• Journal of Digital Convergence
• /
• v.13 no.9
• /
• pp.183-189
• /
• 2015

In this paper, we propose an object tracking method using the color information of the image in surveillance network. This method perform a object detection using of adaptive color model. Object contour detection plays an important role in application such as object recognition. Experimental results demonstrate successful object detection over a wide range of object's variation in color and scale. In applications to detect an object in real time, when transmitting a large amount of image data it is possible to find the mode of a color distribution. The specific color of an object is modified at dynamically changing color in image. So, this algorithm detects the tracking area information of object within relevant tracking area and only tracking the movement of that object.Through experiments, we show that proposed method is more robust than other methods under certain ideal situations.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.67-67
• /
• 2021

하구에서의 흐름은 하천의 담수와 바다에서부터 유입되는 염수, 조석, 파랑 등으로 인해 복잡한 흐름구조와 혼합 양상을 보인다. 특히 만 내에 하천이 있을 경우 만의 해류특성은 하구에서의 혼합과 이송에 지배적인 영향을 미치며, 하천에서부터 방류되는 입자들은 만의 해류특성 따라 만에서의 체류시간과 이송이 결정된다. 잔차류 특성에 의한 순 물질 플럭스의 방향과 조석비대칭에 따른 하구에서의 퇴적 형태들이 결정되며, 이로 인해 하구에서의 퇴적물 퇴적 및 물질의 집적 위치, 하구 인근과 만에서의 환경변화에 영향을 줄 수 있다. 따라서 만 내에서의 혼합과 입자의 이송확산, 하천 담수의 영향역 등과 같은 만과 하천의 흐름 특성을 이해하는 것은 연안 및 하구의 환경 및 관리에 중요하다. 본 연구에서는 영일만과 형산강을 대상으로 계절변화에 따른 영일만 내 흐름과 형산강 하구에서의 퇴적양상에 대해 수치모의를 통해 수행하였다. 수치모델로는 천수방정식으로 준 3차원 유동해석을 하는 Delft-3D Flow와 파랑모형인 SWAN 모델을 결합하여 형산강 하구와 영일만의 유동을 해석하였다. 상류개방경계는 형산강하구 9 km, 하류개방경계는 영일만 외해 50 km로 설정하였고, 경계조건은 대상지역의 관측소 자료와 전지구 모형자료를 결합하여 구성하였다. 또한, 라그랑쥬 입자추적모델을 통해 형산강 상류에서 유입한 입자들의 영일만 내 체류 시간과 집적 위치를 평가하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.04b
• /
• pp.586-588
• /
• 2000

KUeyes는 3차원 실세계의 영상처리를 위해 고려대학교 인공시각연구센터에서 개발된 컬러 스테레오 헤드아이 시스템이다. KUeyes는 인간의 시각 시스템을 모델로 하여 다해상도 변환 영상, 칼라 정보와 거리 정보, 움직임 정보를 이용하여 지능적이고 빠르게 객체를 탐지하여 추적한다. 또한 병렬적으로 수행되는 인식기를 통해 탐지된 사람의 얼굴을 인식한다. 다양한 실험 및 분석을 통해 KUeyes가 복잡한 실영상을 대상으로 움직이는 개체를 신시간으로 안정되게 추적하고 인식하는 것을 확인할 수 있었다.

• Annual Conference of KIPS
• /
• 2003.05a
• /
• pp.567-570
• /
• 2003

본 논문에서는 연속영상 속에 있는 얼굴영역을 칼만 필터를 이용하여 추적하는 방법을 제안한다. 제안된 방법은 영역-기반접근(region-based approach)방법인 워터쉐드 알고리즘을 이용하여 초기 영역 분할 작업을 한 후 얼굴칼라 모델과의 매칭작업을 통해서 얼굴영역을 찾아내는 얼굴검출 단계와 추출된 얼굴영역의 칼라정보를 칼만 필터의 입력으로 하여 얼굴을 추적하는 단계로 구성되어 있다. 실험결과를 통하여 제안된 방법이 배경이 복잡한 영상에 대해서도 효율적으로 얼굴을 추적할 수 있음을 보인다.

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.497-501
• /
• 2022

대화 상태 추적(Dialogue State Tracking)은 특정 목적을 달성하기 위한 대화 시스템인 목적 지향 대화 시스템의 핵심 부분으로, 대화에서 표현된 사용자의 목적을 추출한다. 조기 위험 검출 시스템은 연속적으로 들어오는 정보를 바탕으로 분류 대상인지 아닌지를 판별하며, 정확도 저하를 피하면서 최대한 빠르게 분류하는 것을 목표로 한다. 본 연구에서는 대화 상태 추적 시스템에서 나온 은닉층을 입력으로 하여 실시간으로 공황 장애 여부를 점진적으로 조기 분류하는 시스템과 조기 분류를 위한 새로운 손실 함수를 제안한다. 조기 위험 검출 시스템에 대화 상태인 belief state의 정보를 함께 사용했을 때, 큰 성능 향상을 보였으며 대화 상태가 조기 위험 검출에 필요한 정보를 담고 있음을 확인할 수 있다.

• Journal of Korea Multimedia Society
• /
• v.12 no.8
• /
• pp.1089-1098
• /
• 2009

Recently, many researches of making more comfortable input device based on gaze detection technology have been performed in human computer interface. Previous researches were performed on the computer environment with a large sized monitor. With recent increase of using mobile device, the necessities of interfacing by gaze detection on mobile environment were also increased. In this paper, we research about the gaze detection method by using UMPC (Ultra-Mobile PC) and an embedded camera of UMPC based on face and facial feature detection by AAM (Active Appearance Model). This paper has following three originalities. First, different from previous research, we propose a method for tracking user's gaze position in mobile device which has a small sized screen. Second, in order to detect facial feature points, we use AAM. Third, gaze detection accuracy is not degraded according to Z distance based on the normalization of input features by using the features which are obtained in an initial user calibration stage. Experimental results showed that gaze detection error was 1.77 degrees and it was reduced by mouse dragging based on the additional facial movement.

• The KIPS Transactions:PartB
• /
• v.16B no.5
• /
• pp.385-394
• /
• 2009

Face tracking and recognition are difficult problems because the face is a non-rigid object. The main reasons for the failure to track and recognize the faces are the changes of a face pose and environmental illumination. To solve these problems, we propose a nonlinear manifold framework for the face pose and the face illumination normalization processing. Specifically, to track and recognize a face on the video that has various pose variations, we approximate a face pose density to single Gaussian density by PCA(Principle Component Analysis) using images sampled from training video sequences and then construct the GMM(Gaussian Mixture Model) for each person. To solve the illumination problem for the face tracking and recognition, we decompose the face images into the reflectance and the illuminance using the SSR(Single Scale Retinex) model. To obtain the normalized reflectance, the reflectance is rescaled by histogram equalization on the defined range. We newly approximate the illuminance by the trained manifold since the illuminance has almost variations by illumination. By combining these two features into our manifold framework, we derived the efficient face tracking and recognition results on indoor and outdoor video. To improve the video based tracking results, we update the weights of each face pose density at each frame by the tracking result at the previous frame using EM algorithm. Our experimental results show that our method is more efficient than other methods.

• Proceedings of the Korea Contents Association Conference
• /
• 2008.05a
• /
• pp.10-14
• /
• 2008

Computer-animated crowd scenes are often observed in computer games and feature films. The common way to model locomotion of large human crowds is to employ agent based methods where the behavior of each person is independently modeled. But for large crowds, it is difficult for a user to control all the individuals using individual behavior model. Instead, crowd behaviors can be controlled more intuitively at the group level than at the individual level. In this paper, we present the group force field model to simulate path following behavior for groups. A group is a set of characters who have the same goals, i.e. the same path to follow. We also define three characteristics of grouping behavior: alignment, cohesion, and distribution. Our group force field model preserves these characteristics while avoiding collisions. By using our model, user can generate desired group behaviors from line-up behavior to lumped one.

• Journal of Digital Convergence
• /
• v.10 no.7
• /
• pp.123-128
• /
• 2012

In this paper, we propose a landmark-detection system of object for more accurate object recognition. The landmark-detection system of object becomes divided into a learning stage and a detection stage. A learning stage is created an interest-region model to set up a search region of each landmark as pre-information necessary for a detection stage and is created a detector by each landmark to detect a landmark in a search region. A detection stage sets up a search region of each landmark in an input image with an interest-region model created in the learning stage. The proposed system uses Fast Fourier Transform to detect landmark, because the landmark-detection is fast. In addition, the system fails to track objects less likely. After we developed the proposed method was applied to environment video. As a result, the system that you want to track objects moving at an irregular rate, even if it was found that stable tracking. The experimental results show that the proposed approach can achieve superior performance using various data sets to previously methods.

• Journal of Institute of Control, Robotics and Systems
• /
• v.7 no.9
• /
• pp.749-757
• /
• 2001

We present a simple artificial landmark model and robust landmark tracking algorithm for mobile robot localization. The landmark model, consisting of symmetric and repetitive color patches, produces color histograms that are invariant under the geometric and photometric distortions. A stochastic approach based on the CONDENSATION tracks the landmark model robustly even under the varying illumination conditions. After the landmark detection, relative position of the mobile robot to the landmark is calculated. Experimental results show that the proposed landmark model is effective and can be detected and tracked in a clustered scene robustly. With the tracked single landmark, we extract geometrical information than achieve accurate localization.