• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.49 no.1
• /
• pp.94-102
• /
• 2012

Recently entered into an aging socity as the number of elderly drivers is increasing. Traffic accidents of elderly drivers are caused by driver inattentions such as poor vehicle control due to aging, visual information retrieval problems caused by presbyopia, and objects identifying problems caused by low contrast sensitivity. In this paper, detection method of ROIs on the road is proposed. The proposed method creates the saliency map to detect the candidate ROIs from the input image. And, the input image is segmented to obtain the ROIs boundary. Finally, selective visual attention regions are detected according to the presence or absence of a segmented region with saliency pixels. Experimental results from a variety of outdoor environmental conditions, the proposed method presented a fast object detection and a high detection rate.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.45-46
• /
• 2024

본 논문에서는 Self-Attention 기반 딥러닝 기법인 Dense Prediction Transformer(DPT) 모델을 MVTec Anomaly Detection(MVTec AD) 데이터셋에 적용하여 실제 산업 제품 이미지 내 이상 부분을 분할하는 연구를 진행하였다. DPT 모델의 적용을 통해 기존 Convolutional Neural Network(CNN) 기반 이상 탐지기법의 한계점인 지역적 Feature 추출 및 고정된 수용영역으로 인한 문제를 개선하였으며, 실제 산업 제품 데이터에서의 이상 분할 시 기존 주력 기법인 U-Net의 구조를 적용한 최고 성능의 모델보다 1.14%만큼의 성능 향상을 보임에 따라 Self-Attention 기반 딥러닝 기법의 적용이 산업 제품 이상 분할에 효과적임을 입증하였다.

• Journal of Advanced Marine Engineering and Technology
• /
• v.35 no.5
• /
• pp.625-631
• /
• 2011

The passive control of fluid force acting on a square prism near a plane wall was studied by attaching horizontal splitter plate on the corner of the prism. The width of the splitter plate was 10% of the square width. The experiments were performed by measuring of fluid force on the prism and by visualization of the flow field using PIV. The experimental parameters were the attaching position and the space ratios G/B between the prism and wall. The flow between the prism and wall was remarkable and Karman vortex in the wake of the prism was considerable in the space ratio over 0.4. The point of inflection of average lift coefficient and Strouhal number on the prism were represented at the space ratio G/B=0.4 for the prototype prism and G/B=0.6 for the prism having horizontal splitter plate. The drag of the prism was reduced average 4.5% with the space ratios by attaching the horizontal splitter plate at the rear and lower corner on the prism. In this case, the size of the separated region on the upside of the prism was smaller than that of prism without the splitter plate.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2010.05a
• /
• pp.1084-1088
• /
• 2010

일반적으로 자연하천에서는 횡방향 흐름저항 요소가 매우 다를 수 있다. 이러한 하천은 흐름저항 요인에 따라 몇 개의 소단면으로 구분될 수 있으며, 1차원 해석을 위해서는 단면 전체를 대표하는 복합 조도계수(composite roughness coefficient)를 사용함으로써 수위 또는 평균유속의 계산이 가능해 진다. 복합 조도계수는 각 소단면의 면적(A), 윤변(P), 또는 동수반경(R)을 적절히 조합하여 각 소단면의 조도계수에 가중치를 부여하면서 계산되는데, 각 산정식들의 개발과정에 도입된 가정 조건에 따라 상이한 가중치를 부여하게 되며, 일부 산정식들에서는 횡방향으로 동일한 재료로 구성된 조건에서도 복합 조도계수 산정 결과는 하상재료에 의한 조도계수와 다른 값을 산정하게 된다. 본 연구에서는 13개의 기존 복합 조도계수 산정식을 이론적으로 검토하였고, 소규모 실내 수리실험자료로부터 실측 복합 조도계수와 계산된 값을 비교 분석하였으며, 소단면 분할방법에 의한 기존 산정식의 적용성을 분석하였다. 분석결과, 윤변을 가중치로 사용하는 경우는 실측 복합 조도계수 그리고 각 산정식에 의한 계산 복합 조도계수의 차이가 비교적 작게 나타났으나 각 산정식의 가정조건에 유의하여야 하는 것으로 나타났다. 한편 단면적 또는 윤변과 동수반경을 조합하여 가중치로 사용하는 경우는 방법별로 큰 차이를 보이는 것으로 분석되었고, 그 원인은 단면분할 방법에 기인하므로 이러한 방법을 적용할 경우에는 소단면 분할방법에 특히 주의하여야 함을 알 수 있다.

• International Area Studies Review
• /
• v.12 no.3
• /
• pp.549-566
• /
• 2008

This study examines the effect of social conservative values that have risen as an important factor in American politics. Focusing on the abortion issue, it discusses how the abortion issue has affected American voters' issue and party preferences and their ideological orientations. The empirical results demonstrate that the abortion issue has contributed to reinforce the existing ideological and partisan divisions, although it has not realigned them. As a consequence, the abortion issue has become a significant determinant for vote choice since 1980s. Particularly in 1990s, when the polarization among the political elites became clear, the political effect of the abortion issue appears to be more evident.

• Korean Journal of Cognitive Science
• /
• v.10 no.3
• /
• pp.1-15
• /
• 1999

Based on known physiological and psychophysical results, a neural network model for visual selection, called FeaureGate is proposed. The model consists of a hierarchy of spatial maps. and the flow of information from each level of the hierarchy to the next is controlled by attentional gates. The gates are jointly controlled by a bottom-up system favoring locations with unique features. and a top-down mechanism favoring locations with features designated as target features. The present study focuses on the top-down mechanism of the FeatureGate model that produces results similar to Moran and Desimone's (1985), which many current models have failed to explain, The FeatureGate model allows a consistent interpretation of many different experimental results in visual attention. including parallel feature searches and serial conjunction searches. attentional gradients triggered by cuing, feature-driven spatial selection, split a attention, inhibition of distractor locations, and flanking inhibition. This framework can be extended to produce a model of shape recognition using upper-level units that respond to configurations of features.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.4
• /
• pp.29-37
• /
• 2021

In this paper, we propose a deep learning-based retinal vessel segmentation model for handling multi-scale information of fundus images. we integrate the selective kernel convolution into U-Net-based convolutional neural network. The proposed model extracts and segment features information with various shapes and sizes of retinal blood vessels, which is important information for diagnosing eye-related diseases from fundus images. The proposed model consists of standard convolutions and selective kernel convolutions. While the standard convolutional layer extracts information through the same size kernel size, The selective kernel convolution extracts information from branches with various kernel sizes and combines them by adaptively adjusting them through split-attention. To evaluate the performance of the proposed model, we used the DRIVE and CHASE DB1 datasets and the proposed model showed F1 score of 82.91% and 81.71% on both datasets respectively, confirming that the proposed model is effective in segmenting retinal blood vessels.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.4
• /
• pp.87-87
• /
• 2001

일반화 대칭 변환 (generalized symmetry transform, GST)은 주어진 영상에서 사전 분할이 없이 국부성과 반사 대칭성을 결합하여 대칭을 측정하고 관심 영역을 추출한다. GST의 거리 가중치 함수에서 국부적인 대칭성이 반영되며 이 함수의 표준 편차 u에 의해 GST의 수행 범위가 조절된다. 넓은 관심영역을 추출하기 위해 반지름 r이 큰 검색영역 내에서의 대칭성이 추출될 필요가 있다. 이에 따라서 GST의 수행시간은 r에 따라 2차적으로 증가하게 된 본 논문에서는 이를 개선하기 위해 선택적 방향 주의를 가지는 수정된 스캔라인 GST를 제안한다. 제안된 GST는 기존의 GST와 유사한 대칭 특성을 추출하지만 선택적 방향의 기울기만을 고려한 스캔라인 위의 에지 화소쌍에서 GST를 수행함으로써 r에 따라서 이의 수행시간이 선형적으로 증가된다 특히 r이 큰 경우에 선택적 방향에 대해서만 적용하면 기존의 GST의 계산량이 비대해지는 단점을 보완해 줄 수 있다. 제안된 GST가 기존의 GST보다 시간적으로 효과적이며 유용하다는 것이 여러 종류의 영상에 대한 실험으로 확인되었다.

• School Mathematics
• /
• v.14 no.1
• /
• pp.29-43
• /
• 2012

This paper investigated the conceptual schemes in which four children constructed a strategy representing the situation as a figure and partitioning it related to the work which they quantify the result of partitioning to various types of fractions when an equal sharing situation was given to them in contextual or an abstract symbolic form of division. Also, the paper researched how the relationship of factors and multiples between the numerator and denominator, or between the divisor and dividend affected the construction. The children's partitioning strategies were developed such as: repeated halving stage ${\rightarrow}$ consuming all quantity stage ${\rightarrow}$ whole number objects leftover stage ${\rightarrow}$ singleton object analysis/multiple objects analysis ${\rightarrow}$ direct mapping stage. When children connected the singleton object analysis with multiple object analysis, they finally became able to conceptualize division as fractions and fractions as division.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.3
• /
• pp.120-125
• /
• 1996

A new hit-and-miss ratio transform is introduced as a modified hit-and-miss transform to be robust to noise, which uses a quasi-matching technique based on the fitting ratio functions. And a new gray-level object segmentation algorithm is proposed, which is based on the hit-and-miss ratio transform and threshold decomposition. The proposed segmentation images, and is similarly applicable to segmentation of an object with specific shapes form natural real images.