• 대한원격탐사학회지
• /
• 제30권3호
• /
• pp.383-397
• /
• 2014

Information technology advances are allowing conventional surveillance systems to be combined with mobile communication technologies, creating ubiquitous monitoring systems. This paper proposes monitoring system that uses smart camera technology. We discuss the dependence of interior orientation parameters on calibration target sheets and compare the accuracy of a three-dimensional monitoring system with camera location calculated by space resectioning using a Digital Surface Model (DSM) generated from stereo images. A monitoring housing is designed to protect a camera from various weather conditions and to provide the camera for power generated from solar panel. A smart camera is installed in the monitoring housing. The smart camera is operated and controlled through an Android application. At last the accuracy of a three-dimensional monitoring system is evaluated using a DSM. The proposed system was then tested against a DSM created from ground control points determined by Global Positioning Systems (GPSs) and light detection and ranging data. The standard deviation of the differences between DSMs are less than 0.12 m. Therefore the monitoring system is appropriate for extracting the information of objects' position and deformation as well as monitoring them. Through incorporation of components, such as camera housing, a solar power supply, the smart camera the system can be used as a ubiquitous monitoring system.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1993년도 한국자동제어학술회의논문집(국내학술편); Seoul National University, Seoul; 20-22 Oct. 1993
• /
• pp.811-814
• /
• 1993

The development of fuzzy pan/tilt controller for remote handling in hostile environment is presented in this paper. In remote handling, control of the camera system is somewhat tedious and time consuming. Operators should do the two tasks of manipulating teleoperator and camera pan/tilt at the same time. By automating pan/tilt control, we expect operators could concentrate only on remote operation. When operators control camera pan/tilt they use simple linguistic rules such as "If the position of end effector on TV monitor is at the edge of the screen, control pan/tilt to display the end effector near the center of the screen." Such a rule is similar to fuzzy logic, so we used fuzzy logic controller to control camera pan/tilt. pan/tilt.

• International journal of advanced smart convergence
• /
• 제7권3호
• /
• pp.8-14
• /
• 2018

In the field of surveillance cameras, it is possible to increase the people detection accuracy by using depth information indicating the distance between the camera and the object. In general, depth information is obtained by calculating the parallax information of the stereo camera. However, this method is difficult to operate in real time in the embedded environment due to the large amount of computation. Jetson TX2, released by NVIDIA in March 2017, is a high-performance embedded board with a GPU that enables parallel processing using the GPU. In this paper, a stereo camera is installed in Jetson TX2 to acquire depth information in real time, and we proposed a people counting method using acquired depth information. Experimental results show that the proposed method had a counting accuracy of 98.6% and operating in real time.

• Journal of information and communication convergence engineering
• /
• 제2권1호
• /
• pp.52-57
• /
• 2004

In this paper, we propose a panorama-based object tracking scheme for wide-view surveillance systems that can detect and track moving objects with a pan-tilt camera. A dynamic mosaic of the background is progressively integrated in a single image using the camera motion information. For the camera motion estimation, we calculate affine motion parameters for each frame sequentially with respect to its previous frame. The camera motion is robustly estimated on the background by discriminating between background and foreground regions. The modified block-based motion estimation is used to separate the background region. Each moving object is segmented by image subtraction from the mosaic background. The proposed tracking system has demonstrated good performance for several test video sequences.

• 한국인터넷방송통신학회논문지
• /
• 제9권5호
• /
• pp.101-107
• /
• 2009

본 논문은 감시카메라 영상으로부터 응급상황을 탐지하는 방법과 응급상황의 정밀 탐색 및 서비스를 위한 이동로봇 추적 시스템 개발에 대하여 기술한다. 건물 곳곳에 설치된 카메라로부터 얻어지는 일련의 영상들을 분석하여 처리함으로써 사람의 행동을 인식할 수 있으며, 이 중 응급상황이 탐지된 경우 준비된 이동로봇을 이용해 응급상황 발생지점의 정밀 탐색이 가능하다. 감시 카메라 영상을 통하여 사람의 행동들을 인식하기 위해서는 인간의 모습이라고 가정되는 영역들을 추적하고 관리해야 한다. 한 영상에서 가우시안 혼합 모델(MOG)을 이용하여 배경과 분리된 관심 영역들을 추출하고, 각 영역들을 외관 모델을 이용하여 지속적으로 추적한다. 그리고 각 영역의 실루엣 정보를 이용한 움직임 누적 영상(MHI)을 생성하여 행동을 모델링하고 신경망을 이용하여 응급 상황을 최종 인식한다. 또한 응급상황에 처한 사람과 이동로봇의 위치정보를 계산해 이동로봇이 사람에게 접근하는 기술을 구현한다.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제2권11호
• /
• pp.795-800
• /
• 2013

한우 발정기의 조기 탐지는 축산 농가의 경제성을 향상시키는 매우 중요한 연구 과제 중 하나이다. 이를 위한 다양한 방법들이 제안되었으나, 현재까지도 시스템의 경제성 문제를 포함한 조기 발정 탐지 및 탐지 정확도 등에 여전히 취약한 점이 있는 것이 사실이다. 본 논문에서는 감시카메라 환경에서 축사내 승가 행동을 포함하는 한우의 특이 행동들을 탐지하는 다중 객체의 특이 행동 탐지 프로토타입 시스템을 제안한다. 다중 객체의 특이 행동 탐지란 감시카메라로부터 유입되는 영상에서 다중 객체가 위험에 처한 상황 혹은 비정상적인 행동들을 신속하고 정확하게 탐지하는 분야를 말한다. 제안된 시스템은 한우 축사에 고정 설치된 카메라의 입력 동영상으로 부터 움직임 벡터 정보를 이용하여 영상내의 움직임 정보를 추출 표현하였으며, 특이 행동의 판별 문제를 실용적 차원의 단일 클래스 분류 문제로 재해석하여 단일 클래스 SVM의 대표적 모델인 SVDD를 탐지기로 설계하였다. 실제로 진주에 위치한 한 축사에서 취득한 한우 암소의 영상 정보를 이용하여 본 논문에서 제안한 시스템의 성능을 실험적으로 검증한다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2008년도 하계종합학술대회
• /
• pp.789-790
• /
• 2008

In this paper, we introduce the multi-target-based auto surveillance algorithm. Multi-target-based surveillance system detects intrusion objects in the specified areas. The proposed algorithm can divide into two parts: i) background generation, ii) object extraction. In this paper, one of the optical flow equation methods for estimation of gradient method used to generate the background [2]. In addition, the objects and back- ground video images that are continually entering the differential extraction.

• 한국컴퓨터정보학회논문지
• /
• 제11권6호
• /
• pp.151-156
• /
• 2006

본 논문에서는 이동 카메라를 이용하여 얻은 영상에서 이동 물체 자동 검출 알고리즘을 위한 배경 에지 생성을 제시한다. 배경 영상은 삼각대 위에 고정시킨 카메라를 수평방향으로 회전하여 얻은 영상을 정렬시켜 재구성하여 만든다. 입력영상과 배경영상간의 에지 매칭 방법과 함께 강건한 파노라믹 배경 에지 생성을 위한 효율적인 방법을 제시한다. 제안한 알고리즘은 실제 영상 열에 적용하였다. 제안된 방법은 비디오 감시는 물론 침입자 검출과 같은 여러 감시 시스템에 성공적으로 이용될 수 있다.

• Journal of Information Processing Systems
• /
• 제15권4호
• /
• pp.785-796
• /
• 2019

Due to the view point, illumination, personal gait and other background situation, person re-identification across cameras has been a challenging task in video surveillance area. In order to address the problem, a novel method called Joint Bayesian across different cameras for person re-identification (JBR) is proposed. Motivated by the superior measurement ability of Joint Bayesian, a set of Joint Bayesian matrices is obtained by learning with different camera pairs. With the global Joint Bayesian matrix, the proposed method combines the characteristics of multi-camera shooting and person re-identification. Then this method can improve the calculation precision of the similarity between two individuals by learning the transition between two cameras. For investigating the proposed method, it is implemented on two compare large-scale re-ID datasets, the Market-1501 and DukeMTMC-reID. The RANK-1 accuracy significantly increases about 3% and 4%, and the maximum a posterior (MAP) improves about 1% and 4%, respectively.

• 한국군사과학기술학회지
• /
• 제19권1호
• /
• pp.66-75
• /
• 2016

Stereoscopic image generated by depth image-based rendering(DIBR) for surveillance robot and camera is appropriate in a low bandwidth network. The image is very important data for the decision-making of a commander and thus its integrity has to be guaranteed. One of the methods used to detect manipulation is to check if the stereoscopic image is taken from the original camera. Sensor pattern noise(SPN) used widely for camera identification cannot be directly applied to a stereoscopic image due to the stereo warping in DIBR. To solve this problem, we find out a shifted object in the stereoscopic image and relocate the object to its orignal location in the center image. Then the similarity between SPNs extracted from the stereoscopic image and the original camera is measured only for the object area. Thus we can determine the source of the camera that was used.