• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.11a
• /
• pp.1028-1030
• /
• 2017

최근 스마트 기기에 대한 관심이 지속적으로 증가함에 따라 다양한 스마트 기기가 출시되고 그에 대한 연구가 활발히 진행되고 있다. 기존 스마트 기기에 탑재된 모션 센서에 관한 연구 대부분은 사용자의 움직임을 이용한 게임 연구에 치우쳐 있다. 본 논문은 사용자 모션의 시각화라는 접근을 통해 사용자의 모션을 직관적으로 볼 수 있도록 하였다. 안드로이드 기반 모바일 기기에 탑재되어 있는 모션 센서 중 방향 센서를 이용하여 사용자 모션에 대한 데이터를 수집하고 이를 시각화 알고리즘을 통해 시각화 한다. 시각화한 결과를 손 글씨 숫자 이미지의 대형 데이터베이스 기반 머신러닝을 활용하여 분석하고 사용자의 모션을 인식할 수 있다는 결과를 확인했다.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.2
• /
• pp.31-37
• /
• 2014

In conventional methods for car navigational path detection using Hough transform, navigational path deviation of a car is decided in car navigational images with simple background. But in case of car navigational images having complex background with obstacles on the road, shadows, other cars, and so on, it is very difficult to detect navigational path because these obstacles obstruct correct detection of car navigational path. In this paper, I proposed an effective navigational path detection method having better performance than conventional navigational path detection methods using Hough transform only, and fuzzy binarization method and Canny mask are applied in the proposed method for the better performance. In order to evaluate the performance of the proposed method, I experimented with 20 car navigational images and verified the proposed method is more effective for detection of navigational path.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2002.12a
• /
• pp.313-316
• /
• 2002

이동 물체의 이동 거리 추적이나 대상 물체의 인식과 판별 물체의 특징 추출과 같은 응용분야에서 컴퓨터(Computer)와 비젼시스템(vision system)을 이용한 영상 데이터 처리 분야에 대한 이용률이 증가하면서, 그에 따른 연구가 활발히 진행되고 있다. 따라서 CCD 카메라(Charge-Couple Device Camera)로부터 입력된 그레이 레벨(Gray Level)의 영상을 입력받아 처리과정을 거쳐 위치정보를 전송하는 과정에서 정확한 정보를 얻기 위한 전처리 과정 방법을 제안하고, 실제 시스템에 적용한 결과를 제시한다. 여기서 영상의 전처리 과정 중 입력 영상에서 불필요한 부분을 제거하거나, 배경과 대상물의 분리, 내포된 잡음을 없애기 위하여 흔히 이진화 방법을 많이 사용한다 특히 이진화 과정에서 그레이 레벨의 입력영상에서 히스토그램(histogram) 정보를 이용하여 영상의 이진화시의 임계값을 찾는 것은 아주 중요한 요인이다 따라서 본 논문에서는 신경회로망을 이용하여 실시간으로 CCD 카메라를 통하여 입력되는 그레이 레벨의 입력 영상에 대하여 동적으로 적당한 임계값을 .찾는 방법을 제안하고자한다. 또한 제안한 신경회로망을 이용한 임계값 추출 알고리즘(algorithms)을 구현한 시스템(system)에 적용하여 일반적인 방법과 비교 검토하고 응용 가능성을 확인한다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.7 no.6
• /
• pp.1142-1148
• /
• 2006

Actually, a present traffic accident detection system is subsisting limitation of accurate distinction under the crowded condition at intersection because the system depend upon mainly the image information at intersection and digital image processing techniques nearly all. To complement this insufficiency, this article aims to estimate the level of present technology and a realistic possibility by analyzing the acoustic characteristic of crash sound that we have to investigate fur improvement of traffic accident detection rate at intersection. The skid sound of traffic accident was showed the special pattern at 1[KHz])$\sim$3[KHz] bandwidth when vehicles are almost never operated in and around intersection. Also, the frequency bandwidth of vehicle crash sound was showed sound pressure difference over 30[dB] higher than when there is no occurrence of traffic accident below 500[Hz].

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.1384-1387
• /
• 2015

고령화 사회로 진입하면서 노인들은 노화과정에 의한 보행능력의 감소 및 근력 약화와 같은 신체적 변화로 인해 잦은 낙상을 경험한다. 이에 따라 낙상 사고를 감지하는 연구가 활발히 진행되고 있다. 낙상은 사전 예방도 중요하지만 사고 발생 후의 신속한 대처도 중요하다. 낙상을 감지하고 의료진에게 즉시 낙상정보를 제공하여 후속적 조치를 취하는 것은 사고 후 대처의 핵심이다. 본 논문에서는 스마트폰 환경에서 사용자의 낙상 후 방향을 판별하기 위해 두 가지 센서 데이터의 특정 값들을 추출하였으며, 이에 5 가지 기계학습 알고리즘을 적용하였다. 사용자는 스마트폰을 착용한 상태로 전후좌우 4 방향 낙상 실험을 진행하며 스마트폰 내에 내장된 3 축 가속도 센서와 3 축 자이로 센서값을 측정한다. 피험자 11 명을 대상으로 낙상 실험 결과, 5 가지의 분류기 중 k-NN에서 98.6%의 인식률을 나타내었다. 뽑아낸 특징 값과 분류 알고리즘은 낙상의 방향 검출에 유용한 것으로 판단된다.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.10
• /
• pp.53-59
• /
• 2021

In this paper, we propose a system that can perform dumbbell exercise by recognizing the weight of dumbbells without wearing and device. With the development of virtual reality technnology, many studies are being conducted to simulate the pysical feedback of the real world in the virtual world. Accurate motion recognition is important to the elderly for rehabilitation exercises. They cannot lift heavy dumbbells. For rehabilitation exercise, correct body movement according to an appropriate weight must be performed. We use a machine learning algorithm for the accuracy of motion data input in real time. As an experiment, we was test three types of bicep, double, shoulder exercise and verified accuracy of exercise. In addition, we made a virtual gym game to actually apply these exercise in virtual reality.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.5
• /
• pp.95-102
• /
• 2021

The urinalysis, which is universally accessible to the general public, has disadvantages of being less objective using sight and purchasing a separate portable urinalysis machine. However, due to the high penetration rate and performance improvement of smartphone created by the development of mobile communication technology, research on urinalysis services using smartphone has been conducted. In this paper, a new urinalysis screening application based on smartphone was developed by supplementing the limitations of the previously studied urinalysis services. The key technology of the application is urinalysis recognition algorithm and urinalysis pad color determination algorithm through image-processing and contour detection. In order to confirm the performance of the developed application, urinalysis strip was photographed and analyzed from various backgrounds and angles.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.05a
• /
• pp.826-828
• /
• 2014

Recently trend of product is miniaturization. As a result, We need products surface as well as products internal defect inspection. Generally, Inspection products in production process uses a lot of optical inspection. However, This is difficult to internal inspection of products. We used optical device instead of X-ray generator. At the same time, We have developed system to determine the product defect. First, obtain X-ray image from Machine vision function. Next, Measured value is recognize suitability within error range. otherwise recognize defect. Results presence of defective products can be stored by user.

• Journal of Korean Society of Steel Construction
• /
• v.17 no.1 s.74
• /
• pp.1-11
• /
• 2005

A bi-level damage detection algorithm that utilizes the dynamic responses of the structure as input and neural network (NN) as pattern classifier is presented. Signal anomaly index (SAI) is proposed to express the amount of changes in the shape of frequency response functions (FRF) or strain frequency response function (SFRF). SAI is calculated using the acceleration and dynamic strain responses acquired from intact and damaged states of the structure. In a bi-level damage identification algorithm, the presence of damage is first identified from the magnitude of the SAI value, then the location of the damage is identified using the pattern recognition capability of NN. The proposed algorithm is applied to an experimental model bridge to demonstrate the feasibility of the algorithm. Numerically simulated signals are used for training the NN, and experimentally-acquired signals are used to test the NN. The results of this example application suggest that the SAI-based pattern recognition approach may be applied to the structural health monitoring system for a real bridge.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.236-238
• /
• 2022

According to the current Road Traffic Act, the 2020 amendment bill is currently in effect as a system that designates vehicle types for each lane for the purpose of securing road use efficiency and traffic safety. When comparing the number of traffic accident fatalities per 10,000 vehicles in Germany and Korea, the number of traffic accident deaths in Germany is significantly lower than in Korea. The representative case of the German autobahn, which did not impose a speed limit, suggests that Korea's speeding laws are not the only answer to reducing the accident rate. The designated lane system, which is observed in accordance with the keep right principle of the Autobahn Expressway, plays a major role in reducing traffic accidents. Based on this fact, we propose a traffic enforcement system to crack down on vehicles violating the designated lane system and improve the compliance rate. We develop a designated lane enforcement system that recognizes vehicle types using Yolo5, a deep learning object recognition model, recognizes license plates and lanes using OpenCV, and stores the extracted data in the server to determine whether or not laws are violated.Accordingly, it is expected that there will be an effect of reducing the traffic accident rate through the improvement of driver's awareness and compliance rate.