• 한국컴퓨터정보학회논문지
• /
• 제23권9호
• /
• pp.1-6
• /
• 2018

In this paper, we propose a method dividing effectively the hand and fingers using general webcam. The method executes 4 times empirically preprocessing one to erase noise. First, it erases the overall noise of the image using Gaussian smoothing. Second, it changes from RGB image to HSV color model and YCbCr color model, executes a global static binarization based on the statistical value for each color model, and erase the noise through bitwise-OR operation. Third, it executes outline approximation and inner region filling algorithm using RDP algorithm and Flood fill algorithm and erase noise. Lastly, it erases noise through morphological operation and determines the threshold propositional to the image size and selects the hand and fingers area. This paper compares to existing one color based hand area division method and focuses the noise deduction and can be used to a gesture recognition application.

• Advances in aircraft and spacecraft science
• /
• 제4권3호
• /
• pp.219-235
• /
• 2017

The large container ships and fast patrol boats are complex marine structures. Therefore, their global mechanical behaviour has long been modeled mostly by refined beam theories. Important issues of cross section warping and bending-torsion coupling have been addressed by introducing special functions in these theories with inherent assumptions and thus compromising their robustness. The 3D solid Finite Element (FE) models, on the other hand, are accurate enough but pose high computational cost. In this work, different marine vessel structures have been analysed using the well-known Carrera Unified Formulation (CUF). According to CUF, the governing equations (and consequently the finite element arrays) are written in terms of fundamental nuclei that do not depend on the problem characteristics and the approximation order. Thus, refined models can be developed in an automatic manner. In the present work, a particular class of 1D CUF models that was initially devised for the analysis of aircraft structures has been employed for the analysis of marine structures. This class, which was called Component-Wise (CW), allows one to model complex 3D features, such as inclined hull walls, floors and girders in the form of components. Realistic ship geometries were used to demonstrate the efficacy of the CUF approach. With the same level of accuracy achieved, 1D CUF beam elements require far less number of Degrees of Freedom (DoFs) compared to a 3D solid FE solution.

• Structural Engineering and Mechanics
• /
• 제69권6호
• /
• pp.615-626
• /
• 2019

The 3-noded metric Timoshenko beam element with an offset of the internal node from the element centre is used here to demonstrate the best-fit paradigm using function space formulation under locking and mesh distortion. The best-fit paradigm follows from the projection theorem describing finite element analysis which shows that the stresses computed by the displacement finite element procedure are the best approximation of the true stresses at an element level as well as global level. In this paper, closed form best-fit solutions are arrived for the 3-noded Timoshenko beam element through function space formulation by combining field consistency requirements and distortion effects for the element modelled in metric Cartesian coordinates. It is demonstrated through projection theorems how lock-free best-fit solutions are arrived even under mesh distortion by using a consistent definition for the shear strain field. It is shown how the field consistency enforced finite element solution differ from the best-fit solution by an extraneous response resulting from an additional spurious force vector. However, it can be observed that when the extraneous forces vanish fortuitously, the field consistent solution coincides with the best-fit strain solution.

• 한국멀티미디어학회논문지
• /
• 제22권1호
• /
• pp.35-43
• /
• 2019

Template tracking refers to the procedure of finding the most similar image patch corresponding to the given template through an image sequence. In order to obtain more accurate trajectory of the template, the template requires to be updated to reflect various appearance changes as it traverses through an image sequence. To do that, appearance images are used to model appearance variations and these are obtained by the computation of the principal components of the augmented image matrix at every iteration. Unfortunately, it is prohibitively expensive to compute the principal components at every iteration. Thus in this paper, we suggest a new Sliding Window based truncated URV Decomposition (TURVD) algorithm which enables updating their structure by recycling their previous decomposition instead of decomposing the image matrix from the beginning. Specifically, we show an efficient algorithm for updating and downdating the TURVD simultaneously, followed by the rank-one update to the TURVD while tracking the decomposition error accurately and adjusting the truncation level adaptively. Experiments show that the proposed algorithm produces no-meaningful differences but much faster execution speed compared to the typical algorithms in template tracking applications, thereby maintaining a good approximation for the principal components.

• Journal of the Korean Physical Society
• /
• 제73권10호
• /
• pp.1589-1595
• /
• 2018

Similarity index measures the topological proximity of node pairs in a complex network. Numerous similarity indices have been defined and investigated, but the dependency of structure on the performance of similarity indices has not been sufficiently investigated. In this study, we investigated the relationship between the performance of similarity indices and structural properties of a network by employing a two-state random network. A node in a two-state network has binary types that are initially given, and a connection probability is determined from the state of the node pair. The performances of similarity indices are affected by the number of links and the ratio of intra-connections to inter-connections. Similarity indices have different characteristics depending on their type. Local indices perform well in small-size networks and do not depend on whether the structure is intra-dominant or inter-dominant. In contrast, global indices perform better in large-size networks, and some such indices do not perform well in an inter-dominant structure. We also found that link prediction performance and the performance of similarity are correlated in both model networks and empirical networks. This relationship implies that link prediction performance can be used as an approximation for the performance of the similarity index when information about node type is unavailable. This relationship may help to find the appropriate index for given networks.

• 한국해양공학회지
• /
• 제35권4호
• /
• pp.257-265
• /
• 2021

Many studies have been performed to predict a reliable and accurate stress-range distribution and fatigue damage regarding the Gaussian wide-band stress response due to multi-peak waves and multiple dynamic loads. So far, most of the approximation models provide slightly inaccurate results in comparison with the rain-flow counting method as an exact solution. A step-by-step study was carried out to develop new approximate spectral moments that are close to the rain-flow counting moment, which can be used for the development of a fatigue damage model. Using the special parameters and bandwidth parameters, four kinds of parameter-based combinations were constructed and estimated using the R-squared values from regression analysis. Based on the results, four candidate empirical formulas were determined and compared with the rain-flow counting moment, probability density function, and root mean square (RMS) value for relative distance. The new approximate spectral moments were finally decided through comparison studies of eight response spectra. The new spectral moments presented in this study could play an important role in improving the accuracy of fatigue damage model development. The present study shows that the new approximate moment is a very important variable for the enhancement of Gaussian wide-band fatigue damage assessment.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권9호
• /
• pp.2483-2504
• /
• 2023

Most existing low-light enhancement algorithms either use a large number of training parameters or lack generalization to real-world scenarios. This paper presents a novel lightweight and robust pixel-wise polynomial approximation-based deep network for low-light image enhancement. For mapping the low-light image to the enhanced image, pixel-wise higher-order polynomials are employed. A deep convolution network is used to estimate the coefficients of these higher-order polynomials. The proposed network uses multiple branches to estimate pixel values based on different receptive fields. With a smaller receptive field, the first branch enhanced local features, the second and third branches focused on medium-level features, and the last branch enhanced global features. The low-light image is downsampled by the factor of 2b-1 (b is the branch number) and fed as input to each branch. After combining the outputs of each branch, the final enhanced image is obtained. A comprehensive evaluation of our proposed network on six publicly available no-reference test datasets shows that it outperforms state-of-the-art methods on both quantitative and qualitative measures.

• 지능정보연구
• /
• 제25권4호
• /
• pp.53-65
• /
• 2019

영상 기반의 보안 시스템의 증가함에 따라 각 용도마다 다른 다양한 객체들에 대한 처리들이 중요해지고 있다. 객체 추적은 객체 인식, 검출과 같은 작업들과 함께 필수적인 작업으로 다뤄진다. 이 객체 추적을 달성하기 위해서 다양한 머신러닝이 적용될 수 있다. 성공적인 분류기로써 전체 에러율 최소화(total-error-rate minimization) 기반의 방법론이 사용될 수 있다. 이 전체 에러율 최소화 기반의 방법론은 오프라인 학습을 기반으로 하고 있다. 객체 추적은 실시간으로 처리하며 갱신해야하는 것이 필수적이므로 온라인 학습(online learning)을 기반으로 하는 것이 적합하다. 온라인 전체 에러율 최소화 방법론이 개발되었지만 점근적으로 재가중되는(approximately reweighted) 작업이 포함되어 에러를 누적시킬 수 있다는 단점이 있다. 본 논문에서는 정확하게 재가중되는(exactly reweighted) 방법론을 제안하면서 온라인 전체 에러율 최소화가 달성되었다. 이 제안된 온라인 학습 방법론을 객체 추적에 적용하여 총 8개의 데이터베이스에서 다른 추적 방법론들 보다 좋은 성능이 달성되었다.

• 대한교통학회지
• /
• 제18권6호
• /
• pp.89-99
• /
• 2000

전통적인 OD조사에 의한 OD추정방법의 여러 문제점들로 인해 링크에서 관측된 교통량과 기존OD를 결합해 새로운 OD를 추정하고자 하는 연구들이 지속되고 있으며, 그 필요성도 증대되고 있다. 그러한 기법중의 하나가 Yang(1995)이 제시한 바이레벨 모형으로, 그는 일반화최소자승법을 풀기위한 Sensitivity Analysis Based (SAB)을 제시하였다. 그러나 SAB 알고리즘은 두가지 중요한 문제점을 가지고 있다. 첫 번째 문제는 실제 OD를 알기가 어렵기 때문에, 기존 OD 조사시의 통행패턴이 현재의 통행패턴과 큰 변화가 없다는 가정 하에, 기존 OD를 추정시 중요한 추정기준으로 설정한다는 점이다. 그러나 이러한 기존 OD에 대한 추정의 종속성으로 인해, SAB는 기존 OD와 실제 OD의 차이가 큰 경우 정확한 해를 도출하지 못하고 추정결과가 일관적(robust)이지 않게 도출된다. 두 번째 문제는 SAB는 통행패턴 추정시 선형근사화를 가정하기 때문에 게임이론적 측면에서 전제로 설정한 완전한 Stackelberg 상황을 구현하지 못한다는 점이다. 이러한 문제점을 피하기 위해서는 기존 OD의 오차나 관측교통량의 오차에 대해 일관적이고 안정적인 해도출 기법이 필요하다. 본 연구의 목적은 SAB를 비롯한 기존 바이레벨 OD추정기법의 문제점을 지적하고 이에 대한 대안기법을 제시하는 것이다. OD추정의 문제는 본질적으로 비선형이고 비볼록하기 때문에, 다중해를 도출하게 된다. 따라서 전역해 탐색기법이 필요한데, 본 연구에서는 전역최적화가 가능한 유전알고리즘(Genetic Algorithm)을 이용한 OD추정모형(GA-Model:GAM)을 제시하였다. 사례네트워크에 대한 비교분석결과, GAM은 기존 OD의 오타에 대해 크게 종속적이지 않으며 OD구조가 변하는 경우에도 추정이 가능하여, 일반적으로 실제 OD를 알 수 없는 (기존OD의 오차가 어느 정도인지를 알 수 없는) 도시부 네트워크에서 신뢰성있는 추정력을 보였다.

• Journal of the Korean Data and Information Science Society
• /
• 제28권4호
• /
• pp.831-841
• /
• 2017

원주율 ${\pi}$는 임의의 원의 지름에 대한 둘레의 비로 정의되며 상수값을 갖는다. 이 값은 무리수이며 초월수로서 고대로부터 좀 더 정확한 값을 구하기 위한 수많은 노력이 있어왔다. 특히 확률분야에서는 18세기 Buffon의 바늘문제를 기점으로 확률실험을 통하여 ${\pi}$값을 계산하려는 많은 노력이 있어왔다. 통계분야에서 Chong (2008)은 서로 독립인 이변량표준정규확률분포와 단변량 확률보행과정의 차분이 독립인 정규분포를 따른다는 전제조건하에서 ${\pi}$값을 유도하였다. 본 연구에서는 Buffon의 바늘문제와 정사각형에 내접하는 원의 문제에서 유도된 ${\pi}$값을 확률실험을 통하여 근사값을 구해보며 이 값이 실험횟수와 어떤 관계가 있는지 알아본다. 더불어 Chong이 유도한 단변량확률보행과정의 차분에 근거한 ${\pi}$의 일치추정량을 모의실험을 통하여 검증해본다. 나아가 국내외 금융자료를 사용하여 제시된 방법에 의해 계산된 추정값의 수렴여부와 수렴할 경우 극한값과 ${\pi}$의 오차정도를 살펴보고 이를 통하여 효율적시장가설에 대한 설명을 시도한다.