• 제어로봇시스템학회논문지
• /
• 제16권3호
• /
• pp.269-276
• /
• 2010

In this paper, we present the detection method of moving objects based on two background models. These background models support to understand multi layered environment belonged in images taken by shaking camera and each model is MBM(Multiple Background Model) and TMBM (Temporal Median Background Model). Because two background models are Pixel-based model, it must have noise by camera movement. Therefore correlation coefficient calculates the similarity between consecutive images and measures camera motion vector which indicates camera movement. For the calculation of correlation coefficient, we choose the selected region and searching area in the current and previous image respectively then we have a displacement vector by the correlation process. Every selected region must have its own displacement vector therefore the global maximum of a histogram of displacement vectors is the camera motion vector between consecutive images. The MBM classifies the intensity distribution of each pixel continuously related by camera motion vector to the multi clusters. However, MBM has weak sensitivity for temporal intensity variation thus we use TMBM to support the weakness of system. In the video-based experiment, we verify the presented algorithm needs around 49(ms) to generate two background models and detect moving objects.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제2권1호
• /
• pp.27-34
• /
• 2013

배경제거는 동영상의 내용을 자동으로 분석하기 위한 매우 중요한 기술의 하나로 움직이는 객체를 검출하고 추적하기 위한 핵심 기술이다. 본 논문에서는 배경 모델과 함께 배경 영상을 제공하는 새로운 샘플링 기반의 배경제거 알고리즘을 제안한다. 제안된 방법에서는 움직임이 빠른 객체와 느린 객체를 동시에 처리하기 위해 다중 구간 샘플링 기법을 이용하여 배경 모델을 생성한다. 이러한 다중 구간 배경 모델들로부터 최선의 배경 모델을 만들기 위해 "신뢰도"를 사용한 것이 본 논문의 특징이다. 배경 제거 분야에서 다양한 모델을 병합하여 하나의 모델을 만들기 위해 신뢰도를 정의하여 사용한 경우는 현재까지 보고되지 않았다. 실험을 통해 제안된 방법이 다양한 속도의 객체가 존재하고 시간에 따른 그림자의 이동과 같은 환경 변화가 있는 응용에서도 안정적인 결과를 나타내는 것을 알 수 있었다.

• 한국게임학회 논문지
• /
• 제3권2호
• /
• pp.30-34
• /
• 2003

Image-based rendering is an approach to generate realistic images in real-time without modeling explicit 3D geometry, Especially, TIP(Tour Into the Picture) is preferred for its simplicity in constructing 3D background scene. However, TP has a limitation that a viewpoint cannot go far from the origin of the TIP for the lack of geometrical information. in this paper, we propose a method to interpolating the TIP images to generate smooth and realistic navigation. We construct multiple TIP models in a wide area of the virtual environment. Then we interpolate foreground objects and background object respectively to generate smooth navigation results.

• 반도체디스플레이기술학회지
• /
• 제19권2호
• /
• pp.31-36
• /
• 2020

Most of the background subtraction algorithms show good performance in static scenes. In the case of dynamic scenes, they frequently cause false alarm to "temporal clutter", a repetitive motion within a certain area. In this paper, we propose a robust technique for the multiple interval pixel sampling (MIS) algorithm to handle highly dynamic scenes. An adaptive threshold scheme is used to suppress false alarms in low-confidence regions. We also utilize multiple background models in the foreground segmentation process to handle repetitive background movements. Experimental results revealed that our approach works well in handling various temporal clutters.

• 제어로봇시스템학회논문지
• /
• 제21권11호
• /
• pp.989-995
• /
• 2015

Due to the recent increase of the importance and demand of security services, the importance of a surveillance monitor system that makes an automatic security system possible is increasing. As the market for surveillance monitor systems is growing, price competitiveness is becoming important. As a result of this trend, surveillance monitor systems based on an embedded system are widely used. In this paper, an object detection algorithm based on an embedded system for a surveillance monitor system is introduced. To apply the object detection algorithm to the embedded system, the most important issue is the efficient use of resources, such as memory and processors. Therefore, designing an appropriate algorithm considering the limit of resources is required. The proposed algorithm uses two background models; therefore, the embedded system is designed to have two independent processors. One processor checks the sub-background models for if there are any changes with high update frequency, and another processor makes the main background model, which is used for object detection. In this way, a background model will be made with images that have no objects to detect and improve the object detection performance. The object detection algorithm utilizes one-dimensional histogram distribution, which makes the detection faster. The proposed object detection algorithm works fast and accurately even in a low-priced embedded system.

• 제어로봇시스템학회논문지
• /
• 제14권8호
• /
• pp.848-855
• /
• 2008

In this paper, we describe correspondence among multiple images taken by multiple cameras. The correspondence among multiple views is an interesting problem which often appears in the application like visual surveillance or gesture recognition system. We use the principal axis and the ground plane homography to estimate foot of human. The principal axis belongs to the subtracted silhouette-based region of human using subtraction of the predetermined multiple background models with current image which includes moving person. For the calculation of the ground plane homography, we use landmarks on the ground plane in 3D space. Thus the ground plane homography means the relation of two common points in different views. In the normal human being, the foot of human has an exactly same position in the 3D space and we represent it to the intersection in this paper. The intersection occurs when the principal axis in an image crosses to the transformed ground plane from other image. However the positions of the intersection are different depend on camera views. Therefore we construct the correspondence that means the relationship between the intersection in current image and the transformed intersection from other image by homography. Those correspondences should confirm within a short distance measuring in the top viewed plane. Thus, we track a person by these corresponding points on the ground plane. Experimental result shows the accuracy of the proposed algorithm has almost 90% of detecting person for tracking based on correspondence of intersections.

• 지구물리와물리탐사
• /
• 제8권3호
• /
• pp.207-217
• /
• 2005

이 연구에서는 배경 전기전도도 구조가 1차원 층서구조가 아닌 경우에도 적분방정식법을 이용하여 비교적 정확히 모델링 할 수 있는 근사적 방법에 대한 유도 과정을 제시하였으며, 이를 기반으로 전자탐사 수치 모델링을 구현하여 그 정확도 및 효율성에 대해 고찰하였다. 이 연구에서 제시된 방법은 통상적인 적분방정식법과 마찬가지로 1차원 층서구조에서의 Green함수를 그대로 이용할 수 있어 계산 측면에서 매우 효율적이며, 대체적으로 적분방정식을 구성하기 위한 행렬의 크기를 줄일 수 있다. 본 연구에서 개발된 근사 적분방정식 알고리듬을 간단한 수치 모델에 대하여 적용한 결과 정확도는 반응을 구하고자 하는 이상체 부근에서는 거의 차이가 없었으며, 또한 계산 시간에 대한 분석을 통해 이 모델링 알고리듬을 이용하여 역산을 수행하고자 할 때 계산 시간을 대폭 감소시킬 수 있음을 확인하였다. 본 연구에서 제안된 방법은 1차원 층서구조가 아닌 이미 알려진 공통된 구조론 갖는 여러 지질 모델에 대한 전자탐사 반응을 매우 효율적으로 구할 수 있을 것으로 판단된다.

• 한국정보통신학회논문지
• /
• 제20권8호
• /
• pp.1537-1545
• /
• 2016

실시간영상에서 객체의 분할 및 추적은 침입자 감시와 로봇의 물체 추적, 증강현실의 객체 추적등 다양한 분야에서 사용되고 있다. 본 논문에서는 초기 입력 영상의 일부를 학습하여 배경모델로 제작한 후, 배경제거 방법을 이용하여 움직이는 객체의 분할을 통해 객체를 검출하였다. 검출된 객체의 영역을 기반으로 HSV 색상히스토그램과 파티클 필터를 이용하여 객체의 움직임을 추적하는 방법을 제안한다. 제안한 분할 방법은 평균 배경모델을 이용한 방법보다 주변환경 변화의 영향을 적게 받으며, 움직이는 객체의 검출 성능이 더욱 우수하였다. 또한 단일 객체 및 다수의 객체가 존재하는 환경에서 추적 객체가 유사한 색상 객체와 겹치는 경우, 추적 객체의 영역 절반 이상이 가려지는 경우에도 지속적으로 추적하는 결과를 얻을 수 있었다. 2개의 비디오 영상을 사용한 실험결과는 평균 중첩율 85.9%, 추적률 96.3%의 성능을 보여준다.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회 1997년도 추계학술대회발표논문집; 홍익대학교, 서울; 1 Nov. 1997
• /
• pp.101-104
• /
• 1997

Providing information on corporate level decision making for multiple decision makers in a consistent way is essential in Decision Support Systems. However, since the decision makers have different background and knowledge, the models used by them are also different in representation models. This makes the decision makers require a lot of efforts for model integration in an integrated decision making. The purpose of this paper is to propose an integration mechanism for synthetic use of multi-abstraction level decision making models. The proposed integration mechanism consists of model interpretation phase, model transformation phase and model integration phase. Specifically, the model transformation phase is divided into model tightening mode which gather information to makes a model transformed into upper level model, and model relaxing mode which makes lower level model.

• 천문학회보
• /
• 제37권2호
• /
• pp.147.1-147.1
• /
• 2012

We present empirical fiducial sequences for horizontal-branch (HB) stars in a set of bright Galactic globular clusters previously observed in SDSS (An et al. 2008). Mean loci of HB stars are derived on color-magnitude diagrams with multiple color indices (u - g, g - r, g - i, and g - z ) in order to identify foreground/background objects as well as cluster RR Lyrae variables. We compare our fiducial sequences to the model predictions from Yonsei-Yale isochrones and test the accuracy of the stellar evolution models.