• Communications for Statistical Applications and Methods
• /
• 제21권3호
• /
• pp.225-234
• /
• 2014

We propose a novel hierarchical clustering for distribution valued dissimilarities. Analysis of large and complex data has attracted significant interest. Symbolic Data Analysis (SDA) was proposed by Diday in 1980's, which provides a new framework for statistical analysis. In SDA, we analyze an object with internal variation, including an interval, a histogram and a distribution, called a symbolic object. In the study, we focus on a cluster analysis for distribution valued dissimilarities, one of the symbolic objects. A hierarchical clustering has two steps in general: find out step and update step. In the find out step, we find the nearest pair of clusters. We extend it for distribution valued dissimilarities, introducing a measure on their order relations. In the update step, dissimilarities between clusters are redefined by mixture of distributions with a mixing ratio. We show an actual example of the proposed method and a simulation study.

• Journal of information and communication convergence engineering
• /
• 제3권1호
• /
• pp.56-61
• /
• 2005

In this paper, we present a video rate control scheme for storage and delivery in which the time-varying viewing interests are controlled by human gaze. To track the gaze, the pupil's movement is detected using the three-step process : detecting face region, eye region, and pupil point. To control bit rates, the quantization parameter (QP) is changed by considering the static parameters, the video object priority derived from the pupil tracking, the target PSNR, and the weighted distortion value of the coder. As results, we achieved human interfaced visual model and corresponding region-of-interest rate control system.

• International Journal of Advanced Culture Technology
• /
• 제10권1호
• /
• pp.302-309
• /
• 2022

Occupational safety accidents are caused by various factors, and it is difficult to predict when and why they occur, and it is directly related to the lives of workers, so the interest in safety accidents is increasing every year. Therefore, in order to reduce safety accidents at industrial fields, workers are required to wear personal protective equipment. In this paper, we proposes a method to automatically check whether workers are wearing safety helmets among the protective equipment in the industrial field. It detects whether or not the helmet is worn using YOLOv5, a computer vision-based deep learning object detection algorithm. We transfer learning the s model among Yolov5 models with different learning rates and epochs, evaluate the performance, and select the optimal model. The selected model showed a performance of 0.959 mAP.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2003년도 추계학술발표논문집 (상)
• /
• pp.511-514
• /
• 2003

본 연구는 입력된 영상으로부터 특정한 형태를 이루고 있는 대상 물체를 추출함에 있어, 처리에 소요되는 시간 비용(Time cost)을 줄이는 것을 목적으로 하고 있다. 이를 위하여 특정 관심 지역(Region of Interest)이나 대상 물체(Tareet object)의 경계 검출(Boundary detection)을 하는 과정에 통계학적 수치자료(SSM : Statistical Shape Model)를 사용한 접근법을 이용하였다. 또한, 향후 연구 방향인 의료 영상해석(Medical image analysis)으로의 확장성을 고려, 의료 영상 해석에 많이 사용되어지는 MRI, CT, X-Ray 이미지가 Gray level 영상이라는 것을 감안하여 Gray level 영상을 연구 대상으로 삼았다.

• 한국콘텐츠학회:학술대회논문집
• /
• 한국콘텐츠학회 2003년도 추계종합학술대회 논문집
• /
• pp.460-467
• /
• 2003

한국 만화애니메이션학회의 연구 자료에 따르면 애니메이션 장르에 대한 수용자의 선호도는 조사 대상의 50%가 흥미에 기반하고 있다고 답하였다. 애니메이션에서의 흥미유발의 요소는 여러 가지가 있겠으나 그 중에서도 인물의 액션장면이라 할 수 있다. 본 연구는 일본 애니메이션 '원령공주'와 '신세기 에반게리온'을 중심으로 액션 장면의 장면 전환에 나타나는 인물(대상)의 이동 형태의 특징과 차이를 분석하고 그 결과에 따른 특징적 표현들이 실제 수용자들에게 역동적인 요소로서 영향을 끼치는지 알아보았다.

• 수산해양교육연구
• /
• 제27권6호
• /
• pp.1676-1684
• /
• 2015

The study was conducted to develop the Practical STEAM education Model. To achieve the goal, we did analysis advanced research, comprehensive review of literature, consultation with research team. As a result, the Practical STEAM education Model is consisted as follow; integrated subjects, object, value and aim, curriculum(method, assessment). The result has defined the concept and theoretical framework of STEAM education curriculum as application aspects, it would help to develop the program with STEAM education curriculum. Later in this study is to develop programs and organize. and It intends to become the base to be able to interest and interest in science education by structured around the status of problems that can be found in the life of around themes STEAM.

• 한국멀티미디어학회논문지
• /
• 제20권2호
• /
• pp.196-204
• /
• 2017

Behavior of intelligent video surveillance system is recognized by analyzing the pattern of the object of interest by using the frame information of video inputted from the camera and analyzes the behavior. Detection of object's certain behaviors in the crowd has become a critical problem because in the event of terror strikes. Recognition of object's certain behaviors is an important but difficult problem in the area of computer vision. As the realization of big data utilizing machine learning, data mining techniques, the amount of video through the CCTV, Smart-phone and Drone's video has increased dramatically. In this paper, we propose a multiple-sliding window method to recognize the cumulative change as one piece in order to improve the accuracy of the recognition. The experimental results demonstrated the method was robust and efficient learning units in the classification of certain behaviors.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2019년도 추계학술대회
• /
• pp.252-255
• /
• 2019

본 논문에서 Equirectangular projection(ERP) 영상을 행동 인식 모델에 입력하기전 제안하는 전처리를 통하여 성능을 향상시키는 것을 보인다. ERP 영상의 특성상 행동 인식을 하는데 불필요한 영역이 일반적인 2D 카메라로 촬영한 영상보다 많다. 또한 행동 인식은 사람이 Object of Interest(OOI)이다. 따라서 객체 인식모델로 인간 객체를 인식한 후 Region of Interest(ROI)를 추출하여 불필요한 영역을 없애고, 왜곡 또한 줄어든다. 본 논문에서 제안하는 기법으로 전처리 후 CNN-LSTM 모델로 성능을 테스트했다. 제안하는 방법으로 전처리를 한 데이터와 하지 않은 데이터로 행동 인식을 한 정확도로 비교하였으며 제안하는 기법으로 전처리 한 데이터로 행동 인식을 한 경우 데이터의 특성에 따라 다르지만, 최대 61%까지 성능향상을 보였다.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2002년도 Proceedings of International Symposium on Remote Sensing
• /
• pp.163-167
• /
• 2002

Recently, owing to performance elevation of telecommunication technology, increase of wireless internet's subscriber and diffusion of wireless device, Interest about LBS (Location Based Service) which take advantage of user's location information and can receive information in concerning with user's location is increasing rapidly. So, MOMS (Moving Object Management System) that manage user's location information is required compulsorily to provide location base service. LBS of childhood such as service to find a friend need only current location, but to provide high-quality service in connection with Data Mining, CRM, We must be able to manage location information of past. In this paper, we design distributed manage system to insert and search Moving Object in a large amount. It has been consisted of CLIM (Current Location Information Manager), PLIM (Past-Location Information Manager) and BLIM (Distributed Location Information Manager). CLIM and PLIM prove performance of searching data by using spatiotemporal-index. DLIM distribute an enormous amount of location data to various database. Thus it keeps load-balance, regulates overload and manage a huge number of location information efficiently.

• 한국인터넷방송통신학회논문지
• /
• 제12권3호
• /
• pp.155-162
• /
• 2012

본 논문에서는 유비쿼터스 시대가 도래함에 따라 사회적으로 실내 위치 추적 시스템에 대한 관심이 증가되었다. 하지만 기존 실내 위치 추적 시스템은 실내 환경의 빈번한 변화에 능동적으로 대응하지 못하고, 실내 환경의 NLOS 특성으로 인하여 이동 객체의 정확한 위치 측정이 어려운 문제점이 있다. 본 연구의 목적은 앞으로 유비쿼터스 시대가 도래함에 따라 다양한 사용자의 요구를 만족시키기 위한 서비스를 제공하는데 필수 요소인 실내 이동 객체의 위치를 효과적으로 파악하고, 이동 객체의 위치 정확도를 향상시킨 환경 적응형 위치 추적 시스템을 제안한다.