초음파 영상에서의 Optical Flow 추적 성능 향상을 위한 전처리 알고리즘 개발 연구

김성민(Sung-Min Kim),이주환(Ju-Hwan Lee),노승규(Seung-Gyu Roh),박성윤(Sung-Yun Park) 大韓電子工學會 2010 電子工學會論文誌-SC (System and control) Vol.47 No.5

본 연구에서는 Optical Flow Method의 추적 성능을 향상시키기 위한 전처리 알고리즘을 제안한다. 제안하는 알고리즘은 Median Filter, Binarization, Morphology, Canny Edge, Contour Detecting 및 Approximation Method를 기반으로 개발되었다. Optical Flow 추적 성능 향상 여부를 평가하기 위해 Lucas-Kanade Optical Flow 알고리즘에 개발된 전처리 알고리즘을 적용하고, 전처리 알고리즘이 적용되지 않은 Optical Flow 영상과 추적 결과를 비교 · 분석하였다. 또한, Median Filter와 Histogram Equalization으로 구성된 기존 전처리 알고리즘과의 결과 비교를 통해, 개발된 전처리 알고리즘의 추적 성능 향상여부를 평가하였다. 실험결과, 전처리 알고리즘을 적용하지 않은 영상과 기존 전처리 알고리즘을 적용한 영상은 특징영역의 분할이 이루어지지 않아, Optical Flow의 추적 정확도가 매우 낮게 나타났다. 반면, 개발된 전처리 알고리즘을 적용한 영상에서는 외곽선이 내외부로 세분화되고, 외곽선 트리가 구성됨에 따라 Optical Flow의 추적 성능이 매우 높게 나타났다. In this study, we have proposed a pre-processing algorithm newly developed for improving the tracking efficiency of the optical flow method. The developed pre-processing algorithm consists of a median filter, binarization, morphology, canny edge, contour detecting and an approximation method. In order to evaluate whether the optical flow tracking capacity increases, this study applied the pre-processing algorithm to the Lucas-Kanade(LK) optical flow algorithm, and comparatively analyzed its images and tracking results with those of optical flow without the pre-processing algorithm and with the existing pre-processing algorithm(composed of median filter and histogram equalization). As a result, it was observed that the tracking performance derived from the LK optical flow algorithm with the pre-processing algorithm, shows better tracking accuracy, compared to the one without the pre-processing algorithm and the one with the existing pre-processing algorithm. It seems to have resulted by successful segmentation for characteristic areas and subdivision into inner and outer contour lines.

고품질 빅데이터 분석을 위한 최적의 전처리 순열 추천 방법

김성현(Seounghyun Kim),서영균(Young-Kyoon Suh),탁병철(Byungchul Tak) Korean Institute of Information Scientists and Eng 2020 정보과학회논문지 Vol.47 No.3

Today, due to the explosive increase in data, intelligent service research through big data analysis has been actively conducted in various domains. Pre-processing of training data is essential to big data analytics via data mining or machine learning. Although incomplete and inadequate pre-processing for a given dataset can result in unreliable analysis, it is challenging for users to choose the optimal set and sequence of pre-processing functions that leads to the best results. To address this problem, we have designed and implemented a pre-processing evaluation platform that can analyze the performance of a various permutation of pre-processing functions for a given user dataset and then recommend the best permutation. Evaluation results using the real-world dataset demonstrates that the recommended pre-processing permutation yields the best performance in terms of accuracy when compared to the worst pre-processing permutation. By applying the method proposed in this paper, users can choose the best preprocessing permutation, thus being expected to obtain high-quality big data analysis results.

Pre-biz 프로세스를 적용한 제품디자인사례 연구

김한성 ( Han Sung Kim ) 커뮤니케이션디자인학회(구 시각디자인학회) 2011 커뮤니케이션 디자인학연구 Vol.37 No.-

Per-biz는 광주대학교 광주·전남문화 관광상품디자인혁신센터 (이하TIDIC2)에서 실행하고 있는 디자인 중심 비즈니스모델로써 빠른 기술의 발전과 다양한 변화에 대응하기 위해 개발한 비즈니스모델이다. Per-biz는 Digital/VR3 기술을 활용하여 바이어와 상담 및 소비자의 의견수렴 후 양산개발에 착수하므로 기업의 위험부담을 최소화하고, 개발상품의 상품성과 시장진입시기를 최적화하는 등 중소/벤처기업형 비즈니스모델로 개발되었다. 본 논문은 광주대학교 TIDIC의 디자인개발프로젝트 중 Per-biz의 개념이 적용된 다섯 가지 사례를 통해 디자인개발에 있어 Per-biz방식의 효용과 그 가능성에 대해서 증명하고자 한다 다음의 사례들은 Per-biz가 시도 되었던 주체와 대상에 따라 분류하였다. 사례1 수전금구디자인: 수전 생산자와 완성품생산자 (건설사)를 위한 Per-biz 디자인개발사례 사례2: 관람석디자인: 제품생산자, 발주자 (지자체) 및 투자자를 위한 디자인개발사례 사례3 의료기기디자인: 제품생산자와 투자자를 위한 Per-biz디자인개발사례 사례4: 수전금구디자인: 디자이너와 생산자간의 Per-biz디자인개발사례 사례5: 의료기기디자인 디자이너와 생산자간의 Per-biz디자인개발사례위에 나열된 사례들을 통해 알 수 있듯이 디자인 개발결과를 활용한 Per-biz형태가 매우 다양했으며 그 역할은 중요하고 효과적이었다. 그 중에는 사례가 사례를 도모하는 경우도 있어 기업들의 디자인을 통한 Per-biz의 효용과 수요증가가 가속화되고 있다. 최근 전반적으로 경기가 어려워 디자이너 및 디자인전문회사가 어려움을 겪는 것으로 알고 있다. 여기에 언급된 사례들이 입증하듯이 앞으로 Per-biz의 효용이 강조되고 수요가 증가 함으로서 디자인개발에 대한 수요와 범위가 확장되어 디자인사업 활성화에 도움이 되기 바란다. Pre-biz is a business model developed for coping with rapid develoment of technology and various changes of design oriented business model which is performed in the Tourism Industry Design Innovation Center (It is called as "TIDIC" hereinafter.) of Gwangju University. The Pre-biz was developed for a business model of small and medium/venture company to minimize the risk taking of the company and to optimize the product nature of the developed product and market entry timing because the mass production is started after the consulting with buyers and collection of the opinions from consumers utilizing the digital/VR techology, This thesis proved the effect and possibility of the Pre-biz model in design development through five cases with application of the Pre-biz concept out of the design development projects in TIDIC of Gwangju University. The following cases were classified depending on the subjects and objects which were tried for Pre-biz. Case 1: Faucet design: Pre-biz design development case for the faucet producer and finished product producer (Construction company) Case 2: Viewing seat design: Pre-biz design development case for the producer, ordering party (Local government) and investor. Case 3: Medical instrument design: Pre-biz design development case for the producer and investor. Case 4: Faucet design: Pre-biz design development case between designer and producer. Case 5: Medical instrument design: Pre-biz design development case between designer and producer. As it was known for the cases lited in the above, the type of Pre-biz utilizing the design development result was varied and its role was important and effective. The use and demand increase of the Pre-biz have been accelerated through the company design because there are cases of mutual promoting between the cases. It is true that the designers and design specialized companies have been in difficulties because of the recent general economic recession. As it was proved by the cases mention here, we hope the design business activation owing to extension of the demand and scope of the design development from emphasizing the effect and increasing the demand of the Pre-biz.

HACP2 : The Pre-processing Software Tool for the Hybrid Atomistic-Continuum Coupling Simulation

Qian Wang,Wenjing Yang,Fu Li,Xiaoguang Ren,Yuhua Tang 보안공학연구지원센터 2016 International Journal of Hybrid Information Techno Vol.9 No.1

Fluid simulation is an important application of High Performance Computing. The hybrid atomistic-continuum coupling fluid simulation can effectively handle the contradictory of the reduction of the simulation scale and the increase of the computation load when trying to improve the accuracy. The pre-processing procedure of the coupling simulation is quite important in the whole simulation process and requires the support of an efficient, user-friendly interface. Under the demand of efficient coupling fluid simulation, in this paper we design and implement a visualized pre-processing framework HACP2 based on SALOME, for the unified molecular dynamic-computational fluid dynamics modeling and apply it into the coupling simulation process. The experimental verification indicates that our HACP2 framework can offer efficient, easy-to-use pre-processing for the hybrid atomistic-continuum coupling simulation, and effectively improve the efficiency of the coupling simulation.

建築開發 프로젝트 企劃과정에서의 地理情報시스템 分析 활용에 관한 사례 연구

동재욱,고인룡,이화룡 대한건축학회 2006 대한건축학회논문집 Vol.22 No.9

As the size and complexity of architectural development projects are increasing, the developing business plays a leading role in the domestic construction industry. Only deals most existing project feasibility analysis with financial aspect excluding qualitative elements such as social, cultural values of architecture, which cannot be easily measured. This study views a pre-design process as a series of conscious actions for eliminating the misfits between an existing situation and project goals, using knowledge and experience; that is, a conscious problem-solving process or one of information-processing. It reviews information needed in the process and the characteristics of information-processing in the pre-design step, throughout the case study of a architectural development project. This study asserts the characteristics of this information-processing as a series of uncertain, idiosyncratic and recurring processes, therefor this process cannot be explained by an algorithmic problem-solving process model, but by heuristic strategies that the experience or a rule of thumb can be mainly used. In this view, this study proposes the GIS(Geographic Information System) analysis method as means of a heuristic strategy in order to get more rational decision-making in the feasibility analysis problem space. Finally this study insists on the positive participation and concern of the professional design practice and architectural design research on the feasibility analysis of architectural development project.

Pre-Processing 방법에 따른 얼굴인식 성능 비교

김형복,심귀보 제어로봇시스템학회 2009 제어로봇시스템학회 국내학술대회 논문집 Vol.2009 No.9

This paper is a comparative study of three methods for pre-processing: fast lightning correction, high-pass filter, and histogram equalization. In this paper, we compare performance of face recognition based on PCA/LDA by pre-processing method. Algorithms based on PCA(Principal Components Analysis) and LDA(Linear Discriminant Analysis) are among the most popular appearance-based approaches in face recognition. PCA is recognized as an optimal method th perform dimension reduction. PCA is used as a preprocessing step for dimensionality reduction so as to discard null space of the within-class scatter matrix of the training data set. Then LDA is performed in the lower dimension PCA subspace. Results indicate that the performance of face recognition by histogram equalization method for pre-processing is overall superior those of other methods.

객체 분할 전처리 및 CNN을 이용한 너트 도금 불량 판별

김현태,성은산,마르셀,박장식 국방기술품질원 2020 국방품질연구논집 Vol.2 No.2

It is required to apply computer vision instead of human visual decision in the final stage of production automation. In this paper, we propose a pre-processing of deep learning to improve the classification performance of plating defective nuts, which are representative mechanical parts. The proposed pre-processing algorithm improves classification performance by separating the nut, which is an object, from background in the camera image of the inspection system so that the background image does not affect to train deep learning. The pre-processing algorithm generates a mask image by processing sequentially binarization, edge detection, mathematical morphology filtering and 2D connectivity, and performs masking on the input image to segment the object from the background. It is selected VGG-16 among the widely used deep learning models to train with the proposed segmentation pre-processing in consideration of computational burden and accuracy. As simulation results, it is shown that the proposed pre-processing can be effectively applied to classify plating defective nuts.

예비교사의 과정중심 평가 역량 개발을 위한 프로젝트 기반 학습의 활용

권혁일 국제문화기술진흥원 2023 The Journal of the Convergence on Culture Technolo Vol.9 No.5

As the basic approach of national curriculum shifted from contents-based to competency-based, process-fortified assessment has been stressed. Accordingly, the focus of teacher’s role as an evaluator changed to process-fortified assessment, which emphasizes the development of process-fortified assessment competency of pre-service teachers as well. This study aims to explore the effects of innovations of teacher development programs on pre-service teachers’ process-fortified assessment competency. To achieve this goal, C University of Education implemented a course which was restructured by using PBL, and analyzed its effects on enrolled pre-service teachers in terms of process-fortified assessment. By systematically analyzing data of observation notes, project outputs, and opinion reports, it was found that PBL approach to the course restructuring had positive impacts on pre-service teachers’ awareness and understanding about process-fortified assessment. This implies that providing learning experience reflected by process-fortified assessment perspective, like PBL, can play an important role to the development of process-fortified assessment competency of pre-service teachers. The results of this study are expected to be able to provide methods of innovating curriculum and instruction for developing process-fortified assessment competencies of teacher development institutions.

그래픽 사용자 인터페이스 기반 항공자력탐사 전처리 S/W, KMagLevellingTM

고광범 ( Kwang Beom Ko ),정상원 ( Sang Won Jung ) 한국지구물리·물리탐사학회 2014 지구물리와 물리탐사 Vol.17 No.3

항공자력탐사의 전처리(pre-processing)는 육상탐사에 비해 손품이 많이 들어가는 복잡한 과정이 더 많아 그래픽사용자 인터페이스 기반의 전용 처리도구를 이용하는 것이 가장 효율적이다. 본 글에서는 항공자력자료의 전처리 전용 소프트웨어, KMagLevellingTM을 개발하고 그 주요 기능을 간략히 소개하였다. KMagLevellingTM은 전처리 과정을 크게 세부분으로 구분하여 구현하였다. 세부기능별 사용자 인터페이스 중 편의성과 독창성 측면에서 주목할 만한 기능으로서는① 방대한 양의 항공자력자료 D/B를 비행경로 형태로 시각화하여 표현하는 기법 ② 취합자료 중 특정 영역의 필요한 자료만의 발췌 ③ 자력자료 내의 원치 않는 부분을 선택적으로 쉽게 제거하는 사용자 인터페이스의 세 가지로 요약된다. Aeromagnetic survey generally require much more pre-processing steps than that of common land survey due to several complex and cumbersome steps included in pre-processing stage. Therefore it is desirable to use specific processing tool especially based on graphic user interface. For this purpose, aeromagnetic pre-processing software based on graphic user interface under the Windows environment, called KMagLevellingTM was developed and briefly introduced. In an aspect of its user-friendliness and originality, three noticeable features of KMagLevellingTM are summarized as the following ① function of representation and handling for large amount of aeromagnetic data set as a visualization in the form of flight-path ② function of selective exclusion of unwanted data by using survey area information expressed as polygon, and ③ function of selective removal processing for the irregular flight-path data acquired within the entire survey area by implementing the segmentation of flight-path technique.

Effect of data pre-processing on the performance and robustness of prediction model for distillation column

최영렬,권혁원,이예찬,박현도,문일,조형태,김정환 한국공업화학회 2020 한국공업화학회 연구논문 초록집 Vol.2020 No.-

Though the performance of the predictive model depends on how accurate and how much information data have, the raw process data has low information by including noise, outliers, and defects. Therefore, it is necessary to conduct appropriate data pre-processing to improve the performance of the precess data-driven predictive model. In this study, we suggested two outlier detection and one noise filtering for data pre-processing and applied each method with various ranges on the raw process data of the distillation column. Then we evaluated the effect of the pre-processing on the LSTM-based model performance. The statistical methods were used for performance evaluation, and each predictive model was conducted thirty times to confirm the performance and robustness. As an effect on applying the data preprocessing, we found that the model showed more robust prediction results, and the accuracy and precision were increased by 26.16% and 5.26%, respectively.