• 디지털융복합연구
• /
• 제13권9호
• /
• pp.183-189
• /
• 2015

본 논문은 서베일런스 네트워크에서 영상의 색상 정보를 이용한 객체 추적 방법을 제안한다. 이 방법은 적응적인 색상 모델을 이용한 객체 검출을 수행한다. 객체 윤곽선 검출은 객체 인식과 같은 응용에서 중요한 역할을 수행한다. 실험 결과는 색상과 크기에서 객체의 다양한 변화가 있을 때에도 성공적인 객체 검출을 증명한다. 실시간으로 객체를 검출하는 응용 분야에서 대량의 영상 데이터를 전송할 때 색상 분포의 형태를 찾아내는 것이 가능하다. 객체의 특정 색상 정보는 입력 영상에서 동적으로 변화하는 색상에서 자주 수정되어진다. 그래서, 이 알고리즘은 해당 추적 영역 안에서 객체의 추적 영역 정보를 탐지하고 그 객체의 움직임만을 추적한다. 실험을 통해, 본 논문은 어떤 이상적인 상황하에서 제안하는 객체 추적 알고리즘이 다른 방법보다 더 강인한 면이 있다는 것을 보여준다.

• Spatial Information Research
• /
• 제5권1호
• /
• pp.77-88
• /
• 1997

본 논문에서는 객체관계형 지리정보 시스템의 설계 및 구현에 대하여 논한다. 본 지리정보 시스템은 상용의 객체관계형 데이터베이스 시스템을 하부 구조로 사용하며, 객체지향 데이터 모델에 근거한 공간 객체모델, 공간 질의어 및 시각적 사용자 인터페이스를 제공하고 있다. 특히 본 시스템에서는 데이터베이스 상의 주색인(primary index)기법으로 적용 가능한 DOT 공간 색인 기법을 이용하여 효율적인 공간 질의 처리를 수행한다. 또한 본 시스템에서는 SDTS데이터 모델을 개념적 모델로 사용하며, SDTS의 공간 객체에 관한 개념적 모델은 지리정보 시스템 내에서 내부 데이터 모델인 객체지향 데이터 모델로 전환된다.

• 산학경영연구
• /
• 제6권
• /
• pp.153-179
• /
• 1993

The main purpose of this study is to suggest the new strategic management model for the future successful company. The new model consists of the following structure. First, to identify the object dimension. The upper object is to satisfy the customers needs. And the lower object is to satisfy the workers needs. Second, to identify the external enviromental problems dimensions. There are five dimensions. They are ethical responsinilities, government-business alliances, collaboration amongst competitors, innovative invester-company relations, and globalization of enterprise. Third, to identify the internal enviromental problems dimensions. There are two dimensions. They are new organizational forms and integrated subcultures. Fourth, to find the solution for the above dimensions. The solution is as follow. All the managers and workers must have business reengineering minds and apply the complexity management. And the company should construct the strategic information systems.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2023년도 가을학술발표대회논문집
• /
• pp.239-240
• /
• 2023

Construction site management involves overseeing tasks from the construction phase to the maintenance stage, and digitalization of construction sites is necessary for digital construction site management. In this study, we aim to conduct research on object recognition at construction sites using drones. Images of construction sites captured by drones are reconstructed into BIM (Building Information Modeling) models, and objects are recognized after partially rendering the models using artificial intelligence. For the photorealistic rendering of the BIM models, both traditional filtering techniques and the generative adversarial network (GAN) model were used, while the YOLO (You Only Look Once) model was employed for object recognition. This study is expected to provide insights into the research direction of digital construction site management and help assess the potential and future value of introducing artificial intelligence in the construction industry.

• 디지털산업정보학회논문지
• /
• 제15권3호
• /
• pp.29-36
• /
• 2019

With the rapid development of 5G technology, more and more network functions are interconnected and more popular. In order to effectively manage emerging network concepts, it allows any device object in the real world to be connected anywhere and at any time through the integration of device object recognition, interaction and raw data collection technologies. In addition, IP Multimedia Subsystem (IMS) is an architecture framework for transmitting IP-based information to the device object which can be represented as end user. Therefore, the Internet of Things and IP Multimedia Subsystem (IoT-IMS) communication platform can provide a convenient and fast way for user or device objects to deploy new application services effectively. In particular, in order to collect and manage the device information from IoT effectively in the IoT-IMS communication platform, an IoT Information Gateway (IIG) is proposed. Through the IoT Application Service (AS) scenario, the collected device information can be easily observed and managed in a unified way.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2004년도 Proceedings of ISRS 2004
• /
• pp.272-275
• /
• 2004

Recently, the services using position information of moving objects is embossed. Theses services needs the moving objects databases to manage moving object data with efficiency. To build the moving object databases, we must develop the moving object engine to mange, store, and search the spatio temporal data of moving object. The moving object engine has to support query syntax to search data that suitable for user need like LBS, Telematics, ITS, vehicle management system. In this paper, we design and implement the moving object engine to support service with moving object data. The moving object engine is able to support system environment that users are able to get the moving object data easily even they don't know complex data structure.

• 디지털산업정보학회논문지
• /
• 제14권1호
• /
• pp.77-85
• /
• 2018

This paper proposes a robust digital video stabilization algorithm to extract and track an object, which uses a phase correlation-based motion correction. The proposed video stabilization algorithm consists of background stabilization based on motion estimation and extraction of a moving object. The motion vectors can be estimated by calculating the phase correlation of a series of frames in the eight sub-images, which are located in the corner of the video. The global motion vector can be estimated and the image can be compensated by using the multiple local motions of sub-images. Through the calculations of the phase correlation, the motion of the background can be subtracted from the former frame and the compensated frame, which share the same background. The moving objects in the video can also be extracted. In this paper, calculating the phase correlation to track the robust motion vectors results in the compensation of vibrations, such as movement, rotation, expansion and the downsize of videos from all directions of the sub-images. Experimental results show that the proposed digital image stabilization algorithm can provide continuously stabilized videos and tracking object movements.

• 디지털산업정보학회논문지
• /
• 제15권3호
• /
• pp.37-44
• /
• 2019

In this study, we propose the automatic extraction method of Rescue Requests from Drone Images. A central object is extracted from each image by using central object extraction method[7] before classification. A central object in an images are defined as a set of regions that is lined around center of the image and has significant texture distribution against its surrounding. In this case of artificial objects, edge of straight line is often found, and texture is regular and directive. However, natural object's case is not. Such characteristics are extracted using Edge direction histogram energy and texture Gabor energy. The Edge direction histogram energy calculated based on the direction of only non-circular edges. The texture Gabor energy is calculated based on the 24-dimension Gebor filter bank. Maximum and minimum energy along direction in Gabor filter dictionary is selected. Finally, the extracted rescue requestor object areas using the dominant features of the objects. Through experiments, we obtain accuracy of more than 75% for extraction method using each features.

• 디지털산업정보학회논문지
• /
• 제18권3호
• /
• pp.55-73
• /
• 2022

This study aims to identify the object relations and PAD factors of Instagram users, apply the object relations to the emotional response (PAD) factors, and empirically study the structural relationship between these factors and satisfaction. To this end, we proposed a research model to which the four factors of object relations theory and the three factors of emotional response (PAD) theory that emphasize the emotions of users are applied. Surveys were conducted on the college students in Seoul and Suwon who had used Instagram. As a result of this study, the following conclusions can be drawn: Non-alienation has a significant influence on pleasure, arousal, and domination. Secure attachment does not have a significant influence on pleasure and arousal, while it does have on domination. Social ability does not have a significant influence on pleasure, arousal, and domination. Egocentrism has a significant influence on arousal, but not on pleasure and domination. Pleasure has a significant influence on arousal and satisfaction. Arousal has a significant influence on domination and satisfaction. Domination has a significant influence on satisfaction. In conclusion, when emotions are shared among the users of Instagram, not alienated, it affects their satisfaction.

• 한국건설관리학회:학술대회논문집
• /
• 한국건설관리학회 2002년도 학술대회지
• /
• pp.107-114
• /
• 2002

건설 사업관리를 위해 많은 소프트웨어들이 사용되어감에 따라 데이터 또는 정보 통합이 중요해지게 되었다 이번 연구에서는 건설 정보의 통합에서 설계와 일정 정보의 통합에 초점을 맞추고 있으며, 정보 모델에 관련된 기존의 연구 결과를 분석하여 일정 정보에 대한 일반 모델을 제시하고자 하였다. 이러한 일반 모델은 설계-공정 정보의 연계를 기반으로 설계되었으며, 이를 직접 구현할 수 있는 방안을 제시하고자 한다. 현재 많은 관심을 보이고 있는 개체지향 CAD의 기술을 활용하여 모델에 대한 프로토타입을 구현하였고 이러한 모델이 완성되기 위한 추후 연구 과제도 함께 제시하였다.