• 제목/요약/키워드: resolution methods

검색결과 2,213건 처리시간 0.029초

생성적 적대 신경망을 이용한 함정전투체계 획득 영상의 초고해상도 영상 복원 연구 (A Study on Super Resolution Image Reconstruction for Acquired Images from Naval Combat System using Generative Adversarial Networks)

  • 김동영
    • 디지털콘텐츠학회 논문지
    • /
    • 제19권6호
    • /
    • pp.1197-1205
    • /
    • 2018
  • 본 논문에서는 함정전투체계의 EOTS나 IRST에서 획득한 영상을 초고해상도 영상으로 복원한다. 저해상도에서 초고해상도의 영상을 생성하는 생성 모델과 이를 판별하는 판별 모델로 구성된 생성적 적대 신경망을 이용하고, 다양한 학습 파라미터의 변화를 통한 최적의 값을 제안한다. 실험에 사용되는 학습 파라미터는 crop size와 sub-pixel layer depth, 학습 이미지 종류로 구성되며, 평가는 일반적인 영상 품질 평가 지표에 추가적으로 특징점 추출 알고리즘을 함께 사용하였다. 그 결과, Crop size가 클수록, Sub-pixel layer depth가 깊을수록, 고해상도의 학습이미지를 사용할수록 더 좋은 품질의 영상을 생성한다.

Identifying Effective Dispute Resolution Mechanisms for Intellectual Property Disputes in the International Context

  • Lee, Ju-Yeon
    • 한국중재학회지:중재연구
    • /
    • 제25권3호
    • /
    • pp.155-184
    • /
    • 2015
  • This paper addresses the question of what kinds of dispute resolution choices can effectively handle complex intellectual property disputes, given the rising importance of IP, the increasing frequency and complexity of IP disputes, and the lack of research on dispute resolution strategies. For this analysis, the study adopted the analytic hierarchy process approach, which covers complex, multi-criteria decision problems, to quantify the expert's judgments on IP dispute resolution choice. Its results show that the effectiveness of resolution methods differs, depending on the type of IP dispute classified into seven issues, which are (i) requirement for validity of IP right, (ii) range and duration of IP right, (iii) transfer of IP right, (iv) licensing, (v) use of IP right, (vi) declaration of IP infringement, and (vii) estimation of damage. The disputes over IPR ownership and IP infringement remain challenging issues in due to strong requirement of the cross-border enforcement. Alternative dispute resolution (ADR), especially arbitration, is determined to be a more effective method to deal with international IP disputes, but various advanced types of ADR techniques should be further developed to deal with the increasing complexity of IP disputes.

Multi-resolution Fusion Network for Human Pose Estimation in Low-resolution Images

  • Kim, Boeun;Choo, YeonSeung;Jeong, Hea In;Kim, Chung-Il;Shin, Saim;Kim, Jungho
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • 제16권7호
    • /
    • pp.2328-2344
    • /
    • 2022
  • 2D human pose estimation still faces difficulty in low-resolution images. Most existing top-down approaches scale up the target human bonding box images to the large size and insert the scaled image into the network. Due to up-sampling, artifacts occur in the low-resolution target images, and the degraded images adversely affect the accurate estimation of the joint positions. To address this issue, we propose a multi-resolution input feature fusion network for human pose estimation. Specifically, the bounding box image of the target human is rescaled to multiple input images of various sizes, and the features extracted from the multiple images are fused in the network. Moreover, we introduce a guiding channel which induces the multi-resolution input features to alternatively affect the network according to the resolution of the target image. We conduct experiments on MS COCO dataset which is a representative dataset for 2D human pose estimation, where our method achieves superior performance compared to the strong baseline HRNet and the previous state-of-the-art methods.

High-Resolution Satellite Image Super-Resolution Using Image Degradation Model with MTF-Based Filters

  • Minkyung Chung;Minyoung Jung;Yongil Kim
    • 대한원격탐사학회지
    • /
    • 제39권4호
    • /
    • pp.395-407
    • /
    • 2023
  • Super-resolution (SR) has great significance in image processing because it enables downstream vision tasks with high spatial resolution. Recently, SR studies have adopted deep learning networks and achieved remarkable SR performance compared to conventional example-based methods. Deep-learning-based SR models generally require low-resolution (LR) images and the corresponding high-resolution (HR) images as training dataset. Due to the difficulties in obtaining real-world LR-HR datasets, most SR models have used only HR images and generated LR images with predefined degradation such as bicubic downsampling. However, SR models trained on simple image degradation do not reflect the properties of the images and often result in deteriorated SR qualities when applied to real-world images. In this study, we propose an image degradation model for HR satellite images based on the modulation transfer function (MTF) of an imaging sensor. Because the proposed method determines the image degradation based on the sensor properties, it is more suitable for training SR models on remote sensing images. Experimental results on HR satellite image datasets demonstrated the effectiveness of applying MTF-based filters to construct a more realistic LR-HR training dataset.

SPECT/CT에서 서로 다른 에너지의 방사성동위원소 사용시 영상보정기법의 유용성 평가 (The Evaluation of Image Correction Methods for SPECT/CT in Various Radioisotopes with Different Energy Levels)

  • 신병호;김승정;윤석환;김태엽;임정진;우재룡;오소원;김유경
    • 핵의학기술
    • /
    • 제17권2호
    • /
    • pp.53-58
    • /
    • 2013
  • 본 연구에서는 각기 다른 에너지의 방사성동위원소를 이용하여 CT를 기초로 한 attenuation correction (AC)과 scatter correction (SC)을 적용했을 때 영상의 질을 비교분석하고 영상보정기법의 유용성에 대해 알아보고자 하였다. Resolution 평가를 위해 사용된 spatial resolution phantom 내부에 물을 채우고 각각의 동위원소 $^{99m}Tc$ (140 keV, 2.22 kBq), $^{201}Tl$ (70 keV, 2.22 kBq), $^{131}I$ (364 keV, 2.22 kBq)을 line에 주입하여 제작하였다. Contrast 평가를 위해 이용한 Jaszczak phantom은 배후방사능과 열소원통의 비율이 1:8이 되도록 각각의 동위원소를 주입하여 제작하였다. GE Infinia Hawkeye4 SPECT/CT (GE Medical System, USA)로 영상을 획득하고, non-correction (NC), AC, SC, AC와 SC가 동시에 적용된(ACSC) 4가지 조건으로 OSEM (2 iterations, 10 subsets)을 이용하여 영상을 각각 재구성하였다. FWHM값은 paired samples t-test를 통하여 유의수준 관계를 분석하였고, percent contrast (%)값은 MATLAB (Ver.7.0)$^{(R)}$과 MRIcro$^{(R)}$를 이용하여 각각의 수치를 비교하였다. $^{99m}Tc$의 resolution test에서 NC, AC, SC, ACSC를 각각 적용했 을 때 FWHM (mm)값은 각각 $4.97{\pm}0.46$, $4.73{\pm}0.27$, $49.7{\pm}0.39$, $4.60{\pm}0.26$, $^{201}Tl$에서는 $5.26{\pm}0.28$, $5.14{\pm}0.21$, $5.25{\pm}0.25$, $5.05{\pm}0.23$, $^{131}I$에서는 $6.24{\pm}0.73$, $5.84{\pm}0.57$, $6.24{\pm}0.69$, $5.98{\pm}0.52$의 값을 얻을 수 있었다. 각 방사성 동위원소의 결과 값에서 NC와 비교하여 AC, ACSC를 적용했을 때 통계적으로 유의한 차이를 보였고(P<0.05), SC만을 적용했을 때는 유의한 차이가 없음을 보여주었다(P>0.05). Contrast test에서는 percent contrast(%) 를 4개의 원통에 대한 값을 구했고, NC와 비교했을 때 AC, SC, ACSC의 percent difference (%)가 $^{99m}Tc$은 24.73, 38.10, 67.31, $^{201}Tl$은 30.90, 51.82, 86.02, $^{131}I$에서는 18.60, 46.26, 73.67의 차이를 보였다. 본 연구의 결과에 따르면 $^{99m}Tc$, $^{201}Tl$ 과 같은 낮은 에너지를 가진 핵종에 대해서는 ACSC를 동시에 적용한 영상에서 resolution 향상이 가장 크게 나타났지만, $^{131}I$ 같은 높은 에너지의 핵종에서는 AC만 적용되었을 때 ACSC를 적용했을 때보다 영상의 질이 더 향상됨을 알 수 있었다. 그러므로 SPECT/CT 검사 시 사용되는 핵종의 에너지에 따라 적절한 영상보정기법을 적용한다면 정확한 진단을 위한 최적의 영상을 얻을 수 있을 것으로 사료된다.

  • PDF

CNN을 이용한 Quad Tree 기반 2D Smoke Super-resolution (Quad Tree Based 2D Smoke Super-resolution with CNN)

  • 홍병선;박지혁;최명진;김창헌
    • 한국컴퓨터그래픽스학회논문지
    • /
    • 제25권3호
    • /
    • pp.105-113
    • /
    • 2019
  • 물리 기반 유체 시뮬레이션은 고해상도 연산을 위해 많은 시간이 필요하다. 이 문제를 해결하기 위해 저해상도 유체 시뮬레이션의 한계를 딥 러닝으로 보완하는 연구들이 있으며, 그중에서는 저해상도의 시뮬레이션 데이터를 고해상도로 변환해주는 Super-resolution 분야가 있다. 하지만 기존 기법들은 전체 데이터 공간에서 밀도 데이터가 없는 부분까지 연산하므로 전체 시뮬레이션 속도 면에서 효율성이 떨어지며, 입력 해상도가 큰 경우에는 GPU 메모리가 부족해 연산할 수 없는 경우가 발생할 수 있다. 본 연구에서는 공간 분할 법 중 하나인 쿼드 트리를 활용하여 시뮬레이션 공간을 분할 및 분류하여 Super-resolution 하는 기법을 제안한다. 본 기법은 필요 공간만 Super-resolution 하므로 전체 시뮬레이션 가속화가 가능하고, 입력 데이터를 분할 연산하므로 GPU 메모리 문제를 해결할 수 있게 된다.

환상격자 필터를 이용한 ARMA 스펙트럼 추정에 관한 연구 (Study on ARMA spectrum estimation using circular lattice filter)

  • 장영수;이철희;양흥석
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 제어로봇시스템학회 1987년도 한국자동제어학술회의논문집; 한국과학기술대학, 충남; 16-17 Oct. 1987
    • /
    • pp.442-445
    • /
    • 1987
  • In this paper, a new ARMA spectrum estimation algorithm based on Circular Lattice filter is presented. Since APMA model is used in signal modeling, high-resolution spectrum can be obtained. And the computational burden is reduced by using Circular Lattice filter. By modifying the input estimation part of other proposed methods, we can get high-resolution spectrum with less computation and less memory compared with other Lattice methods. Some computer simulations are performed.

  • PDF

Data Interpretation Methods for Petroleomics

  • Islam, Annana;Cho, Yun-Ju;Ahmed, Arif;Kim, Sung-Hwan
    • Mass Spectrometry Letters
    • /
    • 제3권3호
    • /
    • pp.63-67
    • /
    • 2012
  • The need of heavy and unconventional crude oil as an energy source is increasing day by day, so does the importance of petroleomics: the pursuit of detailed knowledge of heavy crude oil. Crude oil needs techniques with ultra-high resolving capabilities to resolve its complex characteristics. Therefore, ultra-high resolution mass spectrometry represented by Fourier transform ion cyclotron resonance mass spectrometry (FT-ICR MS) has been successfully applied to the study of heavy and unconventional crude oils. The analysis of crude oil with high resolution mass spectrometry (FT-ICR MS) has pushed analysis to the limits of instrumental and methodological capabilities. Each high-resolution mass spectrum of crude oil may routinely contain over 50,000 peaks. To visualize and effectively study the large amount of data sets is not trivial. Therefore, data processing and visualization methods such as Kendrick mass defect and van Krevelen analyses and statistical analyses have played an important role. In this regard, it will not be an overstatement to say that the success of FT-ICR MS to the study of crude oil has been critically dependent on data processing methods. Therefore, this review offers introduction to peotroleomic data interpretation methods.

Hierarchical Regression for Single Image Super Resolution via Clustering and Sparse Representation

  • Qiu, Kang;Yi, Benshun;Li, Weizhong;Huang, Taiqi
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • 제11권5호
    • /
    • pp.2539-2554
    • /
    • 2017
  • Regression-based image super resolution (SR) methods have shown great advantage in time consumption while maintaining similar or improved quality performance compared to other learning-based methods. In this paper, we propose a novel single image SR method based on hierarchical regression to further improve the quality performance. As an improvement to other regression-based methods, we introduce a hierarchical scheme into the process of learning multiple regressors. First, training samples are grouped into different clusters according to their geometry similarity, which generates the structure layer. Then in each cluster, a compact dictionary can be learned by Sparse Coding (SC) method and the training samples can be further grouped by dictionary atoms to form the detail layer. Last, a series of projection matrixes, which anchored to dictionary atoms, can be learned by linear regression. Experiment results show that hierarchical scheme can lead to regression that is more precise. Our method achieves superior high quality results compared with several state-of-the-art methods.

온라인 ADR의 운영현황과 활성화 방안에 관한 연구 (A Study on the Current Operation and Activation of Online Alternative Dispute Resolution)

  • 최석범
    • 한국중재학회지:중재연구
    • /
    • 제18권3호
    • /
    • pp.91-116
    • /
    • 2008
  • E-Commerce constitutes an important part of all commercial activities. Online Alternative Dispute Resolution(Online ADR) or Online Dispute Resolution(ODR) is a new method of dispute, resolution which, is provided online. Most Online ADR services are alternatives to litigation. In this respect, they are the online transposition of the methods developed in the ADR movement such as negotiation, mediation and arbitration. But there are also online courts which are really normal courts in which the contesting parties communicate essentially online. This paper deals with the current operation of Online ADR and the ways to, activate it. They include (1) die establishment of legal stability regarding Online ADR, (2) the enhancement of system security in providing Online ADR services, (3) the introduction of Online ADR service platform for providing the various services through single window on a national, or global basis, and (4) the introduction of Online ADR online monitoring system for systematic dispute resolution services.

  • PDF