• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.07a
• /
• pp.339-340
• /
• 2019

전력사용량이 산업 발전과 더불어 기하급수적으로 증가하고 있으며, 한정된 공간 내에서 대용량의 전력설비를 설치하기 위해 폐쇄형 배전반이 운영되고 있다. 통계에 의하면, 고압 이상 전기설비 검사 결과 절연내력이 불합격인 경우가 다수 발생하고 있다. 특히 수배전반의 경우 부하설비 또는 외부의 영향을 확인할 수 있는 장치 및 보호설비가 설치되어 있으나 자체 안전장치가 마련되어 있지 않아 자체 사고를 신속히 검출하고 판단할 수 있는 기술이 필요하다. 본 논문에서는 열 감지 센서에 고속 디지털 신호 처리를 2차원 보간법으로 해상도를 올려서 사용하는 기술을 이용하여 아크플래시에 의해 발생되는 열 특성을 검출할 수 있는 장치 개발을 위한 기초 특성 조사를 실시하였다.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.4
• /
• pp.189-198
• /
• 2024

Lipreading is one of the important parts of speech recognition, and several studies have been conducted to improve the performance of lipreading in lipreading systems for speech recognition. Recent studies have used method to modify the model architecture of lipreading system to improve recognition performance. Unlike previous research that improve recognition performance by modifying model architecture, we aim to improve recognition performance without any change in model architecture. In order to improve the recognition performance without modifying the model architecture, we refer to the cues used in human lipreading and set other regions such as chin and cheeks as regions of interest along with the lip region, which is the existing region of interest of lipreading systems, and compare the recognition rate of each region of interest to propose the highest performing region of interest In addition, assuming that the difference in normalization results caused by the difference in interpolation method during the process of normalizing the size of the region of interest affects the recognition performance, we interpolate the same region of interest using nearest neighbor interpolation, bilinear interpolation, and bicubic interpolation, and compare the recognition rate of each interpolation method to propose the best performing interpolation method. Each region of interest was detected by training an object detection neural network, and dynamic time warping templates were generated by normalizing each region of interest, extracting and combining features, and mapping the dimensionality reduction of the combined features into a low-dimensional space. The recognition rate was evaluated by comparing the distance between the generated dynamic time warping templates and the data mapped to the low-dimensional space. In the comparison of regions of interest, the result of the region of interest containing only the lip region showed an average recognition rate of 97.36%, which is 3.44% higher than the average recognition rate of 93.92% in the previous study, and in the comparison of interpolation methods, the bilinear interpolation method performed 97.36%, which is 14.65% higher than the nearest neighbor interpolation method and 5.55% higher than the bicubic interpolation method. The code used in this study can be found a https://github.com/haraisi2/Lipreading-Systems.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.2
• /
• pp.268-274
• /
• 2016

To find the location of a random noise source present in the three-dimensional space is required at least four microphones. Using four microphones distributed in a three-dimensional space, noise source imaging technique was applied and evaluated on their performance. To compensate resolution problem which comes from both the position of the sensor array is fixed and the sampling frequency is low, up-sampling technique and interpolation function were applied. Five different interpolation methods were applied such as zero-padding, zero-order hold, first-order hold, spline function, and random signal padding. The up-sampling rate were chosen by two, four, eight times, and counting up 16 times. As a result, it was possible to more accurately estimate the position of the noise source according to the higher of the up-sampling rate. It also found that the first-order hold and the spline function's performance were slightly falling relative to other methods.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.11 no.4
• /
• pp.64-75
• /
• 2008

Since the current database systems for managing geotechnical investigation results were limited by being described boring test result in point feature, it has been trouble for using other GIS data. Although there are some studies for spatial characteristics of subsurface modeling, it is rather lack of being interoperable with GIS, considering geotechnical engineering facts. This is reason for difficulty of practical uses. In this study, we has developed subsurface spatial information model through extracting needed geotechnical engineering data from geotechnical information DB. The developed geotechnical information clustering program(GEOCL) has made a cluster of boring formation(and formation ratio), classification of layer, and strength characteristics of subsurface. The interpolation of boring data has been achieved through zonal kriging method in the consideration of spatial distribution of created cluster. Finally, we make a subsurface spatial information model to integrate with digital elevation model, and visualize 3-dimensional model by subsurface spatial information viewing program(SSIVIEW). We expect to strengthen application capacity of developed model in subsurface interpretation and foundation design of construction works.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.8C
• /
• pp.801-809
• /
• 2005

This paper proposes a new algorithm for improving the performance of the spatial filter which is the most important part of deinterlacing methods. The conventional edge-based algorithms are not satisfactory in deciding the exact edge direction which controls the performance of the interpolation. The proposed algorithm much increases the performance of the intrafield interpolation by finding exact edge directions based on the binary image. Edge directions are decided using 15 by 3 local window to find not only more accurate but also many low-angle edge directions. The proposed interpolation method upgrades the visual quality of the image by alleviating the misleading edge directions. Simulation results for various images show that the proposed method provides better performance than the existing methods do.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.5C
• /
• pp.514-520
• /
• 2009

This paper proposes a new deinterlacing algorithm which improves the performance of the spatial filter. Extracting exact edges is very important element of deinterlacing performance. So the proposed algorithm has interpolated locally adaptive-thresholded binary image, and extracted exact edges from the interpolated binary image. The values of pixels on edges extracted from binary image are interpolated using neighborhood lines on the same edge. With computer simulations for a variety of images, it is shown that the proposed algorithm is much better than traditional methods.

• Journal of Korean Society for Geospatial Information Science
• /
• v.9 no.1 s.17
• /
• pp.39-47
• /
• 2001

DTM(Digital Terrain Model) can play a key rule in a great number of the fields of construction Engineering. One of the most important application fields is to determine volume in that the total construction expenses is usually calculated through this. It therefore is necessary to the study on improving the precise of the determination using DTM on account of saving time and cost. On this study, 1:5000 topographic maps issued by NGI in 15 districts involved in Pusan city was digitalized to generate DTM at first. After this step, not only was the determination of the volume as well as readjusted area and height done for the sake of estimating the changable topography caused by cut & fill volume in future but also provided the model to calculate it as results. In addition, comparison among the interpolations, such as Inverse Distance Method and Nearest Neighbor, was respectively done to look over the differences of the volume estimated from each interpolation and also to find the most suitable method. As a result, the former yielded the largest values of area and the volume while the latter gave the smallest ones. Moreover, the values estimated on this study were closely similar to ones obtained by the government of Pusan.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.9
• /
• pp.2209-2215
• /
• 2014

This paper presents, a deinterlacing method by improving the Direction-Oriented Interpolation (DOI) technique. The technique is considered to be a very strong tool for intrafield-based deinterlacing. However, DOI has some problems such as long processing time, wrong edge detection in periodic pattern. To remedy this problem, we replace the full search in DOI by a two-step search to reduce processing time and introduces two additional processes to improve image quality. In the proposed method, the spatial direction vectors (SDVs) misread data are reconsidered to prevent them utilizing in the next interpolation step, resulting in an accurate deinterlacing method. We conduct experiments with ISO experimental images to compare the proposed method with the existing methods including line evarage (LA), edge-based line averaging (ELA), DOI, selective deinterlacing algorithm (SDA). Experimental results show the proposed method gives better performance in objective and subjective quality than existing deinterlacing methods.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2008.11a
• /
• pp.127-130
• /
• 2008

본 논문에서는 아날로그 TV에서 사용되는 인터레이스 영상을 디지털 디바이스에서 보다 우수하게 출력하기 위해 새로운 디인터레이싱 알고리듬을 제안 한다. 기존의 에지 기반의 라인 평균 방법의 경우 제한된 방향의 화소단위 상관도를 이용하기 때문에 잡음과 계조도 변화에 취약하였다. 또한 공간적 방향 벡터를 사용한 DOI방법은 영상 내 수평 에지가 강한 영역을 보간하는데 우수하지만 좌우 넓은 검색 영역으로 인한 잡음에 취약한 단점이 있었다. ED4D는 에지기반 라인 평균 방법과 공간적 방향 벡터를 적절히 사용하여 규칙적 에지 특성을 갖는 영역에 대한 에지 방향의 정확도를 높였다. 하지만, 참조 방향 및 화소 보간의 판별 기준이 $3{\times}2$ 윈도우로 고정되어 있기 때문에 초기 방향성 판단 기준과 수평 방향 에지 검출에 있어 정밀도가 떨어지는 문제점을 안고 있다. 제안하는 방법은 기존에 사용하던 $3{\times}2$ 윈도우에 $5{\times}2$ 윈도우를 추가적으로 적용하여 초기 방향성 판단 기준을 더 섬세하게 하였으며, 변형된 공간적 방향 벡터를 사용하여 넓은 검색영역으로 인한 잡음의 간섭을 줄였다. 실험결과를 통하여 제안한 방법이 기존의 방법에 비해 주관적 화질뿐만 아니라 객관적인 성능도 우수함을 알 수 있다.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.4
• /
• pp.89-96
• /
• 2009

In this paper, we propose an efficient deinterlacing algorithm which is an edge dependent interpolation based on edge direction refinement. The conventional edge dependent interpolation algorithms have a visually better performance than any other Intra-field deinterlacing algorithms. However they are very sensitive to noise due to the failure of estimating edge direction. In order to exactly detect edge direction, our method detects edge direction of around interpolated pixel and refines the edge direction using weighted median filter. Simulation results have shown the efficacy of the proposed method with significant improvement over the previous methods in terms of the objective PSNR quality as well as the subjective image quality.