• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.313-315
• /
• 2024

본 논문에서는 이미지 검색기를 통한 랜드마크 인식 방법을 제안한다. 특정 랜드마크 데이터세트에서 라벨링을 하지 않은 비지도 학습을 통해서 이미지에서 랜드마크의 클래스 분류를 위한 특징을 추출한다. 학습된 모델을 랜드마크 데이터세트인 Paris6k 데이터세트와 Oxford5k 데이터세트에 적용하여 랜드마크 인식 정확도를 확인하였다. 성능과 속도를 강화하기 위해 이미지 특징 추출 모델로 ResNet 대신에 YOLO에서 사용된 CSPDarknet-53을 사용하여 모델의 크기를 줄이고 랜드마크 인식 정확도를 높였다. 그리고 모델로부터 추출된 특징의 수를 줄여 이미지 검색 시 소요되는 시간을 감소시켰다. 학습된 모델로 rOxford5k 데이터 세트에 적용 시 mAP 80.37, rParis6k에서 mAP 89.07을 얻었다.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.29 no.4
• /
• pp.413-420
• /
• 2011

This study is to extract landmark buildings for pedestrian navigation from the existing spatial data sets automatically. At first, we defined candidates for landmark based on sight of pedestrian, then extracted final landmark by evaluating attributes of each candidate. The attribute is evaluated with relative or absolute criteria depending on the nature of each attribute. Landmarks extracted through the proposed method are compared to existing landmarks for vehicle and assessment of the validity and the applicability is performed. As a result, extracted Landmarks are expected to help guiding pedestrian effectively.

• Archives of design research
• /
• v.16 no.2
• /
• pp.255-270
• /
• 2003

The main goal of this study is to find the role of landmarks in route communication process and to explore the describability of landmarks, a linguistic factor of landmarks that was not noted frequently by previous wayfinding studies. Through analysis of landmarks in this study, the describability of landmarks was identified and this study hypothesized that the describability affects to the whole process of route communication. A virtual reality (VR) simulation test was conducted to examine the effect of the describability of landmarks in route communication. The independent variable was the describability of landmarks and landmarks. As dependent variables, the total time to find final destination and the number of errors were measured. Results showed that the describability of landmarks gives positive effect to the whole of route communication processes. Consequently, this study provides the solution of wayfinding problems in route communication and suggests the usage of landmarks as a prerequisite for planning spaces having the efficiency of wayfinding.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2021.06a
• /
• pp.180-182
• /
• 2021

본 논문은 눈 랜드마크 위치 검출과 시선 방향 벡터 추정이 하나의 딥러닝 네트워크로 통합된 시선 추정 네트워크를 제안한다. 제안하는 네트워크는 Stacked Hourglass Network[1]를 백본(Backbone) 구조로 이용하며, 크게 랜드마크 검출기, 특징 맵 추출기, 시선 방향 추정기라는 세 개의 부분으로 구성되어 있다. 랜드마크 검출기에서는 눈 랜드마크 50개 포인트의 좌표를 추정하며, 특징 맵 추출기에서는 시선 방향 추정을 위한 눈 이미지의 특징 맵을 생성한다. 그리고 시선 방향 추정기에서는 각 출력 결과를 조합하고 이를 통해 최종 시선 방향 벡터를 추정한다. 제안하는 네트워크는 UnityEyes[2] 데이터셋을 통해 생성된 가상의 합성 눈 이미지와 랜드마크 좌표 데이터를 이용하여 학습하였으며, 성능 평가는 실제 사람의 눈 이미지로 구성된 MPIIGaze[3] 데이터 셋을 이용하였다. 실험을 통해 시선 추정 오차는 0.0396 MSE(Mean Square Error)의 성능을 보였으며, 네트워크의 추정 속도는 42 FPS(Frame Per Second)를 나타내었다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.365-366
• /
• 2020

인터넷의 발전으로 인터넷을 통해 미디어 콘텐츠를 제공하는 OTT 서비스의 이용자가 점점 증가하고 있다. 본 논문에서는 OTT 서비스 이용자의 검색 편의성을 위한 Vision API를 활용한 영상 속 랜드마크 검색 시스템을 제안한다. 이는 영상을 시청하는 사용자가 영상을 보다가 궁금한 장소가 있으면 따로 검색하지 않고, 바로 해당 장소의 정보를 얻도록 하는 것이다. 본 논문에서 개발한 영상 속 랜드마크 검색 시스템은 사용자가 원하는 영상을 검색 및 재생할 수 있고 재생 중 바로 화면을 캡처할 수 있다. 해당 캡처 이미지를 랜드마크를 기계 학습한 Vision API를 통해 어떤 랜드마크인지 파악하고 결과를 표시한다, 또한 동일 영상에서 다른 사용자가 검색한 이력이 있는 경우 이력을 표시하여주며, 검색한 랜드마크가 나온 다른 영상을 검색하여 보여준다.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_1
• /
• pp.1309-1320
• /
• 2023

The technological development and popularization of mobile devices have developed so that users can check their location anywhere and use the Internet. However, in the case of indoors, the Internet can be used smoothly, but the global positioning system (GPS) function is difficult to use. There is an increasing need to provide real-time location information in shaded areas where GPS is not received, such as department stores, museums, conference halls, schools, and tunnels, which are indoor public places. Accordingly, research on the recent indoor positioning technology based on light detection and ranging (LiDAR) equipment is increasing to build a landmark database. Focusing on the accessibility of building a landmark database, this study attempted to develop a technique for estimating the user's location by using a single image taken of a landmark based on a mobile device and the landmark database information constructed in advance. First, a landmark database was constructed. In order to estimate the user's location only with the mobile image photographing the landmark, it is essential to detect the landmark from the mobile image, and to acquire the ground coordinates of the points with fixed characteristics from the detected landmark. In the second step, by applying the bag of words (BoW) image search technology, the landmark photographed by the mobile image among the landmark database was searched up to a similar 4th place. In the third step, one of the four candidate landmarks searched through the scale invariant feature transform (SIFT) feature point extraction technique and Homography random sample consensus(RANSAC) was selected, and at this time, filtering was performed once more based on the number of matching points through threshold setting. In the fourth step, the landmark image was projected onto the mobile image through the Homography matrix between the corresponding landmark and the mobile image to detect the area of the landmark and the corner. Finally, the user's location was estimated through the location estimation technique. As a result of analyzing the performance of the technology, the landmark search performance was measured to be about 86%. As a result of comparing the location estimation result with the user's actual ground coordinate, it was confirmed that it had a horizontal location accuracy of about 0.56 m, and it was confirmed that the user's location could be estimated with a mobile image by constructing a landmark database without separate expensive equipment.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.3
• /
• pp.560-570
• /
• 2016

A landmark is a representative image of a given region that impresses distinct regional characteristics upon visitors. As such, there is a need for each local government to develop a symbolic landmark. We investigated examples of landmark development intended to promote regional revitalization in hopes to provide a basic guideline for developing future landmarks, related tourism products, and tourism promotion policy. Aomori prefecture in Japan was selected as a site for a field study. For a long time, Japan has tried to internationalize and revitalize its provincial regions by establishing various tourism policies. In order to foster the tourism industry in rural areas that are behind in development, Aomori prefecture sought to promote local revitalization through the development of tourism products and cultural space centered on a landmark. Based on this example, we can summarize the conditions for successful landmark development as follows. First, in deciding on the symbolism or the design of a landmark, we must fully investigate and understand the given region and invest sufficient time and funds. Second, we must consider the accessibility of the landmark and make sure its surroundings can also serve as a tourist attraction element. Third, in order to increase the value of visiting a landmark, it is important to provide a variety of things to see and enjoy both inside and outside of the landmark, which can be achieved through continuous operation and management of amenities and diverse programs.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.49 no.1
• /
• pp.31-40
• /
• 2012

This paper proposes a visual landmark, and presents a parking assistance system using the landmarks. The visual landmark is a feature corresponding to the parking slots, it must be selected considering the parking lot's environment. The parking lot has simple repetitive pattern environment without noticeable features. The previous landmarks are not proper to the parking lot's environment. We propose the visual landmark for this environment. We estimate the vehicle's location using the proposed landmarks, and expect the vehicle's trajectory according to the vehicle's state. The system's inputs are images from the camera fixed to the vehicle. The presented system estimates the vehicle's location using the input images, and assists a driver through displaying the expected vehicle's trajectory from the steering angle. The experimental results showed the proposed landmark's performance and the parking assistance system's performance.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.11b
• /
• pp.550-552
• /
• 2005

유비쿼터스 환경의 발달과 함께 모바일 장비에서 수집되어지는 컨텍스트 로그를 활용한 연구가 활발히 진행되고 있다. 하지만 기존의 컨텍스트 정보를 사용한 연구는 사용자 모델링에 그 초점을 맞추거나 단순하게 수집된 정보를 정리하여 한눈에 알아보기 쉽게 보여주는 정도에 그치고 있다. 본 논문에서는 사용자에게 새로운 서비스를 제공하기 위한 방법으로서 모바일 컨텍스트 로그와 외부 센서를 통해 정보를 수집하여 학습한 베이지안 네트워크를 이용하여 랜드마크를 찾아내는 예측 모델을 제안한다. 베이지안 네트워크 설계는 사전에 수집된 컨텍스트 정보를 요일과 주별로 분류하여 각각에 대한 베이지안 네트워크를 cross validation하여 랜드마크 예측에 대한 정확도를 평가하였다. 그리고 분류에서 가장 많이 사용하고 있는 SVM 방법을 사용하여 제안한 방법과의 성능을 비교평가하였다. 랜드마크 예측에 대한 정확도는 주간별로 설계한 베이지안 네트워크보다 요일별로 설계한 베이지안 네트워크가 랜드마크를 예측하는데 정화도가 높음을 확인하였고, 베이지안 네트워크를 사용한 방법이 SVM을 사용한 방법보다. 예측에 한 정확성이 우수하였다.

• Journal of the Korean Society for Library and Information Science
• /
• v.54 no.2
• /
• pp.419-434
• /
• 2020

The purpose of the study is to design and propose metadata standard for building AI training dataset of landmark images. In order to achieve the purpose, we first examined and analyzed the state of art of the types of image retrieval systems and their indexing methods, comprehensively. We then investigated open training dataset and machine learning tools for image object recognition. Sequentially, we selected metadata elements optimized for the AI training dataset of landmark images and defined the input data for each element. We then concluded the study with implications and suggestions for the development of application services using the results of the study.