• Journal of the Korean Geographical Society
• /
• v.36 no.5
• /
• pp.561-577
• /
• 2001

Urban spatial structure is closely related to the spatial distribution of urban economic activities. The spatial distribution pattern is no more than an aggregated expression of the location and/or relocation behavior of individual firms and establishments. In this respect, it is important to identify and examine the factors that affect the spatial behavior of individual firms for a more comprehensive understanding of urban space. Agglomeration economies are one of the most prominent urban economic phenomena in the modern metropolitan area. Most firms in an urban space seek external economies through the spatial clustering of their activities. Agglomeration economies feature prominently in the analysis of urban economic structure across urban areas. While the agglomeration economies between cities focus at the macro-scale of analysis, such economies within any given city focus more on the micro geographical scale. There have been a number of researches on agglomeration economies, among which there are relatively few approaches based on an intra-urban context. This proper explores the agglomeration economies at the micro scale and tries to reseal the spatial realization of the agglomeration economies within and between sectors. Three sectors are considered in the analysis; manufacturing, retail and service. The model is based on simultaneous equation systems combined with spatially weighted variables and estimated by the KRP estimators.

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.89-106
• /
• 2022

Recently, the amount of video data collected from smartphones, CCTVs, black boxes, and high-definition cameras has increased rapidly. According to the increasing video data, the requirements for analysis and utilization are increasing. Due to the lack of skilled manpower to analyze videos in many industries, machine learning and artificial intelligence are actively used to assist manpower. In this situation, the demand for various computer vision technologies such as object detection and tracking, action detection, emotion detection, and Re-ID also increased rapidly. However, the object detection and tracking technology has many difficulties that degrade performance, such as re-appearance after the object's departure from the video recording location, and occlusion. Accordingly, action and emotion detection models based on object detection and tracking models also have difficulties in extracting data for each object. In addition, deep learning architectures consist of various models suffer from performance degradation due to bottlenects and lack of optimization. In this study, we propose an video analysis system consists of YOLOv5 based DeepSORT object tracking model, SlowFast based action recognition model, Torchreid based Re-ID model, and AWS Rekognition which is emotion recognition service. Proposed model uses single-linkage hierarchical clustering based Re-ID and some processing method which maximize hardware throughput. It has higher accuracy than the performance of the re-identification model using simple metrics, near real-time processing performance, and prevents tracking failure due to object departure and re-emergence, occlusion, etc. By continuously linking the action and facial emotion detection results of each object to the same object, it is possible to efficiently analyze videos. The re-identification model extracts a feature vector from the bounding box of object image detected by the object tracking model for each frame, and applies the single-linkage hierarchical clustering from the past frame using the extracted feature vectors to identify the same object that failed to track. Through the above process, it is possible to re-track the same object that has failed to tracking in the case of re-appearance or occlusion after leaving the video location. As a result, action and facial emotion detection results of the newly recognized object due to the tracking fails can be linked to those of the object that appeared in the past. On the other hand, as a way to improve processing performance, we introduce Bounding Box Queue by Object and Feature Queue method that can reduce RAM memory requirements while maximizing GPU memory throughput. Also we introduce the IoF(Intersection over Face) algorithm that allows facial emotion recognized through AWS Rekognition to be linked with object tracking information. The academic significance of this study is that the two-stage re-identification model can have real-time performance even in a high-cost environment that performs action and facial emotion detection according to processing techniques without reducing the accuracy by using simple metrics to achieve real-time performance. The practical implication of this study is that in various industrial fields that require action and facial emotion detection but have many difficulties due to the fails in object tracking can analyze videos effectively through proposed model. Proposed model which has high accuracy of retrace and processing performance can be used in various fields such as intelligent monitoring, observation services and behavioral or psychological analysis services where the integration of tracking information and extracted metadata creates greate industrial and business value. In the future, in order to measure the object tracking performance more precisely, there is a need to conduct an experiment using the MOT Challenge dataset, which is data used by many international conferences. We will investigate the problem that the IoF algorithm cannot solve to develop an additional complementary algorithm. In addition, we plan to conduct additional research to apply this model to various fields' dataset related to intelligent video analysis.

• The Journal of the Petrological Society of Korea
• /
• v.19 no.2
• /
• pp.109-121
• /
• 2010

Mt. Mudeung is located in Gwangju city, Damyang-Gun, Hwasun-Gun and its round form give us the mood of soft and rich. Its location is $126^{\circ}06'-127^{\circ}01'E$ and $35^{\circ}06'-35^{\circ}10'N$ and its highest peak is Cheonwang-bong with the height of 1,187 m. The Gwangju city is located in the West of Mt. Mudeng and the mountain range with a small basin in its East. The pavilion such as the Soswaewon, Songganjeong, Sigyongjeong are distributed along the stream in the north of Mt. Mudeung. The mountain is formed from the volcanic activity, Gwangju cauldron during the Cretaceous. The top part of Mt. Mudeung is composed of dark gray quartz-andesite and its K-Ar whole rock age is $48.1{\pm}1.7Ma$. The composition of the north area, where the Wonhyosa temple is located, is micrographic granite, whereas the composition of south area is rhyolite mainly. The main ridge of Mt. Mudeung runs from North, starting from the Bukbong, to south, passing Cheonwangbong, Jangbuljae and ending Anyangsan. Geologic feature of the mountain includes volcanic landform, mountaineous landform, and stream landform. The Seosukdae, Ipseokdae, Gyubongam, which are main ridges and formed from volcanic activity, are composed of mainly columnar joint. Saeinbong and Majipbong in the south-west are composed of mainly cliff and dome. The typical erosion landform of the mountain has three different types of the weathering-cave, each of which reflect the property of the original rock. Four different area of wide block stream, they makes the geological feature of spring-water, though its scale is small compared to that of water fall.

• Korean Journal of Ichthyology
• /
• v.32 no.3
• /
• pp.117-129
• /
• 2020

The body color pattern in fish is a distinctive feature for species identification. The blass bloched rockfish Sebastes pachycephalus is a commercially important marine fish species, distributed in the central and southern parts of Korea and south Hokkaido of Japan. It has a morphological feature divided into four subspecies according to with or lacking distinct spots on the body surface, and to the location of markings on the body surface. However, the genetic basis of body color pattern of S. pachycephalus is still unknown. Thus we analyzed the transcriptome of S. pachycephalus skin samples using RNA-seq analysis to investigate functional genes related to body color patterns. The experimental skin samples were prepared by classified into 'Wild type' (lacking distinct spots and markings) and 'Color type' (with distinct spots and marking). Two skin sample transcriptomes were compared pairwise and the results revealed that were 164 differentially expressed unigenes in the skin samples of 'Wild type' and 'Color type'. Gene Ontology analysis of 164 differentially expressed unigenes showed that these genes were included in the functional group of molecular function (2 genes), biological process (46 genes), and cellular component (6 genes). There were several genes that body color type skin specific expression and the genes were CTL (Galactose-specific lectin nattectin), CUL1 (Cullin-1), CMAS (N-acylneuraminate cytidylyltransferase), NMRK2 (Nicotinamide riboside kinase 2), ALOXE3 (Hydroperoxide isomerase ALOXE3), SLC4A7 (sodium bicarbonate cotransporter 3). Our study is the first attempt to search for functional genes involved in the formation of body color patterns in S. pachycephalus. The differentially expressed unigenes obtained in this study can be used as candidate genes for functional gene study related to body coloration of fish.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.3 no.4
• /
• pp.59-88
• /
• 2008

For the success of the DMB market to meet consumers' demands for Ubiquitous Media and strengthen the nation's competitiveness, it's inevitable for us to activate DMB advertising as of main profit source for DMB Media, and to develop various types of DMB advertising which are linked to the profit model. So I'd like to look over the various types of DMB advertising which are suitable for DMB features as one of the efforts to activate DMB advertising. First of all, I've figured out what kinds of advertising are available for new media and which related technologies are required for DMB media. Through this research, I could find out what features of new media such as cable broadcasting, Internet and Mobile have become the source of developing various types of advertising and how to a great part to activate new media advertising markets by making the best use of their media features. This research also shows that DMB advertising has the high potential to be developed in various and effective types and kinds of advertising with its media feature and technological feature. This research observing DMB advertising cases showed that DMB advertising can be divided into 6 types such as forms, purposes, techniques, advertising positions, the use of LBS(Location Based Service), coupons and it could be developed into various kinds of DMB advertising dependent on each type. On the other hands, it would be great to have continual researches and follow-ups for various types of DMB advertising and the verification of the effectiveness for DMB advertising by performing potential DMB advertising.

• Journal of Korea Water Resources Association
• /
• v.41 no.7
• /
• pp.701-709
• /
• 2008

Surface Image Velocimetry (SIV) is an instrument to measure water surface velocity by using image processing techniques. It gives us one of the easiest ways to measure water velocity. However, since it requires a set of plane survey data to estimate the velocity, it may give us some kind of misconcept that its usage would be difficult or cumbersome in spite of its handiness. If it has a feature that can estimate the plane survey data easily, it may be treated as like one of the conventional propeller velocimetries and its applicability would be improved so high. The present study is to propose a method to estimate the plane geometry of the physical coordinate with a calibrated camera. With the feature we can half-automatize the estimating procedure for the whole water velocity field. Photogrammetric technique to calculate the plane coordinates of the reference points with a calibrated camera was studied, which has originally studied for long time in the field of computer vision. By applying this technique to SIV, it is possible to estimate the location of reference coordinates for projective transform without plane survey. With this procedure the cumbersome plane survey for the reference points is omitted. One example application of the developed method showed fairly good results with insignificant errors.

• Korean Journal of Remote Sensing
• /
• v.27 no.1
• /
• pp.33-41
• /
• 2011

In the information communication technology, it is world-widely apparent that trend movement from internet web to smartphone app by users demand and developers environment. So it needs kinds of appropriate technological responses from geo-spatial domain regarding this trend. However, most cases in the smartphone app are the map service and location recognition service, and uses of geo-spatial contents are somewhat on the limited level or on the prototype developing stage. In this study, app for extraction of corner point features using geo-spatial imagery and their linkage to database system are developed. Corner extraction is based on Harris algorithm, and all processing modules in database server, application server, and client interface composing app are designed and implemented based on open source. Extracted corner points are applied LOD(Level of Details) process to optimize on display panel. Additional useful function is provided that geo-spatial imagery can be superimposed with the digital map in the same area. It is expected that this app can be utilized to automatic establishment of POI (Point of Interests) or point-based land change detection purposes.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.8
• /
• pp.187-195
• /
• 2013

Most of former studies for car license plate detection restrict the image acquisition environment. The aim of this research is to diminish the restrictions by proposing a new method of using SIFT and neural network. SIFT can be used in diverse situations with less restriction because it provides size- and rotation-invariance and large discriminating power. SIFT extracted from the license plate image is divided into the internal(inside class) and the external(outside class) ones and the classifier is trained using them. In the proposed method, by just putting the various types of license plates, the trained neural network classifier can process all of the types. Although the classification performance is not high, the inside class appears densely over the plate region and sparsely over the non-plate regions. These characteristics create a local feature map, from which we can identify the location with the global maximum value as a candidate of license plate region. We collected image database with much less restriction than the conventional researches. The experiment and evaluation were done using this database. In terms of classification accuracy of SIFT keypoints, the correct recognition rate was 97.1%. The precision rate was 62.0% and recall rate was 50.2%. In terms of license plate detection rate, the correct recognition rate was 98.6%.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.8 no.5
• /
• pp.159-166
• /
• 2008

Recently, according to the rapid development of location positioning technology and wireless communications technology and increasement of usage of moving object data, many researches and developments on the real-time locating systems which provides real time service of moving object data stream are under proceeding. However, MO (Moving Object) DBMS used based system in the in these systems is the inefficient management of moving object data streams, and the existing DSMS (Data Stream Management System) has problems that spatio-temporal data are not handled efficiently. Therefore, in this thesis, we designed and implemented spatio-temporal DSMS for efficient real-time management of moving object data stream. This thesis implemented spatio-temporal DSMS based STREAM (STanford stREam dAta Manager) of Stanford University is supporting real-time management of moving object data stream and spatio-temproal query processing and filtering for reduce the input loading. Specifically, spatio-temporal operators of the spatio-temporal DSMS support standard interface of SQL form which extended "Simple Feature Specification for SQL" standard specifications presented by OGC for compatibility. Finally, implemented spatio-temporal DSMS in this thesis, proved the effectiveness of the system that as applied real-time monitoring areas that require real-time locating of object data stream DSMS.

• 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.