• Journal of the Korean Society for Precision Engineering
• /
• v.16 no.5 s.98
• /
• pp.91-97
• /
• 1999

The background of appearing MMS is to cope with the difficulty that occurred in constructing CIM with multi-vendor production devices such as CNC, PLC and robot. But so far the popularized use of MMS service in machine shop is not generalized because of economical and environmental reason. In this paper to solve this problem the CNC_VMD gateway for 3 types of heterogeneous machine tools in which MMS support is not available is developed and its performance is evaluated in shop floor having CIM environment. The developed VMD has the functions such as MMS service, driver for CNC interface and supporting for network. Non-MMS compatible machine tool can be MMS-compatible by using the developed gateway with CNC_VMD.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2003.05a
• /
• pp.235-238
• /
• 2003

본 논문에서는 웹 기반 강의 컨텐츠의 문제점을 알아보고 그 문제점을 해결할 수 있는 방법을 제안한다. 다시 말해서, 기존의 웹 기반 강의 컨텐츠는 HTML을 기반으로 한 획일적인 하나의 큰 파일이거나 미디어 제공 벤더에 종속된 저작도구로 작성된 파일이다. 이러한 강의 컨텐츠는 서로 다른 가상교육 시스템에서 공유하거나 재사용하기가 어렵다. 그래서 본 논문에서는 분산 컴퓨팅 환경에서 가상 교육시스템들이 공유할 수 있고 재사용 할 수 있도록 강의 컨텐츠를 속성을 가진 더 작은 크기로 분해하여 객체화하는 방법을 제시한다. 특히 교수법(pedagogy)적인 설계 방법론에 근거하여 강의 컨텐츠를 분해 및 객체화하여 강의 컨텐츠의 학습 이해도를 높였다.

• Journal of Digital Convergence
• /
• v.14 no.5
• /
• pp.263-271
• /
• 2016

Localizing an object in image is a common task in the field of computer vision. As the existing methods provide a detection for the single object in an image, they have an utilization limit for the use of the application, due to similar objects are in the actual picture. This paper proposes an efficient method of object localization for image recognition. The new proposed method uses color correlation back-projection in the YCbCr chromaticity color space to deal with the object localization problem. Using the proposed algorithm enables users to detect and locate primary location of object within the image, as well as candidate regions can be detected accurately without any information about object counts. To evaluate performance of the proposed algorithm, we estimate success rate of locating object with common used image database. Experimental results reveal that improvement of 21% success ratio was observed. This study builds on spatially localized color features and correlation-based localization, and the main contribution of this paper is that a different way of using correlogram is applied in object localization.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.9
• /
• pp.2373-2383
• /
• 1999

Recently, due to the popularity of object-oriented programming languages, object-oriented modeling and development methodologies become widely applied to information system development. When object-oriented methodology is adopted, using object-oriented modeling languages for business analysis and redesign has the advantages such that business modeling results can be easily understood and referred by information system developers. In this paper, UML-B, Unified Modeling Language extension for Business modeling is proposed, which uses UML notation for modeling organization structure, actors, use cases, business processes, and entities in business systems. It also utilizes extension mechanisms of UML to facilitate business modeling activities, and supports business process reengineering with object-oriented modeling.

• Journal of Internet Computing and Services
• /
• v.2 no.2
• /
• pp.71-93
• /
• 2001

Commonly to design a database system. a conceptual database has to be designed and then it is transformed into a logical database schema prior to building a target database system. This paper proposes a method which transforms a Temporal Entity-Relationship Model(TERM) into a Temporal Object-Oriented Model(TOOM) to build an efficient database schema. I formalize the time concept in view of object versioning and specify the constraints required during transformation procedure. The proposed transformation method contributes to getting the logical temporal data from the conceptual temporal events Without any loss of semantics, Compared to other approaches of supporting various properties, this approach is more general and efficient because it is the semantically seamless transformation method by using the orthogonality of types of objects, semantics of relationships and constraints over roles.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.5
• /
• pp.16-22
• /
• 2011

This paper presents the multi-object tracking approach using the background difference and particle filtering by monte carlo sampling. We apply particle filters based on probabilistic importance sampling to multi-object independently. We formulate the object observation model by the histogram distribution using color information and the object dynaminc model for the object motion information. Our approach does not increase computational complexity and derive stable performance. We implement the whole Bayesian maximum likelihood framework and describes robust methods coping with the real-world object tracking situation by the observation and transition model.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.01a
• /
• pp.41-44
• /
• 2022

Mean-Shift 영상 분할은 객체 검출을 위한 영상 전처리 방법으로써, 영상 처리 및 패턴 인식 분야에서 널리 사용되는 방법이다. 영상 분할은 영역 기반과 에지 기반 방식으로 나누어지며 대표적으로 FCM, Quickshift, Felzenszwalb, SLIC 알고리즘 등 이 있다. 언급한 영상 분할 방법들은 Mean-Shift 영상 분할에 비해서 빠른 속도로 실행시킬 수 있지만, 형태적 특징이 훼손되고 하나의 객체가 여러 세그멘테이션으로 분할된다는 단점을 가지고 있다. 본 논문에서는 소형 객체를 탐지하기 위한 고속화된 Mean-Shift 영상 분할과 객체의 형태적 특징을 이용하여 객체를 탐지하는 방법을 제안한다. 하드웨어 리소스가 제한된 신호처리기에 제안하는 알고리즘을 수행하기 위하여 Mean-Shift 영상 분할에서 필터링 과정을 고속화 하였고, 적외선 영상 내 영상 전처리 수행을 통해 잡음 제거 후 Mean-Shift 영상 분할 방법을 수행함으로써, 객체의 형태적 특징을 잘 살려서 영상 분할을 할 수 있도록 하였다. 또한 각 세그멘테이션의 크기, 너비, 높이, 밝기 정보와 형태적 특징점을 이용한 객체 탐지 방법을 제안한다.

• Spatial Information Research
• /
• v.7 no.2
• /
• pp.255-269
• /
• 1999

This is an experimental study to translate the Korean digital topographic maps into distributable information-hide objects, which are designed with object-oriented development's key features ; encapsulation, polymorphism, inheritance, In order to achieve this goal , the characteristics of the data mode and inter-relationships of digital topographic maps are investigated . As a result, it is revealed that the current Korean digital topographic maps, which is organized into so many individual layers of mixed spatial and attributed data, have to explicit and concrete hierarchies in spatial data model and data definition . Due to this limitation , data layer stage and object class stage are integrated. And ISCO(the is-computer -of relationships) mechanism is mainly used to develop the objects of digital topogrpahic maps, which is implemented with spatial primitive classes. the designed objects are coded with JAVA and then testified in web interface.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2000.11a
• /
• pp.266-270
• /
• 2000

내용기반 영상검색시스템에서 객체 단위로 영상을 검색하기 위해서는 영상에서 의미있는 객체를 추출하는 과정이 필수적이며, 이를 위해 영역 분할을 효율적으로 수행하기 위한 양자화가 선행되어야 한다. 일반적인 칼라 양자화 기법은 칼라 수를 줄이되 양자화 된 영상이 원시 영상과 가능할 비슷해 보이도록 하는 것을 목적으로 하지만, 영역 분할을 위한 칼라 양자화에서는 칼라의 표현보나는 의미있는 객체를 용이하게 추출할 수 있도록 양자화 하는 것을 목적으로 한다. 본 논문에서는 기존의 Octree 양자화 방법과 K-means 알고리즘의 장점을 조합하여 영역 분할에 용이한 양자화 결과를 얻을 수 있는 방법을 제안한다. 먼저, Octree 양자화 방법을 수행하여 얻어진 양자화 된 칼라들 중에서 시각적으로 유사한 칼라를 병합함으로써, Octree 양자화 방법의 단점인 강제 분할 문제점을 해결한다. 이어서, 병합 후의 양자화 된 칼라에 대해서만 K-means 알고리즘을 수행함으로써, 보다 빠른 시간 내에 영역 분할에 적합한 양자화 된 영상을 얻는다. 실험을 통해 제안한 방법의 효용성을 확인하였다.

• Convergence Security Journal
• /
• v.22 no.5
• /
• pp.11-20
• /
• 2022

As the Internet and web technology develop around mobile devices, image data contains various types of sensitive information such as people, text, and space. In addition to these characteristics, as the use of SNS increases, the amount of damage caused by exposure and abuse of personal information online is increasing. However, research on de-identification technology based on multi-type object detection for personal information protection is insufficient. Therefore, this paper proposes an artificial intelligence model that detects and de-identifies multiple types of objects using existing single-type object detection models in parallel. Through cutmix, an image in which person and text objects exist together are created and composed of training data, and detection and de-identification of objects with different characteristics of person and text was performed. The proposed model achieves a precision of 0.724 and mAP@.5 of 0.745 when two objects are present at the same time. In addition, after de-identification, mAP@.5 was 0.224 for all objects, showing a decrease of 0.4 or more.