• 방송공학회논문지
• /
• 제7권2호
• /
• pp.181-191
• /
• 2002

능동 감시 카메라에서 얻어진 연속 영상에는 카메라의 움직임에 의해 발생하는 전역 움직임과 이동 물체의 국부 움직임이 동시에 존재한다. 따라서 이동 물체의 자동 추적을 위한 영상 기반의 실시간 감시 시스템의 구현을 위해 이동 물체의 국부 움직임만을 검출하고 추적할 수 있는 효과적인 알고리즘이 요구된다. 이 논문에서는 연속 영상의 차영상을 이용하는 빠르고 효율적인 움직임 검출 및 추적 알고리즘을 제안한다. 이 알고리즘은 우선 물체의 속도를 고려하여 이전 영상을 선택하고. 현재 영상과 선택된 이전 영상에 존재하는 전역 움직임을 빠르고 정확하게 추정하기 위해 신뢰성 있는 소수의 정합 블록만을 선택하여 사용한다. 마지막으로 현재 영상과 전역 움직임이 보상된 이전 영상의 차영상을 얻고, 현재 영상과 차영상의 상관 관계를 이용하여 차영상에 존재하는 강한 잡음을 효과적으로 제거하여 이동 물체 영역을 추출한다. 팬틸트 유닛과 AMD 800MHz 프로세서가 내장된 PC로 구성된 능동 카메라 시스템에 제안한 알고리즘을 적용하였다. 이 시스템은 320$\times$240 크기의 영상을 처리하며 수평 수직 방향의 $\pm$20 탐색 영역에서 전역 움직임을 추정할 때 약 50 frames/sec 의 속도로 움직임 검출이 가능하므로 빠른 이동 물체의 실시간 추적에 적합하다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2008년도 학술대회 논문집 정보 및 제어부문
• /
• pp.333-334
• /
• 2008

A real-time face tracking is a broad topic, covering a large spectrum of technologies and applications. Briefly face tracking is a kind of tracing technique which follows human face in any directions. It needs some algorithms such as human face detection and motion controller to track face. Moreover, both processing time and calculation time are the most important factors that influence to drive tracking system. In this paper, two algorithms are used to find human face: earn-shift algorithm and face detection algorithm using OpenCV. Fuzzy controller is utilized to move pan-tilt camera system which can move four directions along to x-y axis.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2010년도 하계학술대회
• /
• pp.42-45
• /
• 2010

This paper proposes an intelligent video surveillance system for human object tracking. The proposed system integrates the object extraction, human object recognition, face detection, and camera control. First, the object in the video signals is extracted using the background subtraction. Then, the object region is examined whether it is human or not. For this recognition, the region-based shape descriptor, angular radial transform (ART) in MPEG-7, is used to learn and train the shapes of human bodies. When it is decided that the object is human or something to be investigated, the face region is detected. Finally, the face or object region is tracked in the video, and the pan/tilt/zoom (PTZ) controllable camera tracks the moving object with the motion information of the object. This paper performs the simulation with the real CCTV cameras and their communication protocol. According to the experiments, the proposed system is able to track the moving object(human) automatically not only in the image domain but also in the real 3-D space. The proposed system reduces the human supervisors and improves the surveillance efficiency with the computer vision techniques.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2007년도 추계학술대회 논문집 전기기기 및 에너지변환시스템부문
• /
• pp.65-67
• /
• 2007

In this paper describes the design and characteristic analysis of a novel 2-DOF(Degree of Freedom) motor. For multi DOF actuating, several numbers of motors have been used. But the using of normal motors they connected each other in single joint, have necessary to a several type of complex power transmission devices. The 2-DOF motor can drive pan, tilt motion in only one unit and it is not necessary to use additional gears and links parts. Therefore by the using of 2-DOF spherical motor ran eliminate; combined effects of inertia, backlash, non-linear friction, and elastic deformation of gears. The validity of the analysis is confirmed by 3D finite element method.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1996년도 한국자동제어학술회의논문집(국내학술편); 포항공과대학교, 포항; 24-26 Oct. 1996
• /
• pp.511-515
• /
• 1996

A remote controlled mobile robot system has been developed and tested to monitor the radiation area in the nuclear power plant. The mobile robot system operates according to car-driving-like commands and is capable of radiation measurement and visual inspection in unmanned situations under radiation. The robot system is equipped with a radiation sensor and two cameras with appropriate illumination set-ups. The camera with auto-focus function and 8-times zoom lens is mounted on the pan/tilt rotational base and the other is mounted on the front panel of the robot system. All commands regarding the motion of the mobile robot and various sensors are given through the monitoring system which is designed to provide an integrated man-machine interface.

• 로봇학회논문지
• /
• 제13권1호
• /
• pp.45-54
• /
• 2018

This paper presents a vision-based fall detection system to automatically monitor and detect people's fall accidents, particularly those of elderly people or patients. For video analysis, the system should be able to extract both spatial and temporal features so that the model captures appearance and motion information simultaneously. Our approach is based on 3-dimensional convolutional neural networks, which can learn spatiotemporal features. In addition, we adopts a thermal camera in order to handle several issues regarding usability, day and night surveillance and privacy concerns. We design a pan-tilt camera with two actuators to extend the range of view. Performance is evaluated on our thermal dataset: TCL Fall Detection Dataset. The proposed model achieves 90.2% average clip accuracy which is better than other approaches.

• International Journal of Control, Automation, and Systems
• /
• 제1권4호
• /
• pp.495-502
• /
• 2003

This paper focuses on the implementation of an efficient tracking method of a moving object using optimal representative blocks by way of a pan-tilt camera. The key idea is derived from the fact that when the image size of a moving object is shrunk in an image frame according to the distance between the mobile robot camera and the object in motion, the tracking performance of a moving object can be improved by reducing the size of representative blocks according to the object image size. Motion estimations using Edge Detection (ED) and Block-Matching Algorithm (BMA) are regularly employed to track objects by vision sensors. However, these methods often neglect the real-time vision data since these schemes suffer from heavy computational load. In this paper, a representative block able to significantly reduce the amount of data to be computed, is defined and optimized by changing the size of representative blocks according to the size of the object in the image frame in order to improve tracking performance. The proposed algorithm is verified experimentally by using a two degree-of- freedom active camera mounted on a mobile robot.

• 전자공학회논문지SC
• /
• 제49권4호
• /
• pp.55-60
• /
• 2012

해상환경에서 감시장비의 운용시 원치 않는 외란 운동으로 장비의 안정화 성능이 저하된다. 본 논문에서는 선상 2축 감시장비의 정밀한 목표물 지향를 위해 자세정보의 좌표변환을 통해 움직임을 보상해주는 기구적 안정화를 적용하였다. 적용 결과, MEMS 센서의 떨어지는 정밀도와 기구적인 제약에 의해 오차를 더 줄일 없어 보완적인 기능으로 영상 안정화를 도입하였다. 또한 본 이중 안정화 방식의 실시간 실행을 위해 6축 운동 시뮬레이터를 포함한 테스트 베드를 구축하였으며, 하드웨어 포함 시뮬레이션 수행을 통해 본 방식의 유용성을 검증하였다.

• 한국지능시스템학회논문지
• /
• 제21권6호
• /
• pp.743-748
• /
• 2011

본 논문에서는 지능형 영상 감시 시스템을 위한 다수의 네트워크 카메라를 이용한 협동 추적 알고리즘을 제안한다. 이를 위하여 각의 카메라는 모션 템플릿 기법을 통하여 영상내의 움직임 물체를 추출하고, 추출된 움직임 물체의 이동방향을 추정한다. 움직임 물체가 추출되면 칼만 필터를 이용하여 움직임 물체의 정확한 좌표를 추정한다. 움직임 물체의 이동방향과 카메라의 상태를 이용하여 가장 효율적인 협동추적 카메라를 선정하고, 각 카메라의 공간정보를 이용하여 PTZ 변수를 설정하고 협동요청을 한다. 협동요청을 받은 카메라는 설정된 PTZ 변수를 이용하여 움직임 물체를 협동 추적하고 확대영상을 획득한다. 실험을 통하여 제안된 협동추적 알고리즘의 성능분석 및 그 응용 가능성을 확인한다.

• 한국해양공학회:학술대회논문집
• /
• 한국해양공학회 2004년도 학술대회지
• /
• pp.198-203
• /
• 2004

This paper describes a real-time control architecture for DUSAUV (Dual Use Semi-Autonomous Underwater Vehicle), which has been developed at Korea Research Institute of Ships & Ocean Engineering (KRISO), KORDI, for being a test-bed oj development of technologies for underwater navigation and manipulator operation. DUSAUV has three built-in computers, seven thrusters for 6 degree of freedom motion control, one 4-function electric manipulator, one pan/tilt unit for camera, one ballasting motor, built-in power source, and various sensors such as IMU, DVL, sonar, and so on. A supervisor control system for GUI and manipulator operation is mounted on the surface vessel and communicates with vehicle through a fiber optic link. Furthermore, QNX, one of real-time operating system, is ported on the built-in control and navigation computers of vehicle for real-time control purpose, while MicroSoft OS product is ported on the supervisor system for GUI programming convenience. A hierarchical control architecture which consist of three layers (application layer, real-time layer, and physical layer) has been developed for efficient control system of above complex underwater robotic system. The experimental results with implementation of the layered control architecture for various motion control of DUSAUV in a basin of KRISO is also provided.