• 한국정보통신학회논문지
• /
• 제11권4호
• /
• pp.786-792
• /
• 2007

비디오 감시 시스템에서 물체의 추적은 매우 중요하다. 본 논문에서는 외부 환경에서 움직이는 물체를 추적하는 방법을 제안한다. 움직이는 물체를 추적하기 위하여 먼저 가중치 차 영상을 구하여 움직이는 물체를 추출한 후 다시 닫힘 연산을 사용하여 잡음을 제거한다. 그리고 추출된 다양한 특징 정보로 매칭하여 움직이는 물체를 추적한다. 제안된 추적 방법은 가중치 차 영상을 사용하여 움직이는 물체를 추적하기에 정지된 물체가 갑자기 움직이거나 갑자기 멈출 때도 정확히 추적할 수 있다. 본 논문에서 제안한 추적 시스템은 공간위치, 형상과 명암도 특징을 종합하기에 움직이는 물체를 보다 더 효과적으로 추적할 수 있다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권10호
• /
• pp.3668-3684
• /
• 2021

Video action recognition is widely used in video surveillance, behavior detection, human-computer interaction, medically assisted diagnosis and motion analysis. However, video action recognition can be disturbed by many factors, such as background, illumination and so on. Two-stream convolutional neural network uses the video spatial and temporal models to train separately, and performs fusion at the output end. The multi segment Two-Stream convolutional neural network model trains temporal and spatial information from the video to extract their feature and fuse them, then determine the category of video action. Google Xception model and the transfer learning is adopted in this paper, and the Xception model which trained on ImageNet is used as the initial weight. It greatly overcomes the problem of model underfitting caused by insufficient video behavior dataset, and it can effectively reduce the influence of various factors in the video. This way also greatly improves the accuracy and reduces the training time. What's more, to make up for the shortage of dataset, the kinetics400 dataset was used for pre-training, which greatly improved the accuracy of the model. In this applied research, through continuous efforts, the expected goal is basically achieved, and according to the study and research, the design of the original dual-flow model is improved.

• 한국공간구조학회논문집
• /
• 제21권3호
• /
• pp.43-50
• /
• 2021

A tilted tall building is actively constructed as landmark structures around world to date. Because lateral displacement responses of a tilted tall building occurs even by its self-weight, reduction of seismic responses is very important to ensure structural safety. In this study, a smart tuned mass damper (STMD) was applied to the example tilted tall building and its seismic response control performance was investigated. The STMD was composed of magnetorheological (MR) damper and it was installed on the top floor of the example building. Control performance of the STMD mainly depends on the control algorithn. Fuzzy logic controller (FLC) was selected as a control algorithm for the STMD. Because composing fuzzy rules and tuning membership functions of FLC are difficult task, evolutionary optimization algorithm (EOA) was used to develop the FLC. After numerical simulations, it has been seen that the STMD controlled by the EOA-optimized FLC can effectively reduce seismic responses fo the tilted tall building.

• 한국공간구조학회논문집
• /
• 제21권4호
• /
• pp.49-56
• /
• 2021

This study aims to develop a form-finding algorithm for a single-layered pneumatic membrane. The initial shape of this pneumatic membrane, which is an air-supported type pneumatic membrane, is to find a state in which a given initial tension and internal pneumatic pressure are in equilibrium. The algorithm developed to satisfy these conditions is that a nonlinear optimization problem based on the force method considering the deformed shape is formulated, and, it's able to find the shape by iteratively repeating the process of obtaining a solution of the governing equations. An computational technique based on the Gauss-Newton method was used as a method for obtaining solutions of nonlinear equations. In order to verify the validity of the proposed form-finding algorithm, a single-curvature pneumatic membrane example and a double-curvature air pneumatic membrane example were adopted, respectively. In the results of these examples, it was possible to well observe the step-by-step convergence process of the shape of the pneumatic membrane, and it was also possible to confirm the change in shape according to the air pressure. In addition, the calculation results of the shape and internal force after deformation due to initial tension, air pressure, and self-weight were obtained.

• 한국공간구조학회논문집
• /
• 제23권1호
• /
• pp.25-34
• /
• 2023

This paper presents a computational fluid dynamics (CFD) analysis to investiagate the effect of expansion chamber on overpressure reduction in protective tunnels subjected to detonation of high explosives. A commercial CFD code, Viper::Blast, was used to model the blast waves in a protective tunnel with a length of 160 m, width of 8.9 m and height of 7.2 m. Blast scenarios and simulation matrix were establihsed in consideration of the design parameters of expansion chamber, including the chamber lengths of 6.1 m to 12.1 m, widths of 10.7 m to 97 m, length to width ratios of 0.0 to 5.0, heights of 8.0 m and 14.9 m, and ratios of chamber to tunnel width of 1.2 to 10.9 m. A charge weight of TNT of 1000 kg was used. The mesh sizes of the numerical model of the protective tunnel were determined based on a mesh convergence study. A parametric study based on the simulation matrix was performed using the proposed CFD tunnel model and the optimized shape of expansion chamber of the considered tunnel was then proposed based on the numerical results. Design recommendations for the use of expansion chamber in protective tunnel under blast loads to reduce the internal overpressures were finally provided.

• Advances in Computational Design
• /
• 제8권4호
• /
• pp.327-351
• /
• 2023

This article explores how multi-objective optimization techniques can be used to design cost-effective and structurally optimal spatial steel structures, highlighting that optimizing performance can be as important as minimizing costs in real-world engineering problems. The study includes the minimization of maximum horizontal displacement, the maximization of the first natural frequency of vibration, the maximization of the critical load factor concerning the first global buckling mode of the structure, and weight minimization as the objectives. Additionally, it outlines a systematic approach to selecting the best design by employing four different evolutionary algorithms based on differential evolution and a multi-criteria decision-making methodology. The paper's contribution lies in its comprehensive consideration of multiple conflicting objectives and its novel approach to simultaneous consideration of bracing system, column orientation, and commercial profiles as design variables.

• 한국정보통신학회논문지
• /
• 제21권3호
• /
• pp.629-635
• /
• 2017

본 논문에서는 영상에 첨가된 가우시안 잡음과 임펄스 잡음의 영향을 완화하기 위하여 잡음의 종류에 따라 처리하는 비선형 합성 필터를 제안하였다. 잡음 판단을 통해 국부 마스크의 중심화가 가우시안 잡음으로 판단된 경우, 국부 마스크 내의 표본분산을 이용하여 공간 가중치 필터와 화소 변화에 따른 가중치 필터의 가중치를 다르게 적용하여 처리하고, 임펄스 잡음으로 판단된 경우, 국부 마스크의 잡음 밀도에 따라 국부 히스토그램 가중치 필터와 표준 메디안 필터의 가중치를 다르게 적용하여 처리하는 알고리즘을 제안하였다. 그리고 제안한 필터 알고리즘의 성능을 평가하기 위해 PSNR(peak signal to noise ratio)을 사용하여 기존의 방법들과 제안한 필터 알고리즘을 가우시안 잡음, 임펄스 잡음 및 두 잡음이 혼합된 복합잡음 환경에서 각각 비교하였다.

• 한국농공학회논문집
• /
• 제56권5호
• /
• pp.55-65
• /
• 2014

Radar remote sensing is appropriate for rice monitoring because the areas where this crop is cultivated are often cloudy and rainy. Especially, Synthetic Aperture Radar (SAR) can acquire remote sensing information with a high temporal resolution in tropical and subtropical regions due to its all-weather capability. This paper analyzes the relationships between backscattering coefficients of rice measured by RADARSAT-2 SAR and growth parameters during a rice growth period. And we applied the relationships to crop monitoring of paddy rice in North Korea. As a result, plant height and Leaf Area Index (LAI) increased until Day Of Year (DOY) 234 and then decreased, while fresh weight and dry weight increased until DOY 253. Correlation coefficients revealed that Horizontal transmit and Horizontal receive polarization (HH)-polarization backscattering coefficients were correlated highly with plant height (r=0.95), fresh weight (r=0.92), vegetation water content (r=0.91), LAI (r=0.90), and dry weight (r=0.89). Based on the observed relationships between backscattering coefficients and variables of cultivation, prediction equations were developed using the HH-polarization backscattering coefficients. Concerning the evaluation for the applicability of the LAI distribution from RADARSAT-2, the LAI statistic was evaluated in comparison with LAI distribution from RapidEye image. And LAI distributions in Pyongyang were presented to show spatial variability for unaccessible areas.

• 대한전자공학회논문지SP
• /
• 제43권4호
• /
• pp.1-8
• /
• 2006

본 논문은 엔트로피 기반의 가중치와 클러스터 분포크기를 이용한 향상된 FCM(Fuzzy C-Mean)알고리즘을 제안한다. FCM 알고리즘은 영상분할에서 일반적으로 많이 사용되는 퍼지 클러스터링 방법이다. 그러나 공간정보를 포함하지 않기 때문에 잡음 등에 민감하고, 클러스터를 이루는 특정들의 분포에 따라 화소들을 정확하게 분류할 수 없다. 이러한 단점을 해결하기 위해서 FCM 알고리즘의 소속정도를 연산할 때 클러스터 분포크기와 이웃 화소의 공간정보를 이용한 엔트로피 기반의 가중치를 적용한다. 실험결과에서 제안한 방법이 기존의 방법들보다 잡음에 강건하며 분할결과를 보였다.

• 한국정보통신학회논문지
• /
• 제25권10호
• /
• pp.1310-1316
• /
• 2021

최근 인공지능과 IoT 기술의 발달에 따라 물체 추적, 의료 영상, 객체 인식과 같은 영상처리에 대한 중요성이 높아지고 있다. 특히 전처리 과정에서 사용되는 잡음제거 기술은 시스템에서 영상의 중요성이 높아짐에 따라 잡음을 효율적으로 제거하며 세부적인 특징을 보존하는 성능을 요구하고 있다. 본 논문에서는 AWGN 환경에서 화소매칭 기반의 변형된 가중치 필터를 제안한다. 제안한 알고리즘은 영상에서 화소값이 크게 변하는 고주파성분을 보존하기 위해 화소매칭 기법을 사용하며, 주변 영역에서 연관성이 높은 패턴을 지닌 영역을 검출하여 출력계산에 필요한 매칭 화소값을 분류한다. 최종 출력은 필터링 과정에서 에지성분을 고려하기 위해 중심화소와 매칭화소 사이의 격차값 및 공간적 거리에 따라 가중치를 계산하여 구한다.