• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.744-746
• /
• 2003

A 3D modeling of urban area can be composed the terrain modeling that can express specific and shape of the terrain and the object modeling such as buildings, trees and facilities which are found in urban areas. Especially in a 3D modeling of building, it is very important to make a unit model by simplifying 3D structure and to take a texture mapping, which can help visualize surface information. In this study, the texture mapping technique, based on library for 3D urban modeling, was used for building modeling. This technique applies the texture map in the form of library which is constructed as building types, and then take mapping to the 3D building frame. For effectively apply, this technique, we classified buildings automatically using LiDAR data and made 3D frame using LiDAR and digital map. To express the realistic building texture, we made the texture library using real building photograph.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.39 no.6
• /
• pp.696-708
• /
• 2002

In this paper, a novel transcoding algorithm for the Adaptive Multi Rate(AMR) and the Enhanced Variable Rate Codec(EVRC) vocoders via direct parameter transformation is proposed. In contrast to the conventional tandem transcoding algorithm, the proposed algorithm converts the parameters of one coder to the other without going through the decoding and encoding processes. The proposed algorithm consists of the parameter decoding, frame classification, mode decision, and transcoders for two frame types. The transcoders convert the parameters such as LSP, frame energy, pitch delay for the adaptive codebook, fixed codebook vector, and codebook gains. Evaluation results show that while exhibiting better computational and delay characteristics, the proposed algorithm produces equivalent speech quality to that produced by the tandem transcoding algorithm.

• Journal of Fashion Business
• /
• v.15 no.5
• /
• pp.195-219
• /
• 2011

The purpose of the study is to analyze Hollywood actresses' makeup in formative characteristics and see the transition of the change for the usage as the fundamental materials to develop the future makeup field academy with the focus focused from 1920s to 2000s when the cosmetic industry began in earnest. The content of the study is to see the transition of the change by analyzing makeup of each era in formative aspect after seeing the transition of the makeup change in the social background by classifying by 10 years from 1920s to 2000s with related literature as the center in the theoretical background. The method of the study is to analyze makeup in formative aspect with total 180 pieces of pictures selected by two experts among their photos by selecting four actresses by each era and analyze Hollywood actresses' advertisement pictures which can be called as beauty icons at that time. Analysis frame to analyze the formativeness established new classification frame based on theories of Marian L. Davis, Marilyn Revell Delong, and Kang to analyze line, shape, texture, and decoration, and researcher's analysis frame was prepared based Munsell's color circle, tone analysis of P.C.C.S color system, and Kang's makeup color name to analyze colors. The result of the study is like below. Generally 20s and 30s highlighted line of eyebrows, 40s naturalness, 50s and 60s highlighted eye makeup, and from 70s makeup was focused on health, in 80s colorful makeup was boom, and 90s and 2000s has shown characteristics focused on texture of face.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.7
• /
• pp.190-200
• /
• 2014

The video-based system of the broadcasters and the video-related institutions have shifted from analogical to digital in worldwide. This migration process can generate a defect, digital dropout, in the quality of the contents. Moreover, there are limited researches focused on these kind of defects and those related have limitations. For that reason, we are proposing a new method for feature extraction emphasizing in the peculiar block pattern of digital dropout based on discrete cosine transform (DCT). For classification of error block, we utilize support vector machine (SVM) which can manage feature vectors efficiently. Further, the proposed method overcome the limitation of the previous one using continuity of frame by frame. It is using only the information of a single frame and works better even in the presence of fast moving objects, without the necessity of specific model or parameter estimation. Therefore, this approach is capable of detecting digital dropout only with minimal complexity.

• 한국정보교육학회:학술대회논문집
• /
• 2021.08a
• /
• pp.411-418
• /
• 2021

In this study, in order to analyze the AI convergence education courses of 38 graduate schools of education, the analysis frame was constructed in terms of basic subject classification, content field of subject, and detailed subject composition by field. And as a result of analysis through this frame, it was found that the number of subjects currently operated by these graduate schools of education is very different from 14 subjects to 48 subjects. Therefore, it was judged that it was urgent to develop a standard curriculum for the AI convergence education major operated by each graduate school of education for the same purpose. The AI Convergence Education Major, which was established for the same purpose and operated in different forms, will eventually produce teachers with different competencies, so there is a risk of bringing confusion to the direction of AI Convergence Education in the school field.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.14 no.4
• /
• pp.897-905
• /
• 1994

Project Informations Classification System (PICS) can be utilized as a springboard for advanced construction management techniques because it marries informations to networks and maintains a disciplined cost control. The present study attempts to develop a PICS which can be applied in construction management techniques. The frame work largely consists of the three parts such as: (i) development of the tentative Work Breakdown Structure with three divisions, facility calssifications, functional classifications and work classifications, covering the whole areas of civil works, (ii) development of the integrated informations system including the other informations in cost estimating and network scheduling, (iii) construction of relational database system for computer application. The system suggested in the study is found useful for the systematic and uniform management of construction works in the various stages.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.8
• /
• pp.9-16
• /
• 2018

In this paper, a kidnapping detection scheme in which human pose estimation is used to classify accurately between kidnapping cases and normal ones is proposed. To estimate human poses from input video, human's 10 joint information is extracted by OpenPose library. In addition to the features which are used in the previous study to represent the size change rates and the regularities of human activities, the human pose estimation features which are computed from the location of detected human's joints are used as the features to distinguish kidnapping situations from the normal accompanying ones. A frame-based kidnapping detection scheme is generated according to the selection of J48 decision tree model from the comparison of several representative classification models. When a video has more frames of kidnapping situation than the threshold ratio after two people meet in the video, the proposed scheme detects and notifies the occurrence of kidnapping event. To check the feasibility of the proposed scheme, the detection accuracy of our newly proposed scheme is compared with that of the previous scheme. According to the experiment results, the proposed scheme could detect kidnapping situations more 4.73% correctly than the previous scheme.

• Journal of KIISE:Software and Applications
• /
• v.31 no.11
• /
• pp.1534-1542
• /
• 2004

A novel vision-based scheme of extracting real-time traffic information parameters is presented. The method is based on a region classification followed by a spatio-temporal image analysis. The detection region images for each traffic lane are classified into one of the three categories: the road, the vehicle, and the shadow, using statistical and structural features. Misclassification in a frame is corrected by using temporally correlated features of vehicles in the spatio-temporal image. Since only local images of detection regions are processed, the real-time operation of more than 30 frames per second is realized without using dedicated parallel processors, while ensuring detection performance robust to the variation of weather conditions, shadows, and traffic load.

• Journal of Information Processing Systems
• /
• v.18 no.5
• /
• pp.677-687
• /
• 2022

We propose a detection algorithm based on tree-structured convolutional neural networks (TsCNNs) that finds pornography, propaganda, or other inappropriate content on a social media network. The algorithm sequentially applies the typical convolutional neural network (CNN) algorithm in a tree-like structure to minimize classification errors in similar classes, and thus improves accuracy. We implemented the detection system and conducted experiments on a data set comprised of 6 ordinary classes and 11 inappropriate classes collected from the Korean military social network. Each model of the proposed algorithm was trained, and the performance was then evaluated according to the images and videos identified. Experimental results with 20,005 new images showed that the overall accuracy in image identification achieved a high-performance level of 99.51%, and the effectiveness of the algorithm reduced identification errors by the typical CNN algorithm by 64.87 %. By reducing false alarms in video identification from the domain, the TsCNNs achieved optimal performance of 98.11% when using 10 minutes frame-sampling intervals. This indicates that classification through proper sampling contributes to the reduction of computational burden and false alarms.

• The Journal of the Acoustical Society of Korea
• /
• v.30 no.3
• /
• pp.149-157
• /
• 2011

In this paper, we propose a new cardiac disorder classification method using an support vector machine (SVM) to combine hidden Markov model (HMM) and murmur existence information. Using cepstral features and the HMM Viterbi algorithm, we segment input heart sound signals into HMM states for each cardiac disorder model and compute log-likelihood (score) for every state in the model. To exploit the temporal position characteristics of murmur signals, we divide the input signals into two subbands and compute murmur probability of every subband of each frame, and obtain the murmur score for each state by using the state segmentation information obtained from the Viterbi algorithm. With an input vector containing the HMM state scores and the murmur scores for all cardiac disorder models, SVM finally decides the cardiac disorder category. In cardiac disorder classification experimental results, the proposed method shows the relatively improvement rate of 20.4 % compared to the HMM-based classifier with the conventional cepstral features.