• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권5호
• /
• pp.2346-2362
• /
• 2016

As one of the most important issues in computer vision and image processing, online object tracking plays a key role in numerous areas of research and in many real applications. In this study, we present a novel tracking method based on the proposed structured sparse representation model, in which the tracked object is assumed to be sparsely represented by a set of object and background templates. The contributions of this work are threefold. First, the structure information of all the candidate samples is utilized by a joint sparse representation model, where the representation coefficients of these candidates are promoted to share the same sparse patterns. This representation model can be effectively solved by the simultaneous orthogonal matching pursuit method. In addition, we develop a tracking algorithm based on the proposed representation model, a discriminative candidate selection scheme, and a simple model updating method. Finally, we conduct numerous experiments on several challenging video clips to evaluate the proposed tracker in comparison with various state-of-the-art tracking algorithms. Both qualitative and quantitative evaluations on a number of challenging video clips show that our tracker achieves better performance than the other state-of-the-art methods.

• 한국컴퓨터정보학회논문지
• /
• 제20권12호
• /
• pp.67-74
• /
• 2015

The heat conduction equation, a type of a Poisson equation which can be applied in various areas of engineering is calculating its value with the iteration method in general. The equation which had difference discretization of the heat conduction equation is the simultaneous equation, and each line has the characteristic of expressing in sparse matrix of the equivalent number of none-zero elements with neighboring grids. In this paper, we propose a data structure for sparse matrix that can calculate the value faster with less memory use calculate the heat conduction equation. To verify whether the proposed data structure efficiently calculates the value compared to the other sparse matrix representations, we apply the representative iteration method, CG (Conjugate Gradient), and presents experiment results of time consumed to get values, calculation time of each step and relevant time consumption ratio, and memory usage amount. The results of this experiment could be used to estimate main elements of calculating the value of the general heat conduction equation, such as time consumed, the memory usage amount.

• 대한전자공학회논문지SP
• /
• 제49권2호
• /
• pp.122-129
• /
• 2012

Compressive sensing 분야에서 orthogonal matching pursuit (OMP) 알고리듬은 underdetermined 시스템의 스파스 (sparse) 신호를 복구하는 대표적인 greedy 알고리듬으로 많은 관심을 받고 있다. 본 논문에서는 OMP 알고리듬의 반복과정에서 하나 이상의 support들을 선택할 수 있도록 하는 OMP 알고리듬의 일반화된 형태의 generalized orthogonal matching pursuit (gOMP)기법을 제안한다. gOMP가 완벽한 신호 복원을 보장하기 위해 restricted isometry property (RIP)를 이용한 충분조건, ${\delta}_{NK}$ < $\frac{\sqrt{N}}{\sqrt{K}+2\sqrt{N}}$을 제시한다. 실험을 통해 gOMP는 매 반복과정에서 하나 이상의 support들를 선택함으로써 높은 복원 성능과 낮은 복잡도를 가짐을 확인하였다.

• 스마트미디어저널
• /
• 제5권1호
• /
• pp.88-94
• /
• 2016

본 논문에서는 희소성 표현을 기반으로 하는 객체 추적 방법에 있어서 객체 표류 현상을 처리하기 위한 새로운 방법을 제시한다. 그중에서도 APG-L1 (accelerated proximal gradient L1) 방법은 희소성 표현이란 객체의 외형을 표현하기 위한 목표 템플릿(target template)과 배경이나 폐색(occlusion)과 같은 객체 이외의 부분을 대체하기 위한 기본 템플릿(trivial template)를 이용하여 입력 영상을 표현하는 방법이다. 또한 어파인 변환행렬을 이용한 particle filtering 이 적용되어 객체의 위치를 찾고 APG 방법을 사용하여 희소성기반의 L1-norm을 최소화한다. 본 논문에서는 객체추적의 표류현상을 방지하기 위하여 기본 템플릿의 계수를 활용하여 배경을 가진 객체가 채택되는 현상을 방지하는 방법을 제시한다. 다양한 영상에 적용하여 제안하는 방법을 실험한 결과, 기존의 방법들과 비교하여 높은 성과를 보인다.

• Genomics & Informatics
• /
• 제20권4호
• /
• pp.48.1-48.7
• /
• 2022

Penalized regression has been widely used in genome-wide association studies for joint analyses to find genetic associations. Among penalized regression models, the least absolute shrinkage and selection operator (Lasso) method effectively removes some coefficients from the model by shrinking them to zero. To handle group structures, such as genes and pathways, several modified Lasso penalties have been proposed, including group Lasso and sparse group Lasso. Group Lasso ensures sparsity at the level of pre-defined groups, eliminating unimportant groups. Sparse group Lasso performs group selection as in group Lasso, but also performs individual selection as in Lasso. While these sparse methods are useful in high-dimensional genetic studies, interpreting the results with many groups and coefficients is not straightforward. Lasso's results are often expressed as trace plots of regression coefficients. However, few studies have explored the systematic visualization of group information. In this study, we propose a multi-level polar Lasso (MP-Lasso) chart, which can effectively represent the results from group Lasso and sparse group Lasso analyses. An R package to draw MP-Lasso charts was developed. Through a real-world genetic data application, we demonstrated that our MP-Lasso chart package effectively visualizes the results of Lasso, group Lasso, and sparse group Lasso.

• 방사선산업학회지
• /
• 제17권4호
• /
• pp.377-384
• /
• 2023

In this study, the image quality assessment, especially spatial resolution evaluation, for Sparse-view CT reconstructed images was performed. The main goal of the experiment is to evaluate Modulation Transfer Function by using American Standard Method for Measurement of Computed Tomography System Performance(ASTM E1695-95) which uses the edge test object. To compare with the ASTM method, a different method, the radial-type edge profile, to measure MTF using the edge method also performed. Both approaches were tested on the same image acquired by the stationary-gantry sparse-view CT security-screening system using cylindrical test phantom manufactured in accordance with ANSI 42.45. Both of the spatial resolutions at 10% modulation are 0.195, 0.203lp pixel^-1, respectively. The method implemented by ASTM E1695-95 showed higher reliability and had a relatively more accurate spatial resolution result than the radial-type edge profile method.

• 대한음성학회지:말소리
• /
• 제67호
• /
• pp.135-147
• /
• 2008

In this paper, we propose a method for source localization in reverberant environments based on an adaptive eigenvalue decomposition (AED) algorithm which directly estimates channel impulse responses from a speaker to microphones. Unfortunately, the AED algorithm may suffer from whitening effects on channels estimated from temporally correlated natural sounds. The proposed method which applies sparse priors to the estimated channels can avoid the temporal whitening and improve the performance of source localization in reverberant environments. Experimental results show the effectiveness of the proposed method.

• 대한수학회논문집
• /
• 제15권4호
• /
• pp.587-595
• /
• 2000

We contain a simple construction for the sparse n x n connected orthogonal matrices which have a row of p nonzero entries with 2$\leq$p$\leq$n. Moreover, we study the analogous sparsity problem for an m x n connected row-orthogonal matrices.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 1998년도 가을 학술발표논문집 Vol.25 No.2 (2)
• /
• pp.336-338
• /
• 1998

This paper presents a novel neural network structure to the blind deconvolution task where the input (source) to a system is not available and the source has any type of distribution including sparse distribution. We employ multiple sensors so that spatial information plays a important role. The resulting learning algorithm is linear so that it works for both sub-and super-Gaussian source. Moreover, we can successfully deconvolve the mixture of a sparse source, while most existing algorithms [5] have difficulties in this task. Computer simulations confirm the validity and high performance of the proposed algorithm.

• 한국콘텐츠학회:학술대회논문집
• /
• 한국콘텐츠학회 2018년도 춘계 종합학술대회 논문집
• /
• pp.485-486
• /
• 2018

In this paper, we consider a binary recovery framework of the Compressed Sensing (CS) problem. We derive an upper bound for $L_0$ recovery performance of a binary sparse signal in terms of the dimension N and sparsity K of signals, the number of measurements M. We show that the upper bound obtained from this work goes to the limit bound when the sensing matrix sufficiently become dense. In addition, for perfect recovery performance, if the signals are very sparse, the sensing matrices required for $L_0$ recovery are little more dense.