• Proceedings of the Korea Society for Simulation Conference
• /
• 1999.04a
• /
• pp.54-59
• /
• 1999

본 논문에서는 유연생산시스템 (FMS: Flexible Manufacturing System)의 객체지향 시뮬레이션(OOS: Object Oriented Simulation)에 대한 기존의 연구들을 소개한다. 먼저 FMS와 객체지향시뮬레이션의 일반적인 개념에 대해서 이야기하고 기존의 연구들을 대상 시스템의 추상화(abstraction)과정을 중심으로 분류하여 정리하였다. 추상화 방법론과 FMS를 위한 객체지향시뮬레이션의 현황 및 과제에 대해서도 간략하게 살펴보았다.

• Journal of Korea Society of Industrial Information Systems
• /
• v.11 no.1
• /
• pp.77-85
• /
• 2006

In this paper, we propose a hierarchical classifier of object images using neural networks for content-based image classification. The images for classification are object images that can be divided into foreground and background. In the preprocessing step, we extract the object region and shape-based texture features extracted from wavelet transformed images. We group the image classes into clusters which have similar texture features using Principal Component Analysis(PCA) and K-means. The hierarchical classifier has five layes which combine the clusters. The hierarchical classifier consists of 59 neural network classifiers learned with the back propagation algorithm. Among the various texture features, the diagonal moment was the most effective. A test with 1000 training data and 1000 test data composed of 10 images from each of 100 classes shows classification rates of 81.5% and 75.1% correct, respectively.

• Journal of Broadcast Engineering
• /
• v.16 no.3
• /
• pp.462-470
• /
• 2011

We proposed a realtime object tracking system that detects the abandoned or disappeared objects. Because these events are caused by human, we used the tracking based algorithm. After the background subtraction by Gaussian mixture model, the shadow removal is applied for accurate object detection. The static object is classified as either of abandoned objects or disappeared object. We assigned monitoring time to the static object to overcome a situation that it is being overlapped by other object. We obtained more accurate detection by using region growing method. We implemented our algorithm by DSP processor and obtained an excellent result throughout the experiment.

• Journal of the Korea Computer Industry Society
• /
• v.10 no.4
• /
• pp.127-134
• /
• 2009

This paper has been designed genius software program model that introducted new class basing the Heurilistic Classification model. In order to implement this model, we have introducted heurilistic class to genius software program. And we compared comparing group with treating group using genius software program and study relationship of creation increase.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.11a
• /
• pp.767-770
• /
• 2002

영상 검색의 수행 방법으로 사람의 시각 시스템의 특성을 기반으로 웨이블릿 변환의 고주파수 에너지와 형태학적 필터링을 이용하여 분할된 객체의 효과적인 특징 추출을 통한 계층적인 검색 시스템을 제안한다. 영상 고유의 특징을 얻기 위해 객체의 형태 정보와 질감(texture) 방향성 및 칼라 정보를 이용한다. 본 논문에서는 객체의 형태 정보의 추출을 위하여 사용자의 질의(query)영상에서 객체의 윤곽선의 편각차분 변동율에 의한 형태 특징 벡터를 추출하고 GLCM (Gray Level Co-occurrence Matrix)의 Contrast를 질감 특징으로 추출한다. 이들 두 특징을 이용하여 1차 분류 과정을 거치고 2차 검사에서는 보다 정확한 검색을 수행하기 위하여 1차로 분류된 후보영상들에 대하여 세부 정보인 칼라 정보를 기반으로 유사도를 측정함으로써 유사한 칼라와 형태를 가지는 영상뿐만 아니라 칼라가 다른 유사한 영상에도 효율적인 검색 성능을 보였다.

• Journal of Broadcast Engineering
• /
• v.21 no.5
• /
• pp.782-791
• /
• 2016

The object segmentation algorithm from the background could be used for object recognition and tracking, and many applications. To segment objects, this paper proposes a method that refer to several initial frames with real-time processing at fixed camera. First we suggest the probability model to segment object and background and we enhance the performance of algorithm analyzing the color consistency and focus characteristic of camera for several initial frames. We compensate the segmentation result by using human skeleton characteristic among extracted objects. Last the proposed method has the applicability for various mobile application as we minimize computing complexity for real-time video processing.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.10b
• /
• pp.442-447
• /
• 2006

디지털 카메라의 대중화와 고용량 저장매체의 보편화로 인해 대중들은 손쉽게 디지털 사진 촬영이 가능하게 되었다. 디지털 사진은 필름 사진과 달리 촬영을 하는데 있어 비용이 들지 않을 뿐만 아니라 플래쉬 메모리의 증가로 인해 다수의 사진들을 촬영할 수 있게 되었으나 그만큼 많은 사진들을 관리하고 분류하는 것은 쉽지 않은 일이 되었다. 따라서 디지털 사진을 자동으로 분류하고 관리하는 기능은 중요한 과제가 되었지만, 현재까지 나온 방법들은 사진 내의 객체가 확대, 축소 및 이동하거나 배경이 바뀌는 영상에 있어서 정확한 유사도를 측정하여 분류하는데 어려움이 있었다. 본 논문에서는 이와 같은 어려움을 보완한 디지털 사진의 클러스터링 알고리즘을 제안한다. 입력영상을 그리드 형태로 나누어 각 블록별로 측정한 유사도 값을 바탕으로 클러스터링하며, 이때 디지털 사진 내에 포함되어 있는 촬영정보인 EXIF를 이용하여 입력 영상에 따라 적응적(adaptive)으로 그리드를 나누어 비교한다. 또한, 영상에 따라 각기 다른 색상의 분포 정도를 고려해 색상 가중치를 고려하여 사진을 비교함으로써, 영상의 고수준(high-level) 분석에서처럼 객체와 배경을 추출하여 따로 분리하지 않고도 객체의 배경이 다른 사진들을 저수준(low-level) 에서 분석이 가능토록 하였다. 제안한 방법으로 실험한 결과 객체의 크기 및 이동이나 배경에 큰 영향을 받지 않으면서 입력영상들을 클러스터링 할 수 있었다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.5
• /
• pp.3183-3191
• /
• 2014

It is essential to effectively manage facilities because operating and maintenance cost for them accounts for more than 83% of lifecycle cost. This study developed BIM Object-based classification list to manage information required to operating and maintenance phase of them from design and construction phase. In order to develop this classification list, Construction Information Classification System, Design Criteria for Architectural Electrical Installations, commodity list classification of PPS(Public Procurement Service) were analyzed. and problems for consisting of object classification list were drawn. And each materials is classified that drawings discipline code (KSF 1540:2010 (Principle and criteria for CAD Drawing) was classified as level 1 to cover main areas and construction information classification system was classified as level 2 to cover elements also UNSPSC was classified as level 3 to cover objects for devices and equipments. this classification criteria was given code. This study is expected to be useful to exchange and share information in operating and maintenance phase by offering object point of view classification in design and construction phase. besides, it is looking forward to effective operating and maintenance of facilities by enabling management of devices and equipments by function, space, use.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.1
• /
• pp.144-150
• /
• 2017

Recently, deep learning is used for intelligent processing and accuracy improvement of data. It is formed calculation model composed of multi data processing layer that train the data representation through an abstraction of the various levels. A category of deep learning, convolution neural network is utilized in various research fields, which are human pose estimation, face recognition, image classification, speech recognition. When using the deep layer and lots of class, CNN that show a good performance on image classification obtain higher classification rate but occur the overfitting problem, when using a few data. So, we design the training network based on convolution neural network and trained our image data set for object classification in few class problem. The experiment show the higher classification rate of 7.06% in average than the previous networks designed to classify the object in 1000 class problem.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.33 no.2
• /
• pp.73-79
• /
• 2020

Building Information Modeling (BIM) tools have not only increased the use of technology in the design process, but also increased the need for more information standard systems. The object classification system consists of 327 types of construction results obtained from 25 kinds of facilities, 174 types of parts, and 207 types of construction parts. In the previous study, the property classification system was developed into 4 major classifications, 13 middle classifications, 58 small classifications (category), and 333 attribution information of roads and rivers. It is extremely difficult to input the property information according to such extensive object classification. In addition, the development of external applications such as Revit plug-ins has created a need to automate specific and repetitive tasks. Therefore, following the BIM property classification system, an attribute input program was implemented for the system to enhance the productivity and convenience of the BIM users.