• Smart Structures and Systems
• /
• 제28권6호
• /
• pp.779-789
• /
• 2021

Cracks in railway sleeper are an inevitable condition and has a significant influence on the safety of railway system. Although the technology of railway sleeper condition monitoring using machine learning (ML) models has been widely applied, the crack recognition accuracy is still in need of improvement. In this paper, a two-stage method using edge detection and convolutional neural network (CNN) is proposed to reduce the burden of computing for detecting cracks in railway sleepers with high accuracy. In the first stage, the edge detection is carried out by using the 3×3 neighborhood range algorithm to find out the possible crack areas, and a series of mathematical morphology operations are further used to eliminate the influence of noise targets to the edge detection results. In the second stage, a CNN model is employed to classify the results of edge detection. Through the analysis of abundant images of sleepers with cracks, it is proved that the cracks detected by the neighborhood range algorithm are superior to those detected by Sobel and Canny algorithms, which can be classified by proposed CNN model with high accuracy.

• 근관절건강학회지
• /
• 제7권2호
• /
• pp.241-257
• /
• 2000

Rheumatoid arthritis as one of the chronic illness requiring management in long period of time puts great burden to patients, their family and society. For patients with chronic illnesses, providing a social support is important and the most important source comes from spouses. Therefore we assessed burden of husbands of female rheumatoid arthritic patients and also found out the factors affecting burden. The sample of study was 107 female rheumatoid arthritic patients and their spouses. The tool of assessing spouses' burden was the revised version of subjective and objective parameters developed by Montgomery et al.(1985). The results are as follows: 1. General characteristics of patients and spouses: The mean age of the patients was 48 years. Educational level of patients was high school 41.1%. The mean age of the spouses was 51years. Educational level of spouses was mostly high school(40.2%) and college(29.9%) graduate. The mean marital period was 23.4years. Average income per month was 1,609,000 won. The average duration since diagnosis was 9.4years. As a therapy, 67.3% chose standard drug therapy. Average rating of discomfort by patient was 3.05(range 1-5) and that of severity was 3.48 and that of dependency was 2.58. The husband's rating of their spouses disease severity was 3.68. 2. Husbands' burden: The average burden in subjective items was 21.61(range 6-36) and objective items was 35.24(range 10-60). The average of total burden was 56.59(range 16-96). 3. Husband's total burden correlated with patient's age, educational level of patients, therapy method, patient's level of discomfort, patient's severity, patient's level of dependence, husband's recognition of level of severity in statistical level. Husband's objective burden correlated with patient's age, educational level of patient, patient's level of discomfort, husband's recognition of level of severity. Husband's subjective burden correlated with patient's age, educational level of patients, therapy method, patient's severity, patient's level of dependence, husband's recognition of level of severity. 4. Linear correlation analysis on burden: The husbands' total burden is explained in 37 7% by husband's recognition of level of severity and husband's age. The husbands' objective burden is explained in 31.2% by patient's level of dependence, husband's age, husband's recognition of level of severity. The husbands' subjective burden is explained in 26.7% by husband's recognition of level of severity and patient's age. In conclusion, husbands' level of burden is affected by many factors and therefore nursing strategy for relieving burden of middle aged husbands should be individualized taking these factors into consideration.

• 로봇학회논문지
• /
• 제4권4호
• /
• pp.257-264
• /
• 2009

This paper proposes a novel face detection method that finds tiny faces located at a long range even with low-resolution input images captured by a mobile robot. The proposed approach can locate extremely small-sized face regions of $12{\times}12$ pixels. We solve a tiny face detection problem by organizing a system that consists of multiple detectors including a mean-shift color tracker, short- and long-rage face detectors, and an omega shape detector. The proposed method adopts the long-range face detector that is well trained enough to detect tiny faces at a long range, and limiting its operation to only within a search region that is automatically determined by the mean-shift color tracker and the omega shape detector. By focusing on limiting the face search region as much as possible, the proposed method can accurately detect tiny faces at a long distance even with a low-resolution image, and decrease false positives sharply. According to the experimental results on realistic databases, the performance of the proposed approach is at a sufficiently practical level for various robot applications such as face recognition of non-cooperative users, human-following, and gesture recognition for long-range interaction.

• 한국정보통신학회논문지
• /
• 제15권8호
• /
• pp.1813-1819
• /
• 2011

본 연구에서 제안하는 위치인식시스템은 전파의 위상 및 크기를 이용하여 거리를 구하고 여기서 구한 거리 정보를 보다 정확하게 측정하기 위해서 비젼에 의한 영상 히스토그램 기법을 이용하여 보완하는 기술이다. 제안하는 기술은 거리측정용 무선송수신기로부터 송수신된 900Mhz대 RF 신호로부터 중간주파수인 450Khz의 아날로그 데이터를 디지털신호처리를 통하여 얻어내며, 여기서 얻어진 거리 정보에다 비젼에 의해 얻어진 거리를 상호 보완하여 보다 정확한 거리 정보를 획득한다. 측정된 거리의 평가를 위해서 실제거리와 측정된 거리를 비교 분석하고, 또한 평균처리 및 진폭특성을 통한 측정오차 개선 방법과 기존의 RF 신호만 이용하는 경우와 비교 검토한다.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2017년도 추계학술대회
• /
• pp.699-701
• /
• 2017

장거리 관측용 카메라의 일반적인 운용방법은 광각에서 표적에 대한 탐지를 하며, 망원으로 표적에 대한 인지/식별을 하게 된다. 탐지/인지거리 성능은 방산용 적외선카메라의 성능을 평가하는 중요한 항목이다. 탐지거리 성능이 증가하려면 카메라의 시야가 좁아져야 하고, 좁은 시야각으로 인하여 표적을 찾게 될 확률이 상대적으로 낮아지게 된다. 본 연구에서는 탐지거리 성능을 유지하면서 넓은 시야각을 제공하여 표적에 대한 탐색을 용이하게 할 수 있는 방안을 검토하였다. 그리고 M&S 및 최적화 설계를 통하여 시야 확장형 적외선카메라를 제작하고 시험한 결과를 정리하였다.

• 한국멀티미디어학회논문지
• /
• 제21권5호
• /
• pp.626-637
• /
• 2018

Human exchanges information not only through words, but also through body gesture or hand gesture. And they can be used to build effective interfaces in mobile, virtual reality, and augmented reality. The past 2D gesture recognition research had information loss caused by projecting 3D information in 2D. Since the recognition of the gesture in 3D is higher than 2D space in terms of recognition range, the complexity of gesture recognition increases. In this paper, we proposed a real-time gesture recognition deep learning model and application in 3D space using deep learning technique. First, in order to recognize the gesture in the 3D space, the data collection is performed using the unity game engine to construct and acquire data. Second, input vector normalization for learning 3D gesture recognition model is processed based on deep learning. Thirdly, the SELU(Scaled Exponential Linear Unit) function is applied to the neural network's active function for faster learning and better recognition performance. The proposed system is expected to be applicable to various fields such as rehabilitation cares, game applications, and virtual reality.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2015년도 춘계학술대회
• /
• pp.74-77
• /
• 2015

WiSee는 Wi-Fi(802.11n / ac)의 주파수를 이용하여 사용자의 제스처로 동작인식을 하는 기술이다. 현재 모션 인식방식은 전용 장치(리프모션, 키넥트)를 사용하고 있으며, 인식범위는 30cm~3.5m 이며, 인식범위가 좁고 인식률을 높이기 위해서는 제한적인 거리를 유지해야하는 불편함이 있다. 반면에 WiSee에서 사용하는 장비는 Wi-Fi가 사용가능한 장소라면 어디서든 동작인식을 할 수 있으며, 투과성도 기존인식방식에 비해 뛰어난 장점이 있다. 이에 본 논문에서는 WiSee의 동작과정과 최근동향을 살펴본다.

• 대한전자공학회논문지SP
• /
• 제40권6호
• /
• pp.31-40
• /
• 2003

대부분의 얼굴인식 시스템은 현재 2차원 영상을 기반으로 많은 분야에 응용되고 있다. 그러나 2차원 얼굴인식 시스템은 심하게 변화된 얼굴 포즈에 강인한 얼굴인식이 매우 어렵다. 이에 얼굴 포즈 추정은 정면 영상이 아닐 경우 인식률 향상을 위한 필수적인 과정이라 할 수 있다. 그러므로, 본 논문은 3차원 얼굴인식을 위한 새로운 얼굴 포즈 추정 방식을 제안한다 먼저 3차원 거리(range) 영상이 입력될 때 얼굴 곡선에 기반한 자동 얼굴 특징점 추출 기법을 적용한다. 추출된 특징점을 바탕으로 오류 보상 특이치 분해를 적용 한 새로운 3차원 얼굴 포즈 추정 방식을 제안한다. 특이치 분해를 이용하여 초기 회전각을 획득한 후 존재하는 오류를 보다 세밀하게 보상한다. 제안 알고리즘은 정규화된 3차원 얼굴 공간에서 추출된 특징점의 기하학적 위치를 이용하여 수행된다. 또한 3차원 얼굴인식을 위하여 3차원 최근접 이웃 분류기를 이용한 데이터베이스내에서 후보 얼굴을 선택하는 방식을 제안한다. 실험 결과를 통해 다양한 얼굴 포즈에 대하여 제안 알고리즘의 효율성과 타당성을 검증하였다.

• 보건의료산업학회지
• /
• 제5권3호
• /
• pp.13-23
• /
• 2011

This paper investigated the operating environment for the representative of each agency and the facility workers on the basis of analytical result of recognition changes of the operating environment changes under the operating the long-term care insurance. It was described plans to take positive effect on the operating as follows. The first, on the result of regression analysis, the service administrative range takes the biggest effect on the general recognition of executing the long-term care insurance off and on. The affirmative recognition of the service administrative range had the general recognition on the system be positive effect. But the operator of facility asserts that the care manager's professionalism related quality of service be strengthened. The second, on the result of regression analysis, in the financial accounting administrative it is revealed the more positive recognition it is, the more positive effects it has. From the difference verification of an operation size from operation subject, the small operation size and personal facility recognize the long term care insurance positively. On the other side the facilities where the operation size is big recognize the system negatively. The long-term care facility should rearrange a support program newly and the government needs to promote the donation activity, because it is needed to reduce the financial burden of facilities.

• 한국융합학회논문지
• /
• 제11권6호
• /
• pp.1-6
• /
• 2020

본 연구에서는 컴퓨터 비전의 분야 중 하나인 문자 인식에 관한 연구를 수행했다. 대표적인 문자인식 기법 중 하나인 광학식 문자 판독 기법의 경우 일정한 규격과 서식에서 벗어나게 되면 인식률이 떨어진다는 한계점이 있다. 따라서 본 연구에서는 딥 러닝 기법을 적용해 이러한 문제점을 해결하고자 한다. 또한 기존의 문자 인식 연구의 경우 대부분 영어 및 숫자 인식에 국한되어 있다. 따라서 본 연구는 한글 인식을 위한 딥 러닝 기반 문자 인식 알고리즘을 제시한다. 알고리즘은 1-NED 평가 방법에서 0.841의 점수를 얻었으며, 이는 영어 인식 결과와 비슷한 수치이다. 본 연구를 통해 딥 러닝 기반 한글 인식 알고리즘의 성능을 확인할 수 있으며, 이를 통해 향후 연구방향에 대해 제시한다.