• The KIPS Transactions:PartB
• /
• v.14B no.4
• /
• pp.311-320
• /
• 2007

This paper presents vision-based 3D facial expression animation technique and system which provide the robust 3D head pose estimation and real-time facial expression control. Many researches of 3D face animation have been done for the facial expression control itself rather than focusing on 3D head motion tracking. However, the head motion tracking is one of critical issues to be solved for developing realistic facial animation. In this research, we developed an integrated animation system that includes 3D head motion tracking and facial expression control at the same time. The proposed system consists of three major phases: face detection, 3D head motion tracking, and facial expression control. For face detection, with the non-parametric HT skin color model and template matching, we can detect the facial region efficiently from video frame. For 3D head motion tracking, we exploit the cylindrical head model that is projected to the initial head motion template. Given an initial reference template of the face image and the corresponding head motion, the cylindrical head model is created and the foil head motion is traced based on the optical flow method. For the facial expression cloning we utilize the feature-based method, The major facial feature points are detected by the geometry of information of the face with template matching and traced by optical flow. Since the locations of varying feature points are composed of head motion and facial expression information, the animation parameters which describe the variation of the facial features are acquired from geometrically transformed frontal head pose image. Finally, the facial expression cloning is done by two fitting process. The control points of the 3D model are varied applying the animation parameters to the face model, and the non-feature points around the control points are changed by use of Radial Basis Function(RBF). From the experiment, we can prove that the developed vision-based animation system can create realistic facial animation with robust head pose estimation and facial variation from input video image.

• Journal of the Korean Wood Science and Technology
• /
• v.2 no.2
• /
• pp.22-24
• /
• 1974

1. Object and importance of the research. The exports of plywood are increasing annually and it has ranked first in the world market because of the high quality product developed and manufactured using modern techniques. However, it is known that the exports of the other wood products, except plywood, is inactive because of their low quality. Accordingly, to increase the exports of various wood products investigations were carried out on kiln drying techniques to improve the quality of the wood. 2. The details and scope of the research Wet wood should be kiln dried before use to prevent various drying defects such as distortion, shrinkage etc, which would develop after processing, and also wet wood is not suitable for cutting, gluing and finishing. Therefore, the kiln drying properties of lumber from such species as Persimmon, Oak, Ramin and Meranti which are used in large quantity for manufacturing exporting wood products have been studied. Also the real state of kiln drying industry in Korea was investigated. 3. Results and proposal for practical use of the research 3. 1 Results of the research 3.1.1 The end checks and the time for drying from intial moisture content of about 40 percent to 5 percent moisture content in ovendry were investigated as Table 1. 3.1.2 The kiln dried results, for 30mm stock, which are presented by using kiln schedule Table 2 are as Table 3. 3.1.3 The kiln schedule for Persimmon which has a normal drying properties is given in Table 4. However, the persimmon which has easy checking properties should be air dried under a relative humidity of above 85% until reaching about 25 percent moisture content. 3.1.4 The kiln schedules for ramin, meranti and oak are given respectively as follows. Ramin kiln schedule ............ Table 5 and Table 6 Meranti kiln schedule ............ Table 7 Oak kiln schedule ............ Table 8 3.2 Proposal for practical use of the research Firms using the above species should be informed the results of the research so they can be used to preventing drying defects and shortening drying time.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.6 no.2
• /
• pp.71-84
• /
• 2004

There is a growing demand for agrometeorological information that end-users can use and not just interesting information. lo achieve this, each region/community needs to develop and provide localized climate and weather information for growers. Additionally, provide tools to help local users interpret climate forecasts issued by the National Weather Service in the country. Real time information should be provided for farmers, including some basic data. An ideal agrometeorological information system includes several components: an efficient data measuring and collection system; a modern telecommunication system; a standard data management processing and analysis system; and an advanced technological information dissemination system. While it is conventional wisdom that, Internet is and will play a major role in the delivery and dissemination of agrometeorological information, there are large gaps between the "information rich" and the "information poor" countries. Rural communities represent the "last mile of connectivity". For some time to come, TV broadcast, radio, phone, newspaper and fax will be used in many countries for communication. The differences in achieving this among countries arise from the human and financial resources available to implement this information and the methods of information dissemination. These differences must be considered in designing any information dissemination system. Experience shows that easy across to information more tailored to user needs would substantially increase use of climate information. Opportunities remain unexplored for applications of geographical information systems and remote sensing in agro meteorology.e sensing in agro meteorology.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.33 no.6
• /
• pp.265-274
• /
• 2021

Outlier detection research in ocean data has traditionally been performed using statistical and distance-based machine learning algorithms. Recently, AI-based methods have received a lot of attention and so-called supervised learning methods that require classification information for data are mainly used. This supervised learning method requires a lot of time and costs because classification information (label) must be manually designated for all data required for learning. In this study, an autoencoder based on unsupervised learning was applied as an outlier detection to overcome this problem. For the experiment, two experiments were designed: one is univariate learning, in which only SST data was used among the observation data of Deokjeok Island and the other is multivariate learning, in which SST, air temperature, wind direction, wind speed, air pressure, and humidity were used. Period of data is 25 years from 1996 to 2020, and a pre-processing considering the characteristics of ocean data was applied to the data. An outlier detection of actual SST data was tried with a learned univariate and multivariate autoencoder. We tried to detect outliers in real SST data using trained univariate and multivariate autoencoders. To compare model performance, various outlier detection methods were applied to synthetic data with artificially inserted errors. As a result of quantitatively evaluating the performance of these methods, the multivariate/univariate accuracy was about 96%/91%, respectively, indicating that the multivariate autoencoder had better outlier detection performance. Outlier detection using an unsupervised learning-based autoencoder is expected to be used in various ways in that it can reduce subjective classification errors and cost and time required for data labeling.

• Geophysics and Geophysical Exploration
• /
• v.8 no.4
• /
• pp.270-279
• /
• 2005

Under the research project supported by Japanese Ministry of Education, Culture, Sports, Science and Technology (MEXT), we have conducted the development of GPR systems for landmine detection. Until 2005, we have finished development of two prototype GPR systems, namely ALIS (Advanced Landmine Imaging System) and SAR-GPR (Synthetic Aperture Radar-Ground Penetrating Radar). ALIS is a novel landmine detection sensor system combined with a metal detector and GPR. This is a hand-held equipment, which has a sensor position tracking system, and can visualize the sensor output in real time. In order to achieve the sensor tracking system, ALIS needs only one CCD camera attached on the sensor handle. The CCD image is superimposed with the GPR and metal detector signal, and the detection and identification of buried targets is quite easy and reliable. Field evaluation test of ALIS was conducted in December 2004 in Afghanistan, and we demonstrated that it can detect buried antipersonnel landmines, and can also discriminate metal fragments from landmines. SAR-GPR (Synthetic Aperture Radar-Ground Penetrating Radar) is a machine mounted sensor system composed of B GPR and a metal detector. The GPR employs an array antenna for advanced signal processing for better subsurface imaging. SAR-GPR combined with synthetic aperture radar algorithm, can suppress clutter and can image buried objects in strongly inhomogeneous material. SAR-GPR is a stepped frequency radar system, whose RF component is a newly developed compact vector network analyzers. The size of the system is 30cm x 30cm x 30 cm, composed from six Vivaldi antennas and three vector network analyzers. The weight of the system is 17 kg, and it can be mounted on a robotic arm on a small unmanned vehicle. The field test of this system was carried out in March 2005 in Japan.

• Investigative Magnetic Resonance Imaging
• /
• v.16 no.1
• /
• pp.67-75
• /
• 2012

Purpose : We studied enhanced method to view the vessels in the brain using Magnetic Resonance Angiography (MRA). Noticing that Maximum Intensity Projection (MIP) image is often used to evaluate the arteries of the neck and brain, we propose a new method for view brain vessels to stereo image in 3D space with more superior and more correct compared with conventional method. Materials and Methods: We use 3T Siemens Tim Trio MRI scanner with 4 channel head coil and get a 3D MRA brain data by fixing volunteers head and radiating Phase Contrast pulse sequence. MRA brain data is 3D rotated according to the view angle of each eyes. Optimal view angle (projection angle) is determined by the distance between eye and center of the data. Newly acquired MRA data are projected along with the projection line and display only the highest values. Each left and right view MIP image is integrated through anaglyph imaging method and optimal stereoscopic MIP image is acquired. Results: Result image shows that proposed method let enable to view MIP image at any direction of MRA data that is impossible to the conventional method. Moreover, considering disparity and distance from viewer to center of MRA data at spherical coordinates, we can get more realistic stereo image. In conclusion, we can get optimal stereoscopic images according to the position that viewers want to see and distance between viewer and MRA data. Conclusion: Proposed method overcome problems of conventional method that shows only specific projected image (z-axis projection) and give optimal depth information by converting mono MIP image to stereoscopic image considering viewers position. And can display any view of MRA data at spherical coordinates. If the optimization algorithm and parallel processing is applied, it may give useful medical information for diagnosis and treatment planning in real-time.

• KIPS Transactions on Computer and Communication Systems
• /
• v.4 no.6
• /
• pp.185-196
• /
• 2015

Energy aware server clusters aim to reduce power consumption at maximum while keeping QoS(Quality of Service) compared to energy non-aware server clusters. They adjust the power mode of each server in a fixed or variable time interval to let only the minimum number of servers needed to handle current user requests ON. Previous studies on energy aware server cluster put efforts to reduce power consumption further or to keep QoS, but they do not consider energy efficiency well. In this paper, we propose an energy efficient cluster management based on autonomous learning for energy aware server clusters. Using parameters optimized through autonomous learning, our method adjusts server power mode to achieve maximum performance with respect to power consumption. Our method repeats the following procedure for adjusting the power modes of servers. Firstly, according to the current load and traffic pattern, it classifies current workload pattern type in a predetermined way. Secondly, it searches learning table to check whether learning has been performed for the classified workload pattern type in the past. If yes, it uses the already-stored parameters. Otherwise, it performs learning for the classified workload pattern type to find the best parameters in terms of energy efficiency and stores the optimized parameters. Thirdly, it adjusts server power mode with the parameters. We implemented the proposed method and performed experiments with a cluster of 16 servers using three different kinds of load patterns. Experimental results show that the proposed method is better than the existing methods in terms of energy efficiency: the numbers of good response per unit power consumed in the proposed method are 99.8%, 107.5% and 141.8% of those in the existing static method, 102.0%, 107.0% and 106.8% of those in the existing prediction method for banking load pattern, real load pattern, and virtual load pattern, respectively.

• Korean Security Journal
• /
• no.33
• /
• pp.103-135
• /
• 2012

The object is that this research searches the relationship of the office given condition actual condition of the country important facility private security guard and job satisfaction degree. In order to grasp and analyze the real state of the country important facility private security guards directly, the questionnaire, that is the general measurement tool, was utilized and the guard whom it works in the airport, the port region and general work place, that is the national important facility of Busan and Ulsan area, was aimed at. The enough survey object was illustrated to the facility and person in charge in the security company and the item was previewed and the total 400 sheets was distributed and 331 sheets (82.8%) except the doubleness subject intention and incongruent questionnaire was utilized for the analysis. The statistic processing of collected data utilized the SPSS version 15.0 the statistical package program through data coding and cleaning process and performed the frequency analysis, reliability analysis, t-test, one way analysis of variance, Pearson analysis, and regression analysis. The relationship of the office given condition actual condition of the guard about the national important facility and job satisfaction degree was classified into the interpersonal relationship, task characteristic, office environment, and complement factor and the difference of the job satisfaction degree according to the general characteristic was verified. If the conclusion obtained through the method of study described in the above looked at, for as to general tendency, the low wages and poor field environment was continued. In the general characteristic, the man was higher than the excitation about the job satisfaction level. As there was lots of the age and the scholarship was low, the age was high. And as there was lots of the career and income, the police of a petition or search and guide staff was high and the job satisfaction degree in which relatively the employee and the other job group is high so that the case of being the former student incidence can be the poorest was shown rather than the facility security agent. As the interrelation analysis result job satisfaction was high, the change of occupation pseudo was low and the organizational commitment degrees was increased. The regression analysis result job satisfaction degree was exposed to reach the meaningful effect on the change of occupation pseudo and organizational commitment. It had an effect on the change of occupation pseudo as the task characteristic and office ambient level was low. It had an effect on the organizational commitment as the extend of satisfaction about the task characteristic and interpersonal relationship, complement, and office ambient level were high. If the research result of this time is integrated, the support of the political system including the interpersonal relationship thesis between top and bottom of the organized I and substantial complement actualization is urgently needed between the office given condition improvement effort in the country important facility defense manpower field and police of a petition and special guard.

• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.39-70
• /
• 2017

Data-drive analytics techniques have been recently applied to public surveys. Instead of simply gathering survey results or expert opinions to research the preference for a recently launched product, enterprises need a way to collect and analyze various types of online data and then accurately figure out customer preferences. In the main concept of existing data-based survey methods, the sentiment lexicon for a particular domain is first constructed by domain experts who usually judge the positive, neutral, or negative meanings of the frequently used words from the collected text documents. In order to research the preference for a particular product, the existing approach collects (1) review posts, which are related to the product, from several product review web sites; (2) extracts sentences (or phrases) in the collection after the pre-processing step such as stemming and removal of stop words is performed; (3) classifies the polarity (either positive or negative sense) of each sentence (or phrase) based on the sentiment lexicon; and (4) estimates the positive and negative ratios of the product by dividing the total numbers of the positive and negative sentences (or phrases) by the total number of the sentences (or phrases) in the collection. Furthermore, the existing approach automatically finds important sentences (or phrases) including the positive and negative meaning to/against the product. As a motivated example, given a product like Sonata made by Hyundai Motors, customers often want to see the summary note including what positive points are in the 'car design' aspect as well as what negative points are in thesame aspect. They also want to gain more useful information regarding other aspects such as 'car quality', 'car performance', and 'car service.' Such an information will enable customers to make good choice when they attempt to purchase brand-new vehicles. In addition, automobile makers will be able to figure out the preference and positive/negative points for new models on market. In the near future, the weak points of the models will be improved by the sentiment analysis. For this, the existing approach computes the sentiment score of each sentence (or phrase) and then selects top-k sentences (or phrases) with the highest positive and negative scores. However, the existing approach has several shortcomings and is limited to apply to real applications. The main disadvantages of the existing approach is as follows: (1) The main aspects (e.g., car design, quality, performance, and service) to a product (e.g., Hyundai Sonata) are not considered. Through the sentiment analysis without considering aspects, as a result, the summary note including the positive and negative ratios of the product and top-k sentences (or phrases) with the highest sentiment scores in the entire corpus is just reported to customers and car makers. This approach is not enough and main aspects of the target product need to be considered in the sentiment analysis. (2) In general, since the same word has different meanings across different domains, the sentiment lexicon which is proper to each domain needs to be constructed. The efficient way to construct the sentiment lexicon per domain is required because the sentiment lexicon construction is labor intensive and time consuming. To address the above problems, in this article, we propose a novel product reputation mining algorithm that (1) extracts topics hidden in review documents written by customers; (2) mines main aspects based on the extracted topics; (3) measures the positive and negative ratios of the product using the aspects; and (4) presents the digest in which a few important sentences with the positive and negative meanings are listed in each aspect. Unlike the existing approach, using hidden topics makes experts construct the sentimental lexicon easily and quickly. Furthermore, reinforcing topic semantics, we can improve the accuracy of the product reputation mining algorithms more largely than that of the existing approach. In the experiments, we collected large review documents to the domestic vehicles such as K5, SM5, and Avante; measured the positive and negative ratios of the three cars; showed top-k positive and negative summaries per aspect; and conducted statistical analysis. Our experimental results clearly show the effectiveness of the proposed method, compared with the existing method.

• Korean Journal of Remote Sensing
• /
• v.32 no.2
• /
• pp.119-131
• /
• 2016

Descriptions are provided of the automated aerosol-type classification and mass concentration calculation algorithm for real-time data processing and aerosol products in Korea Aerosol Lidar Observation Network (KALION, http://www.kalion.kr). The KALION algorithm provides aerosol-cloud classification and three aerosol types (clean continental, dust, and polluted continental/urban pollution aerosols). It also generates vertically resolved distributions of aerosol extinction coefficient and mass concentration. An extinction-to-backscatter ratio (lidar ratio) of 63.31 sr and aerosol mass extinction efficiency of $3.36m^2g^{-1}$ ($1.39m^2g^{-1}$ for dust), determined from co-located sky radiometer and $PM_{10}$ mass concentration measurements in Seoul from June 2006 to December 2015, are deployed in the algorithm. To assess the robustness of the algorithm, we investigate the pollution and dust events in Seoul on 28-30 March, 2015. The aerosol-type identification, especially for dust particles, is agreed with the official Asian dust report by Korean Meteorological Administration. The lidar-derived mass concentrations also well match with $PM_{10}$ mass concentrations. Mean bias difference between $PM_{10}$ and lidar-derived mass concentrations estimated from June 2006 to December 2015 in Seoul is about $3{\mu}g\;m^{-3}$. Lidar ratio and aerosol mass extinction efficiency for each aerosol types will be developed and implemented into the KALION algorithm. More products, such as ice and water-droplet cloud discrimination, cloud base height, and boundary layer height will be produced by the KALION algorithm.