• Journal of Broadcast Engineering
• /
• v.26 no.5
• /
• pp.519-532
• /
• 2021

Recently, in various fields such as games, movies, and animation, content that uses motion capture to build body models and create characters to express in 3D space is increasing. Studies are underway to generate animations using RGB-D cameras to compensate for problems such as the cost of cinematography in how to place joints by attaching markers, but the problem of pose estimation accuracy or equipment cost still exists. Therefore, in this paper, we propose a system that inputs RGB images into a joint estimation network and converts the results into 3D data to create FBX format animations in order to reduce the equipment cost required for animation creation and increase joint estimation accuracy. First, the two-dimensional joint is estimated for the RGB image, and the three-dimensional coordinates of the joint are estimated using this value. The result is converted to a quaternion, rotated, and an animation in FBX format is created. To measure the accuracy of the proposed method, the system operation was verified by comparing the error between the animation generated based on the 3D position of the marker by attaching a marker to the body and the animation generated by the proposed system.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.37 no.4
• /
• pp.243-251
• /
• 2019

The road sign location information installed on national roads is continuously updated using MMS (Mobile Mapping System) technology. It is possible to map accurate road facilities by MMS, but the equipment is very expensive and requires specialized technology. Also, the accuracy of the position of the object greatly depends on the GPS (Global Positioning System) accuracy. In the case of road facility mapping, the advantage of drone is more remarkable than that of field survey or conventional aerial photogrammetry. In particular, it is more efficient than field surveying and it is possible to acquire high resolution images with low budget compared to conventional aerial photogrammetry. In this study, the accuracy of the location information measured by the existing MMS is compared with the GPS survey result and the accuracy analysis is performed by the drone aerial photogrammetry. In order to confirm the space accuracy that can be obtained when conducting drone aerial photogrammetry, the accuracy of the change in the number of ground control points and the degree of overlap was evaluated. As a result of the experiment, it was possible to obtain sufficient accuracy with two ground control points distributed at both ends of the road and 60% overlap.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.24 no.4
• /
• pp.341-353
• /
• 2022

Pipelines are buried in urban area, and the position (depth and orientation) of buried pipeline should be clearly identified before ground excavation. Although various geophysical methods can be used to detect the buried pipeline, it is not easy to identify the exact information of pipeline due to heterogeneous ground condition. Among various non-destructive geo-exploration methods, ground penetration radar (GPR) can explore the ground subsurface rapidly with relatively low cost compared to other exploration methods. However, the exploration data obtained from GPR requires considerable experiences because interpretation is not intuitive. Recently, researches on automated detection technology for GPR data using deep learning have been conducted. However, the lack of GPR data which is essential for training makes it difficult to build up the reliable detection model. To overcome this problem, we conducted a preliminary study to improve the performance of the detection model using finite difference time domain (FDTD)-based numerical analysis. Firstly, numerical analysis was performed with homogeneous soil media having single permittivity. In case of heterogeneous ground, numerical analysis was performed considering the ground heterogeneity using fractal technique. Secondly, deep learning was carried out using convolutional neural network. Detection Model-A is trained with data set obtained from homogeneous ground. And, detection Model-B is trained with data set obtained from homogeneous ground and heterogeneous ground. As a result, it is found that the detection Model-B which is trained including heterogeneous ground shows better performance than detection Model-A. It indicates the ground heterogeneity should be considered to increase the performance of automated detection model for GPR exploration.

• Journal of Digital Contents Society
• /
• v.15 no.6
• /
• pp.663-673
• /
• 2014

The WBAN technology means a short distance wireless network which provides each device interactive communication by connecting devices inside and outside of body. Standardization on the physical layer, data link layer, network layer and application layer is in progress by IEEE 802.15.6 TG BAN. Wireless body area network is usually configured in energy efficient using sensor and zigbee device due to the power limitation and the characteristics of human body. Wireless sensor network consist of sensor field and sink node. Sensor field are composed a lot of sensor node and sink node collect sensing data. Wireless sensor network has capacity of the self constitution by protocol where placed in large area without fixed position. In this paper, we proposed the efficient addressing scheme for improving the performance of routing algorithm by using ZigBee in WBAN environment. A distributed address allocation scheme used an existing algorithm that has wasted in address space. Therefore proposing x, y and z coordinate axes from divided address space of 16 bit to solve this problems. Each node was reduced not only bitwise but also multi hop using the coordinate axes while routing than Cskip algorithm. I compared the performance between the standard and the proposed mechanism through the numerical analysis. Simulation verified performance about decrease averaging multi hop count that compare proposing algorithm and another. The numerical analysis results show that proposed algorithm reduced the multi hop better than ZigBee distributed address assignment

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.6B
• /
• pp.551-560
• /
• 2009

This paper describes a newly developed pollutant transport model named ARPTM which was designed to simulate the transport and characteristics of pollutant materials after an accidental spill in upstream of river system up to a given position in the downstream. In particular, the ARPTM incorporated ADCP data to compute longitudinal dispersion coefficient and advection velocity which are necessary to apply one-dimensional advection-dispersion equation. ARPTM was built on top of the geographic information system platforms to take advantage of the technology's capabilities to track geo-referenced processes and visualize the simulated results in conjunction with associated geographic layers such as digital maps. The ARPTM computes travel distance, time, and concentration of the pollutant cloud in the given flow path from the river network, after quickly finding path between the spill of the pollutant material and any concerned points in the downstream. ARPTM is closely connected with a recently developed GIS-based Arc River database that stores inputs and outputs of ARPTM. ARPTM thereby assembles measurements, modeling, and cyberinfrastructure components to create a useful cyber-tool for determining and visualizing the dynamics of the clouds of pollutants while dispersing in space and time. ARPTM is expected to be potentially used for building warning system for the transport of pollutant materials in a large basin.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.6
• /
• pp.173-182
• /
• 2012

A recent advance in smart phones is increasing utilization of location information. Existing positioning system was using GPS location for positioning. However, the GPS cannot be used indoors, if GPS location has an incorrectly problem. In order to solve indoor positioning problems of indoor location-based positioning techniques have been investigated. There are a variety of techniques based on indoor positioning techniques like as RFID, UWB, WLAN, etc. But WLAN location positioning techniques take advantage the bond in real life. WLAN indoor positioning techniques have a two kind of method that is centroid and fingerprint method. Among them, the fingerprint technique is commonly used because of the high accuracy. In order to use fingerprinting techniques make a WLAN signal map building that is need to lot of resource. In this paper, we try to solve this problem in an Indoor environment for WLAN-based fingerprint of a virtual building technique, which is proposed. Proposed technique is classified Cell environment in existed Indoor environment, all of fingerprint points are shown virtual grid map in each Cell. Its method can make fingerprint grid map very quickly using estimate virtual signal value. Also built signal value can take different value depending of the real estimate value. To solve this problem using a calibration technique for the Splite-tree is proposed. Through calibration technique that improves the accuracy for short period of time. It also is improved overall accuracy using predicted value of around position in cell.

• Journal of Intelligence and Information Systems
• /
• v.22 no.4
• /
• pp.177-192
• /
• 2016

Machine learning is a field of artificial intelligence. It refers to an area of computer science related to providing machines the ability to perform their own data analysis, decision making and forecasting. For example, one of the representative machine learning models is artificial neural network, which is a statistical learning algorithm inspired by the neural network structure of biology. In addition, there are other machine learning models such as decision tree model, naive bayes model and SVM(support vector machine) model. Among the machine learning models, we use SVM model in this study because it is mainly used for classification and regression analysis that fits well to our study. The core principle of SVM is to find a reasonable hyperplane that distinguishes different group in the data space. Given information about the data in any two groups, the SVM model judges to which group the new data belongs based on the hyperplane obtained from the given data set. Thus, the more the amount of meaningful data, the better the machine learning ability. In recent years, many financial experts have focused on machine learning, seeing the possibility of combining with machine learning and the financial field where vast amounts of financial data exist. Machine learning techniques have been proved to be powerful in describing the non-stationary and chaotic stock price dynamics. A lot of researches have been successfully conducted on forecasting of stock prices using machine learning algorithms. Recently, financial companies have begun to provide Robo-Advisor service, a compound word of Robot and Advisor, which can perform various financial tasks through advanced algorithms using rapidly changing huge amount of data. Robo-Adviser's main task is to advise the investors about the investor's personal investment propensity and to provide the service to manage the portfolio automatically. In this study, we propose a method of forecasting the Korean volatility index, VKOSPI, using the SVM model, which is one of the machine learning methods, and applying it to real option trading to increase the trading performance. VKOSPI is a measure of the future volatility of the KOSPI 200 index based on KOSPI 200 index option prices. VKOSPI is similar to the VIX index, which is based on S&P 500 option price in the United States. The Korea Exchange(KRX) calculates and announce the real-time VKOSPI index. VKOSPI is the same as the usual volatility and affects the option prices. The direction of VKOSPI and option prices show positive relation regardless of the option type (call and put options with various striking prices). If the volatility increases, all of the call and put option premium increases because the probability of the option's exercise possibility increases. The investor can know the rising value of the option price with respect to the volatility rising value in real time through Vega, a Black-Scholes's measurement index of an option's sensitivity to changes in the volatility. Therefore, accurate forecasting of VKOSPI movements is one of the important factors that can generate profit in option trading. In this study, we verified through real option data that the accurate forecast of VKOSPI is able to make a big profit in real option trading. To the best of our knowledge, there have been no studies on the idea of predicting the direction of VKOSPI based on machine learning and introducing the idea of applying it to actual option trading. In this study predicted daily VKOSPI changes through SVM model and then made intraday option strangle position, which gives profit as option prices reduce, only when VKOSPI is expected to decline during daytime. We analyzed the results and tested whether it is applicable to real option trading based on SVM's prediction. The results showed the prediction accuracy of VKOSPI was 57.83% on average, and the number of position entry times was 43.2 times, which is less than half of the benchmark (100 times). A small number of trading is an indicator of trading efficiency. In addition, the experiment proved that the trading performance was significantly higher than the benchmark.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.6
• /
• pp.749-754
• /
• 2011

In this study, we propose the design of optimized pRBFNNs-based face recognition system using two-dimensional Image and ASM algorithm. usually the existing 2 dimensional face recognition methods have the effects of the scale change of the image, position variation or the backgrounds of an image. In this paper, the face region information obtained from the detected face region is used for the compensation of these defects. In this paper, we use a CCD camera to obtain a picture frame directly. By using histogram equalization method, we can partially enhance the distorted image influenced by natural as well as artificial illumination. AdaBoost algorithm is used for the detection of face image between face and non-face image area. We can butt up personal profile by extracting the both face contour and shape using ASM(Active Shape Model) and then reduce dimension of image data using PCA. The proposed pRBFNNs consists of three functional modules such as the condition part, the conclusion part, and the inference part. In the condition part of fuzzy rules, input space is partitioned with Fuzzy C-Means clustering. In the conclusion part of rules, the connection weight of RBFNNs is represented as three kinds of polynomials such as constant, linear, and quadratic. The essential design parameters (including learning rate, momentum coefficient and fuzzification coefficient) of the networks are optimized by means of Differential Evolution. The proposed pRBFNNs are applied to real-time face image database and then demonstrated from viewpoint of the output performance and recognition rate.

• Journal of Families and Better Life
• /
• v.28 no.1
• /
• pp.131-143
• /
• 2010

The purpose of this study is to understand the living culture of transnational married women and to analyze the out door play of children in their hometown. The data was collected through observation from 27th June to 7th July 2008 in Jian, Jilin Province China. The children's play and lifestyles were observed, and data pertaining to the culture of the people were collected by a teacher and staff. We also visited the residents for housing information. The results are given below. 1. They dressed in Korean clothes on festive days and the boys put on a hood. They had eating habits which included cooking for themselves or buying semi-manufactured goods but did not use, instant food. The housing habits involved a combination of cooking and heating by Korean floor heating system(Ondol). They utilized outdoor space to grow vegetables. Those with a fulltime job(teacher) preferred to live in an apartment but an apartment was too expensive. Public utility charges and traffic expenses were cheap. 2. The main festive days are the lunar New Year's Day and Chuseok. The children returned home and enjoyed the festive day with their parents. The language used are Korean language and Chinese. Some Korean words and phrases in Jian Joseonjok have different meanings as compared to how they are used in Korea. A capping ceremony did not to celebrate becoming an adult from an adolescent. Couples performed a wedding ceremony at a wedding hall attended by their parents and invited relatives from both families. The relatives gave the couple a wedding gift. They did not go on a wedding trip as it was not affordable but instead spent their wedding night at a hotel in this culture. When someone dies, they bury the body after cremation. They perform a memorial service for three years on the birthday of the departed. They have a banquet on the 60th birthdays with their relatives and neighbours and are typically presented with a carp for longevity. 3. They understand capitalism and therefore send their children to school to improve their social position. The Korean and Chinese languages are required subjects in school. The students choose a second language(English or Russian). They prefer English class but at the time of this study an English class was not offered at the school in Jian Joseonjok. Therefore the children entered a Chinese school. 4. The children play outdoor games such as Y$\acute{a}$o J$\grave{i}\bar{a}$(要家), X$\grave{i}$ang g$\grave{i}$(象棋), T$\grave{i}\grave{a}$o p$\acute{i}$ j$\grave{i}$n(r)(跳皮節), D$\grave{o}$uch ing g$\grave{u}$n 凍冷根, B$\bar{e}$i B$\bar{e}$i 背背, and soccer. They play games according to the season.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.19 no.1
• /
• pp.95-107
• /
• 2017

In this study, a preliminary study was undertaken for development of a tunnel incident automatic detection system based on a machine learning algorithm which is to detect a number of incidents taking place in tunnel in real time and also to be able to identify the type of incident. Two road sites where CCTVs are operating have been selected and a part of CCTV images are treated to produce sets of training data. The data sets are composed of position and time information of moving objects on CCTV screen which are extracted by initially detecting and tracking of incoming objects into CCTV screen by using a conventional image processing technique available in this study. And the data sets are matched with 6 categories of events such as lane change, stoping, etc which are also involved in the training data sets. The training data are learnt by a resilience neural network where two hidden layers are applied and 9 architectural models are set up for parametric studies, from which the architectural model, 300(first hidden layer)-150(second hidden layer) is found to be optimum in highest accuracy with respect to training data as well as testing data not used for training. From this study, it was shown that the highly variable and complex traffic and incident features could be well identified without any definition of feature regulation by using a concept of machine learning. In addition, detection capability and accuracy of the machine learning based system will be automatically enhanced as much as big data of CCTV images in tunnel becomes rich.