• 한국멀티미디어학회논문지
• /
• 제25권4호
• /
• pp.583-599
• /
• 2022

Although the object detection accuracy with a single image has been significantly improved with the advance of deep learning techniques, the detection accuracy for pig monitoring is challenged by occlusion problems due to a complex structure of a pig room such as food facility. These detection difficulties with a single image can be mitigated by using a video data. In this research, we propose a method in pig detection for video monitoring environment with a static camera. That is, by using both image processing and deep learning techniques, we can recognize a complex structure of a pig room and this information of the pig room can be utilized for improving the detection accuracy of pigs in the monitored pig room. Furthermore, we reduce the execution time overhead by applying a pruning technique for real-time video monitoring on an embedded board. Based on the experiment results with a video data set obtained from a commercial pig farm, we confirmed that the pigs could be detected more accurately in real-time, even on an embedded board.

• 대한용접접합학회:학술대회논문집
• /
• 대한용접접합학회 1998년도 특별강연 및 추계학술발표 개요집
• /
• pp.3-8
• /
• 1998

This paper considers factory simulation based on shipbuilding CIM in which a computer integrated design and manufacturing system is considered. The author proposes the product model and several alterative functions for designing ship's structure, and develop a ship definition system for computer integrated design and manufacturing. This implemented system is called SODAS (System Of Design and Assembly for Shipbuilding). Object oriented concept is used to develop this system. As well as the product model, the design function cutting function, and virtual assembling function are introduced. By using the design function, any type of ship's structure can be designed. And also factory simulation can be carried out by using the cutting function and virtual assembling function.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2003년도 춘계학술대회 논문집
• /
• pp.306-311
• /
• 2003

This paper presents a novel localization paradigm for mobile robots based on artificial and natural landmarks. A model-based object recognition method detects natural landmarks and conducts the global and topological localization. In addition, a metric localization method using artificial landmarks is fused to complement the deficiency of topology map and guide to action behavior. The recognition algorithm uses a modified local Zernike moments and a probabilistic voting method for the robust detection of objects in cluttered indoor environments. An artificial landmark is designed to have a three-dimensional multi-colored structure and the projection distortion of the structure encodes the distance and viewing direction of the robot. We demonstrate the feasibility of the proposed system through real world experiments using a mobile robot, KASIRI-III.

• ETRI Journal
• /
• 제45권1호
• /
• pp.93-104
• /
• 2023

Coreference resolution is a task in discourse analysis that links several headwords used in any document object. We suggest pointer networks-based coreference resolution for Korean using multi-task learning (MTL) with an attention mechanism for a hierarchical structure. As Korean is a head-final language, the head can easily be found. Our model learns the distribution by referring to the same entity position and utilizes a pointer network to conduct coreference resolution depending on the input headword. As the input is a document, the input sequence is very long. Thus, the core idea is to learn the word- and sentence-level distributions in parallel with MTL, while using a shared representation to address the long sequence problem. The suggested technique is used to generate word representations for Korean based on contextual information using pre-trained language models for Korean. In the same experimental conditions, our model performed roughly 1.8% better on CoNLL F1 than previous research without hierarchical structure.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권10호
• /
• pp.3642-3667
• /
• 2021

Texture synthesis technology has the advantages of repairing texture and structure at the same time. However, during the filling process, the size of the patch is fixed, and the content of the filling is not fully considered. In order to be able to adaptively change the patch size, we used the exemplar-based inpainting technique as the test algorithm, considering the image structure and texture, calculated the image structure patch size and texture patch size, and comprehensively determined the image patch size. This can adaptively change the patch size according to the filling content. In addition, we use multi-layer images to calculate the priority, so that the order of image repair was more stable. The proposed repair algorithm is compared with other image repair algorithms. The experimental results showed that the proposed adaptive image repair algorithm can better repair the texture and structure of the image, which proved the effectiveness of the proposed algorithm.

• 정보처리학회논문지D
• /
• 제11D권6호
• /
• pp.1221-1230
• /
• 2004

모바일 환경에서 정보 제공 및 처리의 대상이 되는 사람, 자동차, 비행기 둥과 같은 이동객체는 시간이 경과함에 따라 끊임없이 자신의 위치를 변경하는 특징을 가지며, 이러한 정보들을 데이터베이스에서 효과적으로 처리하기 위해서는 연속적인 위치 변경을 수용할 수 있는 저장공간과 색인 유지 및 관리 기술이 필요하다. 기존의 색인 기법들은 색인의 유지 성능보다 질의 처리 능력을 향상시키는데 노력을 기울여 왔기 때문에 복잡하게 이동하며 매우 빈번하게 위치 정보를 갱신하는 이동객체 정보를 관리하기 어렵다. 이 논문에서는 질의 처리 성능뿐만 아니라 이동객체의 빈번한 위치 갱신을 효율적으로 처리하기 위해 고정 그리드 방식의 색인과 R-Tree의 장점을 결합한 ACAR-Tree(Adaptive Cell index with Auxiliary R-Tree)를 제안한다. 제안된 ACAR-Tree는 R-Tree에서 색인의 재구성으로 인하여 갱신 성능이 저하되는 단점을 보완하기 위하여 고정 그리드 방법의 셀 기반의 색인 방법을 기초로 한다. 또한 고정 그리드 방법에서의 데이터 분포가 편중되었을 경우의 색인 성능저하 문제를 해결하기 위하여, 셀과 버켓이 1 : 1로 매핑되는 셀에서 오버플로가 발생하였을 경우 해당 버켓이 부가적인 색인 구조인 보조R-Tree로 전환하여 처리한다. 제안된 방법을 다양한 데이터 분포 및 데이터 크기에서 실험한 결과, 기존의 R-Tree 기반의 색인 방법과 비교하여 색인의 크기가 크게 감소하였으며, 질의 및 갱신 성능에 대해서도 뛰어난 성능을 보였다.

• 방송공학회논문지
• /
• 제25권5호
• /
• pp.770-775
• /
• 2020

360도 영상은 일반 화각 영상과 다른 프레임 구조를 갖기 때문에 기존 영상 보안 이벤트 검출 알고리즘들을 360도 영상에 바로 적용 시 왜곡에 의한 성능 저하가 발생할 수 있다. 본 논문에서는 360도 영상 공간에서 활성 뷰포트 기반 이벤트 검출 기법을 제안한다. 다중 객체 영역들을 포함하는 활성 뷰포트들을 생성하고, 뷰포트 내 객체 검출과 360도 영상 공간에서 객체 추적을 수행하며, 영역 기반의 보안 이벤트를 검출한다. 제안 방법은 360도 ERP 시퀀스들에 대해 성능이 평가되었고, 활성 뷰포트를 사용하지 않은 이벤트 검출 방법보다 30% 이상의 recall, 30% 이상의 false negative rate 성능 향상을 보였다.

• International Journal of Internet, Broadcasting and Communication
• /
• 제14권1호
• /
• pp.95-104
• /
• 2022

A TPR-tree is a well-known indexing structure that is developed to answer queries about the current or future time locations of moving objects. For the purpose of space efficiency, the TPR-tree employs the notion of VBR (velocity bounding rectangle)so that a regionalrectangle presents varying positions of a group of moving objects. Since the rectangle computed from a VBR always encloses the possible maximum range of an indexed object group, a search process only has to follow VBR-based rectangles overlapped with a given query range, while searching toward candidate leaf nodes. Although the TPR-tree index shows up its space efficiency, it easily suffers from the problem of dead space that results from fast and constant expansions of VBR-based rectangles. Against this, the TPR-tree index is enforced to update leaf nodes for reducing dead spaces within them. Such an update-prone feature of the TPR-tree becomes more problematic when the tree is saved in flash storage. This is because flash storage has very expensive update costs. To solve this problem, we propose a new Bloom filter based caching scheme that is useful for reducing updates in a flash TPR-tree. Since the proposed scheme can efficiently control the frequency of updates on a leaf node, it can offer good performance for indexing moving objects in modern flash storage.

• 시스템엔지니어링학술지
• /
• 제12권2호
• /
• pp.69-80
• /
• 2016

The purpose of this study is to establish a component reutilization system in Nuclear Power Plant (NPP) by Object-Oriented Systems Engineering Method (OOSEM). Unified Modeling Language (UML) is mainly used for OOSEM. Operational Concept (OpsCon), Use cases, Structure Diagrams, and Behavior Diagrams are developed to analyze stakeholders needs, system requirements, logical architecture, and physical architecture. Based on the current decommissioning and purchasing system of the component, some activities from their systems were excepted and additional new activities were developed for a component reutilization system.

• 한국IT서비스학회지
• /
• 제5권2호
• /
• pp.79-92
• /
• 2006

Since software development team members have been more geographically spread due to the globalization of business and Internet technologies, the management of deliverables and communication efforts for developing high-quality software products on time is becoming more complicated. Among the functional requirements for collaborative software development management, the manipulation of shared information objects is essential for the collaborative work among distributed development team members. This paper proposes an integrated information object management framework comprised of a so-called BOC (Bill Of Class) scheme and a standardized software part dictionary for managing shared information objects efficiently among distributed co-workers. In order to manage these complex information objects, the proposed framework adopt product structures represented by Bills Of Materials (BOM) as stems for integrating the various information objects. Based on the proposed framework, a collaborative software development management system (CSDMS) is implemented, and the functionalities and the structure of the system are also described in this paper. The proposed system provides sufficient functionalities for the change management of information objects and the management of their relationship to other objects rather than existing system.