• Journal of Korean Society for Geospatial Information Science
• /
• v.21 no.2
• /
• pp.93-98
• /
• 2013

Multi-temporal high resolution satellite images are essential data for efficient city analysis and monitoring. Yet even when acquired from the same location, identical sensors as well as different sensors, these multi-temporal images have a geometric inconsistency. Matching points between images, therefore, must be extracted to match the images. With images of an urban area, however, it is difficult to extract matching points accurately because buildings, trees, bridges, and other artificial objects cause shadows over a wide area, which have different intensities and directions in multi-temporal images. In this study, we analyze a shadow effect on image matching of high resolution satellite images in urban area using Scale-Invariant Feature Transform(SIFT), the representative matching points extraction method, and automatic shadow extraction method. The shadow segments are extracted using spatial and spectral attributes derived from the image segmentation. Also, we consider information of shadow adjacency with the building edge buffer. SIFT matching points extracted from shadow segments are eliminated from matching point pairs and then image matching is performed. Finally, we evaluate the quality of matching points and image matching results, visually and quantitatively, for the analysis of shadow effect on image matching of high resolution satellite image.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.42 no.1
• /
• pp.117-126
• /
• 2022

Currently, the number of bridge structures in Korea is continuously increasing and enlarged, and the number of old bridges that have been in service for more than 30 years is also steadily increasing. Bridge aging is being treated as a serious social problem not only in Korea but also around the world, and the existing manpower-centered inspection method is revealing its limitations. Recently, various bridge damage detection studies using deep learning-based image processing algorithms have been conducted, but due to the limitations of the bridge damage data set, most of the bridge damage detection studies are mainly limited to one type of crack, which is also based on a close set classification model. As a detection method, when applied to an actual bridge image, a serious misrecognition problem may occur due to input images of an unknown class such as a background or other objects. In this study, five types of bridge damage including crack were defined and a data set was built, trained as a deep learning model, and an open set recognition-based bridge multiple damage recognition model applied with OpenMax algorithm was constructed. And after performing classification and recognition performance evaluation on the open set including untrained images, the results were analyzed.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.4B
• /
• pp.661-674
• /
• 2000

The main memory DBMS(MMDBMS) efficiently supports various database applications that require high performance since it employs main memory rather than disk as a primary storage. In this paper, we discuss theexperiences obtained in developing the index manager of the Tachyon, a next-generation MMDBMS. The indexmanager is an essential sub-component of the DBMS used to speed up the retrieval of objects from a largevolume of a database in response to a certain search condition. Previous research efforts on indexing proposed various index structures. However, they hardly dealt with the practical issues occured in implementating an index manager on a target DBMS. In this paper, we touch these issues and present our experiences in developing the index manager on the Tachyon as solutions. The main issues touched are (1) compact representation of an indexentry, (2) support of variable-length keys, (3) support of multiple-attribute keys, (4) support of duplicated keys,(5) definition of external APls, (6) concurrency control, and (7) backup and recovery. We believe that ourcontribution would help MMDBMS developers highly reduce their trial-and-errors.

• Journal of the Korea Convergence Society
• /
• v.6 no.3
• /
• pp.103-109
• /
• 2015

TOLED(Transparent, Organic Light Emitting Diodes) based edutainment system has been studied to solve the actual feeling training and educational experience problem of e-learning. However, edutainment system using TOLED has a problem for the non-detection of multi marker array and rotate marker array, and it has problem for the dissonance phenomena caused by Illumination Environment between real world and virtual object. It also has a do not provide services through a variety of devices problem. Therefore, in this paper, we designed a system that provides a realistic actual feeling edutainment contents by recognizes the marker array rotation and a plurality of marker arrangement via an improved marker detection technique. And to unify the real space and virtual space of the lighting environment through a nested block layer.

• Korean Journal of Remote Sensing
• /
• v.33 no.6_2
• /
• pp.1075-1087
• /
• 2017

In this study, we tried to utilize results of the change detection analysis for satellite images as the basis for updating the land cover map. The Sequential Spectral Change Vector Analysis ($S^2CVA$) was applied to multi-temporal multispectral satellite imagery in order to extract changed areas, efficiently. Especially, we minimized the false alarm rate of unsupervised change detection due to the seasonal variation using the direction information in $S^2CVA$. The binary image, which is the result of unsupervised change detection, was integrated with the existing land cover map using the zonal statistics. And then, object-based analysis was performed to determine the changed area. In the experiment using PlanetScope data and the land cover map of the Ministry of Environment, the change areas within the existing land cover map could be detected efficiently.

• The KIPS Transactions:PartB
• /
• v.11B no.1
• /
• pp.35-44
• /
• 2004

Web contents created for desktop screens give rise to problems when they are to be displayed on the small screens of mobile terminals. While in some cases some of the objects of a page may not be displayable due to the lack of browser capability, the entire page may not be displayable due to the incompatibility with the browser in other cases. In this paper, we introduce a new mobile content adaptation approach based on web clipping, which transforms an original page into one that is optimally displayed on a mobile terminal. In this method, a source page is automatically clipped and transformed according to the clip specification made by the content provider using a clip editing tool. The clip editing tool allows the user to specify group clips, multi-level cups and dynamic clips as well as simple clips, and the presentation layout through a graphic user interface. Based on the clip specifications, each clip is transformed into an intermediate meta-language document, which in turn is transformed into a presentation page in the target markup language. Transcoding of image objects in major image file formats is also supported.

• Journal of Korea Multimedia Society
• /
• v.7 no.9
• /
• pp.1219-1232
• /
• 2004

Recently, the web sites, such as e-business sites and shopping mall sites, deal with lots of catalog image information and contents. As a result, it is required to support semantic-based image retrieval efficiently on such image data. This paper presents a semantic-based image retrieval system, which adopts XML and Fuzzy technology. To support semantic-based retrieval on product catalog images containing multiple objects, we use a multi-level metadata structure which represents the product information and semantics of image data. To enable semantic-based retrieval on such image data, we design a XML database for storing the proposed metadata and study how to apply fuzzy data. This paper proposes a system, generate the fuzzy data automatically to use the image metadata, that can support semantic-based image retrieval by utilizing the generating fuzzy data. Therefore, it will contribute in improving the retrieval correctness and the user's satisfaction on semantic-based e-catalog image retrieval.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.5
• /
• pp.709-714
• /
• 2018

Visual Reality technology is becoming more and more interesting as it attracts people's interest. VR technology is used in various markets such as games, animation, and education. However, there were many people experiencing motion sickness such as dizziness and headache due to the delay time between hardware such as a device for sending a video after experiencing a VR image and an HMD for reproducing an image. The system proposed in this paper focuses on the environment rather than the movement of the attraction and detects the dividing line existing on the path by the proximity sensor and accurately calculates the position on the path according to the user 's motion. Since the position of the user is synchronized with the VR image, the position error of the user is improved to 0.2%.

• Journal of Korea Multimedia Society
• /
• v.3 no.1
• /
• pp.63-76
• /
• 2000

Most work done in CSCW (Computer Supported Collaborative Work) system has been targeted toward supporting the exchange of documents or messages among group members, and yet support for cognitive aspects such as group organization, division and merge of work, and work flow control. The objective of the study is to provide CSCW environment for the engineering design process such as CAD (Computer Aided Design) and CASE (Computer Aided Software Engineering). The proposed DCWA (Distributed Collaborative Writing Aid) system suggests a mechanism that unifies the group organization, work division, and work flow control in the CAO, CASE, and software simulation tool. In particular, CAD relates the group and work partition by providing expressing the relation of drawing object (e.g., binding, attachment, and proportional scaling) which is owned by different members of group, and CASE combining with the simulation tool supports the flexibility of the work flow control. Simulating the prototype before manu-facturing a product can reduce time and cost in development.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.2
• /
• pp.23-29
• /
• 2014

The advanced traffic management system of intelligent transport systems automates the related traffic tasks such as vehicle speed, traffic volume and traffic incidents through the improved infrastructures like high definition cameras, high-performance radar sensors. For the safety of road users, especially, the automated incident detection and secondary accident prevention system is required. Normally, CCTV based image object detection and radar based object detection is used in this system. In this paper, we proposed the algorithm for real time highway incident detection system using multi surveillance cameras to mosaic video and track accurately the moving object that taken from different angles by background modeling. We confirmed through experiments that the video detection can supplement the short-range shaded area and the long-range detection limit of radar. In addition, the video detection has better classification features in daytime detection excluding the bad weather condition.