• Journal of Korea Multimedia Society
• /
• v.15 no.3
• /
• pp.336-344
• /
• 2012

As an important part of the Computer Vision, the object recognition and tracking function has infinite possibilities range from motion recognition to aerospace applications. One of methods to improve accuracy of the object recognition, are uses colors which have robustness of orientation, scale and occlusion. Computational cost for extracting features can be reduced by using color. Also, for fast object recognition, predicting the location of the object recognition in a smaller area is more effective than lowering accuracy of the algorithm. In this paper, we propose a method that uses SURF descriptors which applied with color model for improving recognition accuracy and combines with Kalman filter which is Motion estimation algorithm for fast object tracking. As a result, the proposed method classified objects which have same patterns with different colors and showed fast tracking results by performing recognition in ROI which estimates future motion of an object.

• Composites Research
• /
• v.31 no.5
• /
• pp.251-259
• /
• 2018

In this paper, statistical volume element modeling method was developed for multi-scale progressive failure analysis of fiber reinforced composite materials. Big-size statistical volume elements (BSVEs) was considered to minimize the size effect in the micro-scale, by including as many fibers as possible. For that purpose, a mesh cutting method is suggested and adapted into the fiber model generator that creates finite element domain rapidly. The fiber defect model was also developed based on the experimental distribution of the fiber strength. The size effects from the local load sharing (LLS) are evaluated by increasing the fiber inclusion in the micro-scale model. Finally, continuum damage mechanics (CDM) model to the fiber direction was extracted from numerical analysis on BSVEs. And it was compared with strength prediction from typical representative volume element (RVE) model.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.37 no.6
• /
• pp.48-59
• /
• 2000

Eigendecomposition based direction-of-arrival(DOA) estimation algorithm such as MUSIC(multiple signal classification) is known to perform well and provide high resolution in white noise environment. However, its performance degrades severely when the noise process is not white. In this paper we consider the DOA estimation problem in a colored noise environment as a problem of extracting periodic signals from noise, and we take the problem to the wavelet domain. Covariance matrix of multiscale components which are obtained by taking wavelet decomposition on the noise has a special structure which can be approximated with a banded sparse matrix. Compared with noise the correlation between multiscale components of narrowband signal decays slowly, hence the covariance matrix does not have a banded structure. Based on this fact we propose a DOA estimation algorithm that transforms the covariance matrix into wavelet domain and removes noise components located in specific bands. Simulations have been carried out to analyze the proposed algorithm in colored noise processes with various correlation properties.

• Composites Research
• /
• v.24 no.6
• /
• pp.25-30
• /
• 2011

This paper presents an experimental study on the enhancement of electromagnetic shielding (EMI) properties of glass fiber, carbon fiber, and glass-carbon fiber composites by adding layers of multi-walled carbon nanotubes (MWCNTs). In the case of glass-fiber composites, spraying 0.1~0.2 g of MWCNT over a fiber area of $200mm{\times}200mm$ (1.8~3.6 ${\mu}m$ in thickness) resulted in significant improvement in EMI shielding effectiveness (SE). Also, when applying multiple MWCNT layers, it was more effective to place the layers concentrated near the center of the composite rather than spreading them out. On the contrary, inherently conductive carbon fiber and glass-carbon fiber composites did not show appreciable improvement with the addition of MWCNT layers. In order to maximize the effectiveness of carbon nanomaterials as EMI shielding fillers, it is imperative to understand the effect of these materials on various EMI shielding mechanisms and their interactions.

• Composites Research
• /
• v.33 no.4
• /
• pp.198-204
• /
• 2020

In this study, we employ the full atomistic molecular dynamics simulation and finite element homogenization method to predict the thermo-mechanical properties of nanocomposites including carbon nanotube bundle. As the number of carbon nanotubes within the single bundle increases, the effective in-plane Young's modulus and in-plane shear modulus decrease, and in-plane thermal expansion coefficient increases, despite the same volume fraction of carbon nanotubes. To investigate the thickness of interphase zone, we employ the radial density distribution. It is investigated that the interphase thickness is almost independent on the number of carbon nanotubes within the single bundle. It is assumed that the matrix and interphase are isotropic materials. According to the predicted thermo-mechanical properties of interphase zone, the Young's modulus and shear modulus of interphase zone clearly decrease, and the thermal expansion coefficient increases. Based on the thermo-mechanical interphase behavior, we developed the multiscale homogenization model to predict the thermo-mechanical properties of PLA nanocomposites that include the carbon nanotube bundle.

• Journal of Korea Multimedia Society
• /
• v.16 no.3
• /
• pp.281-289
• /
• 2013

The iCAM06 has been used as an image appearance model for HDR image rendering. The iCAM06 goes through the color space conversions and scale conversions of the several steps to present HDR images. The dynamic range of an HDR image needs to be mapped on the range of output devices, which is called the tone mapping. However, tone compression process of the iCAM06 causes color distortion because of color-clipping and cross-stimulus. Therefore, we proposed that a color correction method in IPT space which compensates the color distortion in tone compression process. Through the experimental results, we conformed that proposed color correction method had better performance than the iCAM06 and enhanced models.

• Journal of Korea Multimedia Society
• /
• v.25 no.8
• /
• pp.1212-1223
• /
• 2022

Skin lesions are common diseases that range from skin rashes to skin cancer, which can lead to death. Note that early diagnosis of skin diseases can be important because early diagnosis of skin diseases considerably can reduce the course of treatment and the harmful effect of the disease. Recently, the development of computer-aided diagnosis (CAD) systems based on artificial intelligence has been actively made for the early diagnosis of skin diseases. In a typical CAD system, the accurate classification of skin lesion types is of great importance for improving the diagnosis performance. Motivated by this, we propose a novel deep ensemble classification with multi-scale attention networks. The proposed deep ensemble networks are jointly trained using a single loss function in an end-to-end manner. In addition, the proposed deep ensemble network is equipped with a multi-scale attention mechanism and segmentation information of the original skin input image, which improves the classification performance. To demonstrate our method, the publicly available human skin disease dataset (HAM 10000) and the private animal skin lesion dataset were used for the evaluation. Experiment results showed that the proposed methods can achieve 97.8% and 81% accuracy on each HAM10000 and animal skin lesion dataset. This research work would be useful for developing a more reliable CAD system which helps doctors early diagnose skin diseases.

• Composites Research
• /
• v.19 no.1
• /
• pp.1-8
• /
• 2006

Prediction of damage caused by low-velocity impact in laminated composite plate is an important problem faced by designers using composites. Not only the inplane stresses but also the interlaminar normal and shear stresses playa role in estimating the damage caused. But it is well known that the conventional approach based on the homogenization has the limit in description of damage. The work reported here is an effort in getting better predictions of dynamic behavior and damage in composite plate using DNS approach. In the DNS model, we discretize the composite plates through separate modeling of fiber and matrix for the local microscopic analysis. In the view of microscopic mechanics with DNS model, interlaminar stress behaviors in the inside of composite materials are investigated and compared with the results of the homogenized model which has been used in the conventional approach to impact analysis. Also the multiscale model based on DNS concept is developed in order to enhance the effectiveness of impact analysis, and we present the results of multiscale analysis considering micro and macro structures simultaneously.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2011.07a
• /
• pp.556-559
• /
• 2011

최근 디지털 방송 서비스가 본격화가 이루어짐에 따라 디지털 콘텐츠는 기하급수적으로 늘어나고 있다. 또한 방송통신 융합 환경은 기존 셋탑 박스와 같은 방송 전용 단말기와 PC, 노트북, PDA와 같은 인터넷 단말기기, 그리고 모바일 폰과 같은 통신기기 사이의 벽을 허물고 있다. IPTV, SmartTV 시대의 도래로 방송통신 제공자의 양방향성 콘텐츠의 제공 및 상호연동 서비스의 제공은 중요한 이슈가 되었다. 이에 따라 다양한 단말기를 이용해 N-Screen이 가능하도록 방송통신 융합 서비스를 제공하고, 이를 위한 여러 콘텐츠 제작이 활발히 일어나고 있다. 이에 본 논문은 양방향성과 상호운용성을 높이기 위한 하나의 방법으로, 방송통신 융합서비스를 인터넷에 의한 전송과 방송 셋탑에 의한 전송에 있어서 상호 동일한 콘텐츠의 통일성을 유지하여 관리가 쉽도록 하는 Scalable Application Framework를 이용하였고 이를 실제 멀티미디어 모바일 단말기기에 적용하고 구현하였다. 이를 통해 앞으로 스마트 방송 시대에 대비할 수 있는 시스템의 대안을 제안하고자 한다. MPEG-21의 DID를 기초로 하여 SADL(Scalable Application Description Language)를 정의하고 이를 이용한 다양한 프레임워크 모델 중 일부인 멀티미디어 모바일 단말기기에 적용하여 이를 활용하는 방안에 대해 논의한다.

• Journal of Korea Multimedia Society
• /
• v.17 no.12
• /
• pp.1383-1392
• /
• 2014

In this paper, we proposed a method to automatically determine the optimal radius through multi-scale LBP operation generalizing the size of radius variation and boosting learning in facial emotion recognition. When we looked at the distribution of features vectors, the most common was $LBP_{8.1}$ of 31% and sum of $LBP_{8.1}$ and $LBP_{8.2}$ was 57.5%, $LBP_{8.3}$, $LBP_{8.4}$, and $LBP_{8.5}$ were respectively 18.5%, 12.0%, and 12.0%. It was found that the patterns of relatively greater radius express characteristics of face well. In case of normal and anger, $LBP_{8.1}$ and $LBP_{8.2}$ were mainly distributed. The distribution of $LBP_{8.3}$ is greater than or equal to the that of $LBP_{8.1}$ in laugh and surprise. It was found that the radius greater than 1 or 2 was useful for a specific emotion recognition. The facial expression recognition rate of proposed multi-scale LBP method was 97.5%. This showed the superiority of proposed method and it was confirmed through various experiments.