• Journal of the Korea Society of Computer and Information
• /
• v.16 no.6
• /
• pp.89-97
• /
• 2011

When examining current process of object tracking and search, objects were tracked by extracting them from image that was inputted through fixed single camera and objects were recognized through Zoom function to know detailed information on objects tracked. This study proposed system that expresses information on area that can seek and recognize object tracked as augmented reality by recognizing and seeking object by using multi camera. The result of experiment on proposed system showed that the number of pixels that was included in calculation was remarkably reduced and recognition rate of object was enhanced and time that took to identify information was shortened. Compared with existing methods, this system has advantage of better accuracy that can detect the motion of object and advantage of shortening time that took to detect motion.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2013.06a
• /
• pp.68-69
• /
• 2013

본 논문에서는 스마트폰에서 한 장의 깊이 영상을 이용하여 내용기반 3 차원 모델 검색 기법을 범용적으로 수행하기 위한 깊이 영상 전처리 기법을 제안한다. 우선 모바일 증강현실 플랫폼 중 하나인 Vuforia 를 이용하여 다수의 영상 취득과 동시에 스마트폰 카메라의 외부 인자들을 추정한다. 그 후 취득된 영상과 외부 인자들을 이용하여 Multi-View Stereo 기법을 통해 깊이 영상을 추정한다. 이렇게 추정된 깊이 영상은 3 차원 모델 검색 기법의 질의 깊이 영상으로 활용되어 3 차원 모델 검색 기법의 입력으로 활용할 수 있다. 실험 결과 본 논문에서 제안하는 전처리 기법으로 추정된 깊이 영상을 이용하였을 경우 3 차원 모델 검색의 범용성이 확장되고 3 차원 모델 검색이 올바르게 수행된 것을 확인하였다.

• Journal of Digital Contents Society
• /
• v.15 no.2
• /
• pp.263-270
• /
• 2014

This paper proposes a new metadata schema for effective mobile service of augmented reality technology, which is used in the convergence of media into a frame among the real world image and objects of virtual world. The proposed metadata schema is extended from JPSearch Core Metadata Schema (ISO/IEC 24800-2 International Standard) with analysis of the functionalities under industrial requirements, and enables to provide an effective application in the actual services. In addition, the proposed schema is available to organize the exchange of information between heterogeneous systems. With development of the prototype system, the proposed metadata schema is going to be submitted and verified under ISO/IEC JTC1 SC29 WG1 JPEG AR standard project.

• Spatial Information Research
• /
• v.23 no.5
• /
• pp.9-19
• /
• 2015

The popularity of smart devices and Location Based Services (LBSes) is increasing in part due to users demand for personalized information associated with their location. These services provide intuitive and realistic information by adopting Augmented Reality (AR) technology. This technology utilizes various sensors embedded in the mobile devices. However, these services have inherent problems due to the devices small screen size and the complexity of the real world environment; overlapping content on a small screen and placing icons without considering the user's possible movement. In order to solve these problems, this paper proposes a Mobile Augmented Reality Model with the application of Street Data. The model consists of two layers: "Real Space" and "Information Space". In the model, a user creates a query by scanning the nearby street with a camera in real space and searches accessible content along the street through the use of the information space. Furthermore, the results are placed on both sides of the street to solve the issue of Overlapping. Also, the proposed model is implemented for region "Aenigol", and the efficiency and usefulness of the model are verified.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.01a
• /
• pp.167-168
• /
• 2020

본 논문에서 제안하는 모바일 어플리케이션은 증강현실 기술을 적용한 정보공유 플랫폼으로 일상 혹은 특별한 여정에서 찍은 사진에 대한 확장 정보를 제공한다. 이 정보들을 통해 자신의 위치를 기준으로 지역을 구체적으로 알아볼 수 있으며 개인의 지역명소를 찾아 공유한다. 누구나 친숙하게 활용할 수 있도록 개발된 모바일 어플리케이션은 지역경제 및 전통시장 활성화에 대한 솔루션으로 제공이 가능하다.

• Journal of Korea Game Society
• /
• v.11 no.3
• /
• pp.63-72
• /
• 2011

In this paper, we propose a novel database creation and retrieval method of feature descriptors to support real-time marker-less tracking in the augmented reality environments. Each feature descriptor is encoded by integer and multi-level database is created in order to retrieve a feature descriptor efficiently. The retrieval of a feature descriptor is performed as follows: Firstly, candidate feature descriptors are searched by traversing the multi-level database. Secondly, the euclidean distance between input feature descriptor and each candidate one is compared. The shortest one is retrieved. The proposed method is 16 ms faster than previous KD-Tree method for each feature descriptor.

• Spatial Information Research
• /
• v.20 no.2
• /
• pp.59-70
• /
• 2012

Advances in science and technology, especially the increasing popularity of smart phone has opened up infinite possibilities for the information retrieval. And the augmented reality technology which has started getting attention to various fields has allowed us to get an information in an innovative way by providing additional information to a real world before our eyes. The purpose of this study is to suggest and to construct mobile application service which give history-tourism information efficiently based on augmented reality technology. As a result of study, we suggest that it is needed to find the view point that the most accurate information can be provided to the users according to each contents such as maps, pictures, drawings etc. and to provide the function to the users which shows the view points information efficiently. The purpose of this study is to investigate the possibility whether the technology studied in private sector by using augmented reality based on smart phone can also be applied in public sector for the service of history tourism information. We expect that this study can be the basis for providing the more advanced augmented reality service in the near future.

• The Journal of Bigdata
• /
• v.3 no.2
• /
• pp.113-121
• /
• 2018

In this study, an augmented reality(AR)-based information management system for agricultural facility is proposed. Using a variety of sensed data transmitted by Lora-based wireless networks deployed at the agricultural facility, this system is capable of augmenting the sensed data and displaying them on the user's smartphone screen to provide visualized information to user. When users point their smartphone camera to the agricultural facility, the environment information collected from numerous sensors installed at the facility would be visualized and appear on the screen. Unlike traditional system which requires user to search a specific facility and then select sensor(s) to obtain the environment information, the proposed system shows the information on smartphone screen by augmenting it with real image captured by camera without doing a series of time-taking selection process. Since the way of acquiring information is through image or video, this system contributes to convenient monitoring and efficient management for agricultural facility.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.295-300
• /
• 2023

대화 데이터와 같은 데이터는 사람이 수작업으로 작성해야 하기 때문에 데이터셋 구축에 시간과 비용이 크게 발생한다. 현재 대두되고 있는 Large Language Model은 이러한 대화 생성에서 보다 자연스러운 대화 생성이 가능하다는 이점이 존재한다. 이번 연구에서는 LLM을 통해 사람이 만든 적은 양의 데이터셋을 Fine-tuning 하여 위키백과 문서로부터 데이터셋을 만들어내고, 이를 통해 문서 검색 모델의 성능을 향상시켰다. 그 결과 학습 데이터와 같은 문서집합에서 MRR 3.7%p, 위키백과 전체에서 MRR 4.5%p의 성능 향상을 확인했다.

• Journal of the Institute of Convergence Signal Processing
• /
• v.16 no.1
• /
• pp.22-28
• /
• 2015

In this paper, a service system which shows linked video clips from the static images extracted from newspapers, magazines, photo albums and etc in an augmented reality. First, the system uses SURF algorithm to extract features from the original photos printed in the media and stores them with the linked video clips. Next, when a photo is taken by using a camera from mobile devices such as smart phones, the system extracts features in real time, search a linked video clip matching the original image, and shows it on the smart phone in an augmented reality. The proposed system is applied to Android smart phone devices and the test results verify that the proposed system operates not only on normal photos but also on partially damaged photos.