 설계하여 제작하였으며, 스텝트렉(step track) 빙식에 의한 추적과 각속도 센서를 이용한 마운트의 동요보정 기능을 타 장비의 도움없이 스스로 수행할 수 있는 시스템을 연구하였다. 또한 장치를 탑재할 수 있는 선박운동 시뮬레이터를 제작하여 여러가지 형태의 동요를 구현하며, 추적과 동요보정에 따른 수선상태를 측정, 분석하므로써 실험적으로 최적의 알고리즘을 작성하였다.

• 국제학술발표논문집
• /
• The 3th International Conference on Construction Engineering and Project Management
• /
• pp.250-256
• /
• 2009

This paper presents a robotic tower-crane system using encoder and gyroscope sensors as path tracking devices. Tower crane work is often associated with falling accidents and industrial disasters. Such problems often incur a loss of time and money for the contractor. For this reason, many studies have been done on an automatic tower crane. As a part of 5-year 23-million-dollar research project in Korea, we are developing a robotic tower crane which aims to improve the safety level and productivity. We selected a luffing tower crane, which is commonly used in urban construction projects today, as a platform for the robotic tower crane system. This system comprises two modules: the automated path planning module and the path tracking module. The automated path planning system uses the 3D Cartesian coordinates. When the robotic tower crane lifts construction material, the algorithm creates a line, which represents a lifting path, in virtual space. This algorithm seeks and generates the best route to lift construction material while avoiding known obstacles from real construction site. The path tracking system detects the location of a lifted material in terms of the 3D coordinate values using various types of sensors including adopts encoder and gyroscope sensors. We are testing various sensors as a candidate for the path tracking device. This specific study focuses on how to employ encoder and gyroscope sensors in the robotic crane These sensors measure a movement and rotary motion of the robotic tower crane. Finally, the movement of the robotic tower crane is displayed in a virtual space that synthesizes the data from two modules: the automatically planned path and the tracked paths. We are currently field-testing the feasibility of the proposed system using an actual tower crane. In the next step, the robotic tower crane will be applied to actual construction sites with a following analysis of the crane's productivity in order to ascertain its economic efficiency.

• International Journal of Contents
• /
• 제12권2호
• /
• pp.31-36
• /
• 2016

The purpose of this research is to realize interactive art based on user's motions information using real time internet search terms. For this purpose, real-time search terms and related news information were extracted from three domestic and foreign portal sites, and the extracted information was used to generate content for interaction with the user. For interaction between the generated content and the user, a motion-based interactive technology that optimizes the intentions and experiences of the user was developed. A motion-based interactive system can be used to develop an immersive interface that induces user interest.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2015년도 춘계학술대회
• /
• pp.773-774
• /
• 2015

모션캡쳐 기술은 빠른 시간에 움직임을 추적하여 컴퓨터에서 이용할 수 있는 데이터로 기록된다. 모션캡쳐로 얻어진 데이터는 동작을 생성하는 데 있어서 손쉽게 제어할 수 있다. 하지만 키넥트 기반으로 추출된 모션캡쳐 데이터는 불안전한 경우가 많다. 또한 기존의 모션캡쳐 시스템을 활용한 얼굴모션 제작과정은 시간 및 경제적 부담으로 인해 많은 어려움을 갖고 있다. 따라서 본 논문은 키넥트 시스템을 활용하여 얻어진 얼굴 모션캡쳐 데이터에서 부분적 떨림 현상을 일으키는 데이터를 보정하는 방법을 제안한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권7호
• /
• pp.3599-3619
• /
• 2019

In human activity recognition system both static and motion information play crucial role for efficient and competitive results. Most of the existing methods are insufficient to extract video features and unable to investigate the level of contribution of both (Static and Motion) components. Our work highlights this problem and proposes Static-Motion fused features descriptor (SMFD), which intelligently leverages both static and motion features in the form of descriptor. First, static features are learned by two-stream 3D convolutional neural network. Second, trajectories are extracted by tracking key points and only those trajectories have been selected which are located in central region of the original video frame in order to to reduce irrelevant background trajectories as well computational complexity. Then, shape and motion descriptors are obtained along with key points by using SIFT flow. Next, cholesky transformation is introduced to fuse static and motion feature vectors to guarantee the equal contribution of all descriptors. Finally, Long Short-Term Memory (LSTM) network is utilized to discover long-term temporal dependencies and final prediction. To confirm the effectiveness of the proposed approach, extensive experiments have been conducted on three well-known datasets i.e. UCF101, HMDB51 and YouTube. Findings shows that the resulting recognition system is on par with state-of-the-art methods.

• 한국멀티미디어학회논문지
• /
• 제17권6호
• /
• pp.741-750
• /
• 2014

This paper presents a real-time motion restoration system for people who need remedial exercise of musculoskeletal based on Inverse Kinematics. A new approach is suggested to recognize a gesture based on restored human motion which is calculated the 3D positions of intermediate joints using 3D positions of body features estimated from images. For generating the 3D candidate positions of intermediate joints which cannot be extracted from images, we apply an Inverse Kinematics theory to compute the target position of intermediate joints. And we can reduce the number of candidate positions by applying the various physical constraints of body. Finally, we can generate the more accurate final position using the Kalman filter for a motion tracking and the relationship between the previous frame information and the candidate positions. The system provide motion information which are rotation angle and height in real-time, therefore the rehabilitation exercises can be performed based on the information and figured out proper exercise for individual status.

• 한국정밀공학회지
• /
• 제29권10호
• /
• pp.1110-1118
• /
• 2012

In this study, for reducing the residual vibration in high speed motion control stage, an improved 5th order polynomial motion profile was developed. When a stage is moving, the current through the motor coils has the same profile of input motion profile of acceleration, therefore the characteristics of the acceleration input profile directly affect on the performance of the amplifier that includes the current control loop. Commonly low cost amplifier and motor has a narrow current control bandwidth, therefore the proposed algorithm was designed based on this practical constraint. Simulation and experimental results showed that the proposed algorithm clearly has low residual vibration characteristics than conventional 5th order polynomial motion profile on the same drive condition.