• 한국통신학회논문지
• /
• 제32권4C호
• /
• pp.401-410
• /
• 2007

본 논문에서는 비젼 카메라와 다중 객체 추적 방법을 이용한 실시간 수질 감시 시스템을 제안하였다. 제안된 시스템은 기존의 센서 방식의 감시 시스템과 달리 비젼 카메라를 이용해 객체를 개별적으로 분석한다. 비젼 카메라를 이용한 시스템은 영상에서 개별 객체를 분리해 내는 방법과, 연속하는 두 프레임간의 상관관계에 의해서 다수의 객체를 추적하는 방법으로 구성된다. 실시간 처리를 위해 비모수 예측을 사용하여 배경 영상을 생성하고 이를 이용해 객체를 추출한다. 비모수 예측을 이용하면 연산량을 줄이는 동시에 비교적 정확하게 객체를 추출 할 수 있다. 다중 객체 추적 방법은 개별 객체가 움직이는 방향, 속도 및 가속도를 이용해 다음 움직임을 예측하고 이를 기반으로 추적을 수행하였다. 또한 추적 성공률을 향상시키기 위해 예외처리 알고리즘을 적용하였다. 다양한 환경에서 실험한 결과 제안한 시스템은 처리 시간이 짧고 정확하게 다중 객체를 추적할 수 있어 실시간 수질 감시 시스템에 사용이 가능함을 확인하였다.

• 인터넷정보학회논문지
• /
• 제15권1호
• /
• pp.63-71
• /
• 2014

인공지능과 웹 데이터베이스와 같은 분야에서는 기존의 관계 데이터 모형보다 더 고급 모델링 기능을 필요로 한다. 이러한 분야에서 객체지향데이터베이스는 객체를 모아 클래스를 제공하고 또한 클래스 사이에서 상위클래스는 하위 클래스에게 물려주는 계층구조를 제공하기 때문에 더 좋은 데이터 모형이 될 수 있다. 본 논문의 목적은 객체지향데이터베이스에서 다중 계승을 위한 동시성 제어 기법을 개발하는 것이다. 본 논문에서 제안하는 MIIL(Multiple Inheritance Implicit Locking) 기법은 기존의 Implicit 로킹(Locking) 기법에 기반을 두었다. MIIL 기법은 기존의Implicit 로킹에서 불필요한 로킹을 제거하였다. 또한 본 논문에서 제안하는 MIIL 기법에서의 Intention 로킹은 기존의 Implicit 로킹기법과 동일하게 작동한다. 본 논문에서 제안한 MIIL 기법은 기존의 Implicit 로킹 기법보다 로킹 오버헤드가 적음을 증명하였다. 또한, 본 논문에서는 단일 계승과 다중 계승 등 계승구조만을 이용함으로써 로킹 오버헤드를 줄이기 위한 추가적인 비용을 필요로 하지 않는다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권4호
• /
• pp.1712-1731
• /
• 2016

In this paper, we propose a novel saliency detection framework via multiple random walks (MRW) which simulate multiple agents on a graph simultaneously. In the MRW system, two agents, which represent the seeds of background and foreground, traverse the graph according to a transition matrix, and interact with each other to achieve a state of equilibrium. The proposed algorithm is divided into three steps. First, an initial segmentation is performed to partition an input image into homogeneous regions (i.e., superpixels) for saliency computation. Based on the regions of image, we construct a graph that the nodes correspond to the superpixels in the image, and the edges between neighboring nodes represent the similarities of the corresponding superpixels. Second, to generate the seeds of background, we first filter out one of the four boundaries that most unlikely belong to the background. The superpixels on each of the three remaining sides of the image will be labeled as the seeds of background. To generate the seeds of foreground, we utilize the center prior that foreground objects tend to appear near the image center. In last step, the seeds of foreground and background are treated as two different agents in multiple random walkers to complete the process of salient object detection. Experimental results on three benchmark databases demonstrate the proposed method performs well when it against the state-of-the-art methods in terms of accuracy and robustness.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.2486-2491
• /
• 2003

This paper presents a method to segment object ID marks on poor quality images under uncontrolled lighting conditions of FA inspection process. The method is based on multiple templates and normalized gray-level correlation (NGC) method. We propose a multiple template method, called as ATM (Active Template Model) which uses combinational relation of multiple templates from model templates to match and segment several characters of the inspection images. Conventional Snakes algorithm provides a good methodology to model the functional of ATM. To increase the computation speed to segment the ID mark regions, we introduce the Dynamic Programming based algorithm. Experimental results using images from real FA environment are presented.

• 한국생산제조학회지
• /
• 제19권5호
• /
• pp.645-652
• /
• 2010

For free motions, vibration suppression of single flexible manipulators has been one of the hottest research topics. However, for cooperative motions of multiple flexible manipulators, a little effort has been devoted for the vibration suppression control. So, the aim of this paper is to develop a hybrid force/position control and vibration suppression control scheme for multiple cooperation flexible manipulators handling a rigid object. In order to clarify the discussion, the motions of dual-arm experimental flexible manipulator are considered. Using the developed model, we control a robotic system with hybrid position/force control scheme. Finally, Experiments are performed, and a comparison of experimental results is given to clarify the validity of our control scheme.

• 한국통신학회논문지
• /
• 제18권8호
• /
• pp.1176-1189
• /
• 1993

본 논문에서는 객체 지향 멀티미디어 데이타베이스 모델 하에서 다중 키워드를 이용한 검색 기법을 제안하였다. 멀티미디어 데이타 검색에서의 부분 매칭 문제점을 가급적 줄이기 위한 다중 키워드 등록 띤 검색알고리즘을 개발하였으며, 이를 위해 적절한 탐색 테이블의 저장 구조를 설계하였다. 또한 미디어 데이타 화일을 B+ 트리로 구성하여 검색 시간이 일정하도록 하였다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2006년 학술대회 논문집 정보 및 제어부문
• /
• pp.434-436
• /
• 2006

In a visual driver-assistance system, separating moving objects from fixed objects are an important problem to maintain multiple hypothesis for the state. Color and edge-based tracker can often be "distracted" causing them to track the wrong object. Many researchers have dealt with this problem by using multiple features, as it is unlikely that all will be distracted at the same time. In this paper, we improve the accuracy and robustness of real-time tracking by combining a color histogram feature with a brightness of Optical Flow-based feature under a Sequential Monte Carlo framework. And it is also excepted from Tracking as time goes on, reducing density by Adaptive Particles Number in case of the fixed object. This new framework makes two main contributions. The one is about the prediction framework which separating moving objects from fixed objects and the other is about measurement framework to get a information from the visual data under a partial occlusion.

• 제어로봇시스템학회논문지
• /
• 제10권10호
• /
• pp.930-939
• /
• 2004

In this paper, both dynamic constraints and kinematic constraints are considered for the analysis of manipulability of robotic systems comprised of multiple cooperating arms. Given bounds on the torques of each Joint actuator for every robot, the purpose of this study is to drive the bounds of task-space acceleration of object carried by the system. Bounds on each joint torque, described as a polytope, is transformed to the task-space acceleration through matrices related with robot dynamics, robot kinematics, object dynamics, grasp conditions, and contact conditions. A series of mathematical manipulations including the procedure calculating minimum infinite-norm solution of linear equation is applied to get the reachable acceleration bounds from given actuator dynamic constrains. Several examples including two robot systems as well as three robot system are shown with the assumptions of complete-constraint contact model(or' very soft contact') and insufficient or proper degree of freedom robot.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.203-206
• /
• 2009

This paper represents an efficient algorithm to segment objects from the background using multiple images of distinct luminous intensities. The proposed algorithm obtains images with different luminous intensities using a camera flash. From the multiple intensities for a pixel, a saturated luminous intensity is estimated together with the slope of intensity rate. Then, we measure the sensitivities of pixels from their slopes. The sensitivities show different patterns according to the distances from the light source. Therefore, the proposed algorithm segments near objects using the sensitivity information by minimizing an energy function. Experimental results on various objects show that the proposed algorithm provides accurate results without any user interaction.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제2권3호
• /
• pp.215-220
• /
• 2002

This paper proposes a method to apply the Backpropagation(BP) algorithm of MVL(Multi-Valued Logic) Neural Network to pattern recognition. It extracts the property of an object density about an original pattern necessary for pattern processing and makes the property of the object density mapped to MVL. In addition, because it team the pattern by using multiple valued logic, it can reduce time f3r pattern and space fer memory to a minimum. There is, however, a demerit that existed MVL cannot adapt the change of circumstance. Through changing input into MVL function, not direct input of an existed Multiple pattern, and making it each variable loam by neural network after calculating each variable into liter function. Error has been reduced and convergence speed has become fast.