• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.678-681
• /
• 2004

In this paper, efficient tracking of a moving object using optimal representative blocks is implemented by a mobile robot with a pan-tilt camera. The key idea comes from the fact that when the image size of moving object is shrunk in an image frame according to the distance between the camera of mobile robot and the moving object, the tracking performance of a moving object can be improved by changing the size of representative blocks according to the object image size. Motion estimation using Edge Detection(ED) and Block-Matching Algorithm(BMA) is often used in the case of moving object tracking by vision sensors. However these methods often miss the real-time vision data since these schemes suffer from the heavy computational load. In this paper, the optimal representative block that can reduce a lot of data to be computed, is defined and optimized by changing the size of representative block according to the size of object in the image frame to improve the tracking performance. The proposed algorithm is verified experimentally by using a two degree-of-freedom active camera mounted on a mobile robot.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.136-141
• /
• 2009

This paper proposed a framework for handover method in continuously tracking a person of interest across cooperative pan-tilt-zoom (PTZ) cameras. The algorithm here is based on a robust non-parametric technique for climbing density gradients to find the peak of probability distributions called the mean shift algorithm. Most tracking algorithms use only one cue (such as color). The color features are not always discriminative enough for target localization because illumination or viewpoints tend to change. Moreover the background may be of a color similar to that of the target. In our proposed system, the continuous person tracking across cooperative PTZ cameras by mean shift tracking that using color and shape histogram to be feature distributions. Color and shape distributions of interested person are used to register the target person across cameras. For the first camera, we select interested person for tracking using skin color, cloth color and boundary of body. To handover tracking process between two cameras, the second camera receives color and shape cues of a target person from the first camera and using linear color calibration to help with handover process. Our experimental results demonstrate color and shape feature in mean shift algorithm is capable for continuously and accurately track the target person across cameras.

• 한국항행학회논문지
• /
• 제17권3호
• /
• pp.354-360
• /
• 2013

모션 및 무인 차량의 깊이 제어를 위해 스테레오 비전 분석을 하였다. 스테레오 비전에서 3차원 좌표의 깊이 정보는 스테레오 이미지 사이의 포인트를 식별한 후 삼각 측량을 통해 얻을 수 있다. 그러나 항상 몇몇 이유 때문에 삼각 측량의 오류가 발생한다. 비전 삼각 측량의 이러한 오류는 카메라의 위치와 방향에 주의하여 배열함으로써 완화 될 수 있다. 본 논문에서는 무인 차량을 위해 카메라의 최적의 위치와 방향을 결정하는 방법을 제시하였다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2001년도 제14회 신호처리 합동 학술대회 논문집
• /
• pp.415-418
• /
• 2001

The automatic construction of large, high-resolution image mosaics is an active area of reasearch in the fields of photogrammetry, computer vision, image processing, and computer graphics. In this study, we describe a automatic mosaicing method that makes a panorama from images by placing camera in a emitted-grid. In the images captured by cameras, there must be a matched area and the area is in the particular area of the image. Initial transformation matrix, there(ore, is calculated from points searched in the partial area. It is possible to find best transformation matrix by Levenberg-Marquardt method. Finally, each images are multiplied by blending function and stitched by the transformation matrix to complete panoramic image.

• 대한치과의사협회지
• /
• 제49권8호
• /
• pp.443-450
• /
• 2011

The leading paradigm of dentistry had been focused on the rehabilitation treatment that identifies active caries, manages them surgically, and restores their original functions. However, changes in the external environment including the current disease prevalence require dentistry to have a paradigm shift. The new paradigm suggests the detection of caries in their earlier stages over the visual diagnosis of cavities, and the reversal of the incipient caries by non-surgical approach. For this to be achieved, a high-technology detection device recognizing changes in the earlier stages which can not he visually observed is needed. Development of early caries detection device has recently become a major issue in preventive dentistry on account of this need, and QLF(Quantitified Light induced Fluorescence) conspicuously stands out among the newly released devices. In this study, the fundamental concept of QLF(Quantitified Light induced Fluorescence) and the possible clinical applications of the earlier intraoral camera model as well as the recently designed digital camera model will be discussed.

• 동력기계공학회지
• /
• 제18권1호
• /
• pp.112-119
• /
• 2014

In this paper, the authors consider a gimbal system in which a camera is installed to reconnoiter the objects or targets. The issue for this considered system is to obtain information with good quality always. To achieve given objective, it is necessary to control the gimbal system with accurate rotation angle and speed. In this paper, the authors design a robust control system based on $H_{\infty}$ control framework. The controller is designed using a plant model obtained by experiment and simulation. And the experiment result with good control performance is presented.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2005년도 가을 학술발표논문집 Vol.32 No.2 (2)
• /
• pp.931-933
• /
• 2005

감시 시스템에서 많이 사용되는 팬틸트줌(Pan-Tilt-Zoom) 카메라로 객체 검출과 추적을 할 때 카메라를 섬세하게 제어하는 것이 중요하다. 본 논문은 팬틸트줌 카메라를 이용하여 얼굴을 검출 및 추적하는 감시 시스템 구성과 카메라 제어 방법을 제안한다. 얼굴 검출을 위해서 P. Viola가 제안한 Haar-like feature를 이용한 빠른 객체 검출방법을 이용하고 얼굴 추적을 위해서 CAMSHIFT와 AAM을 이용하여 얼굴 추적과 얼굴 특징 정보 추출이 가능한 감시 시스템 구현을 하였다.

• 제어로봇시스템학회논문지
• /
• 제11권8호
• /
• pp.678-687
• /
• 2005

This paper describes a relative localization algorithm using odometry data and consecutive local maps. The purpose of this paper is the odometry error correction using the area matching of two consecutive local maps. The local map is built up using a sensor module with dual laser beams and USB camera. The range data form the sensor module is measured using the structured lighting technique (active stereo method). The advantage in using the sensor module is to be able to get a local map at once within the camera view angle. With this advantage, we propose the AVS (Aligned View Sector) matching algorithm for. correction of the pose error (translational and rotational error). In order to evaluate the proposed algorithm, experiments are performed in real environment.

• 한국통신학회논문지
• /
• 제38C권9호
• /
• pp.797-801
• /
• 2013

Visible light communication (VLC) is a rapidly growing area of research and applications, due to the potential and predicted high efficiency of bandwidth. One of the key challenges in VLC technology is the choice of devices which are going to be deployed VLC features. Smartphone rationally uses the most widely deployed visible light sensor i.e. image sensor in camera, which could be used to receive the intensity modulated data. Image sensor based VLC system would be the most deployable scenario but initially the capacity was not much attractive compared with photodetector based VLC system. Here, the spatial multiplexing is proposed in MIMO based VLC system to increase the system capacity by utilizing the property of spatial separation of optical light sources in smartphone's camera module. The active pixels of imaging plane act as the multiple receivers which could be able to use on MIMO spatial multiplexing to enhance the system performance.

• 대한기계학회논문집A
• /
• 제37권4호
• /
• pp.447-459
• /
• 2013

실제 산업현장에서 비젼 시스템을 적용하기에는 로봇 비젼 제어알고리즘의 기구학모델의 정확도, 로봇이 움직이는 동안 카메라 초점거리와 방위에 대한 보정, 3 차원 물리적 좌표에서 2 차원 카메라 좌표로의 매핑에 대한 이해 등 해결해야 할 많은 문제점들이 있다. 본 논문에 제안된 비젼 시스템 모델은 카메라와 로봇 사이의 상대적인 위치가 알려지지 않아도 제어가 가능하고, 카메라 보정 문제를 해결하기 위해 6 개의 카메라 매개변수를 가지는 비젼 시스템 모델을 제시하였으며, 이를 이용하여 로봇 비젼 제어알고리즘 개발에 N-R 방법과 EKF 방법을 적용하였다. 최종적으로 N-R 과 EKF 방법에 의하여 개발된 로봇 비젼 제어 알고리즘의 위치 정밀도와 데이터 처리 시간을 얇은 막대 배치작업을 수행하여 비교하였다.