• Journal of Welding and Joining
• /
• 제35권3호
• /
• pp.75-81
• /
• 2017

Recently in the welding field, the establishment of unmanned and automated systems are rapidly developing. Accurate interpretation of the welding phenomenon is applied a number of monitoring systems. In this paper, butt welding (6t) type I using Plasma-MIG welding was carried out. And we evaluated characteristics of the Al-5083 aluminium alloy in Plasma-MIG hybrid welding. Process variables including the plasma current, MIG voltage, wire feeding rate and the welding speed were used. Butt welding was conducted 1 pass. Argon gas was used as the protective gas that results from the experiment were able to achieve full penetration. In addition to monitoring the welding process occurring during MIG welding current, welding votage and Plasma current, voltage were collected in real time, the photodiode and CCD cameras observing the phenomenon that the welding is in progress were measured using a quantity of light.

• 대한원격탐사학회지
• /
• 제17권2호
• /
• pp.121-129
• /
• 2001

A DEM(digital elevation model) is generated from a SPOT panchromatic stereo-pair using automated algorithms over a 8 km$\times$10 km region around Mokpo city. The aims are to continue the accuracy assessment over diverse conditions and to examine the applicability of a SPOT DEM for coastal disaster monitoring. The accuracy is assessed with respect to three reference data sets: 10 global positioning system records, 19 leveling data, and 1:50,000 topography map. The planimetric error is 10.6m r.m.s. and the elevation erroer ranges from 12.4m to 14.4m r.m.s.. The DEM accuracy of the flat Mokpo region is consistent with that over a mountainous area, which supports the robustness of the algorithms. It was found that coordinate transformation errors are significant at a few meters when using the data from leveling and topographic maps. The error budget is greater than the requirements for coastal disaster monitoring. Exploiting that a sub-scene is used, the affine transformation improves the accuracy by 50% during the camera modeling.

• 국제학술발표논문집
• /
• The 2th International Conference on Construction Engineering and Project Management
• /
• pp.50-60
• /
• 2007

The endeavor of this paper focuses on designing a monitoring system to provide a cost-effective solution on quality assurance for construction projects. The construction site monitoring system integrates a long-range wireless network, network cameras, and a web-based collaborative platform. The users of the system could obtain the most updated status of construction sites, such as behaviors of workers, project progress, and site events anywhere with Internet connectivity. It was carefully configured in order to maintain the reliability under the reactive conditions of the construction sites. This paper reports the architecture of the monitoring system and reviews the related technologies. The system has been implemented and tested on a construction site and promising results were obtained.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2021년도 봄 학술논문 발표대회
• /
• pp.40-41
• /
• 2021

The construction industry has the highest occupational accidents/injuries among all industries. Korean government installed surveillance camera systems at construction sites to reduce occupational accident rates. Construction safety managers are monitoring potential hazards at the sites through surveillance system; however, the human capability of monitoring surveillance system with their own eyes has critical issues. Therefore, this study proposed to build a deep learning-based safety monitoring system that can obtain information on the recognition, location, identification of workers and heavy equipment in the construction sites by applying multiple-object tracking with instance segmentation. To evaluate the system's performance, we utilized the MS COCO and MOT challenge metrics. These results present that it is optimal for efficiently automating monitoring surveillance system task at construction sites.

• 조명전기설비학회논문지
• /
• 제18권1호
• /
• pp.137-145
• /
• 2004

본 논문은 평행식 스테레오 영상감시 시스템을 이용하여 3차원 공간에서 다중 이동물체를 검출하고, 카메라에서 이동 물체까지의 거리를 측정하는 알고리즘을 제안하였다. 스테레오 영상감시 시스템의 좌, 우측 영상을 입력을 받아 적응형 임계값과 화소귀납 알고리즘(PRA, pixel recursive algorithm)을 사용하여 다중 이동물체 영역을 추출하였다. 그리고 각각의 물체영역을 윈도우 마스크로 검출하고, 다중 이동물체 각각의 위치좌표와 스테레오 시차를 구하였다. 이 시차와 스테레오 비전 시스템의 특성 및 삼각 함수를 이용하여 다중 이동물체의 거리를 측정하였다. 실험결과 거리측정 오차도 7.28％이내에 존재하였으며, 따라서 제안한 알고리즘을 이용하여 시스템을 구현할 경우 스테레오 방범 시스템, 자율 이동로봇 및 스테레오 원격제어 시스템 등에 응용될 수 있을 것이다.

• 대한기계학회논문집B
• /
• 제39권2호
• /
• pp.199-206
• /
• 2015

본 연구에서는 인공신경망을 이용하여 배관이나 배관요소의 작동상태를 예측할 수 있는 진단방법을 제안한다. 입자영상유속계 기술을 이용하여 얻어진 배관의 검사부위의 진동에 의한 이동량을 인공신경망의 학습용으로 사용한다. 측정시스템은 카메라, 조명, 인공신경망이 탑재된 호스트컴퓨터로 구성된다. 구축된 모니터링시스템이 제대로 작동하는지 이미 알고 있는 진동원(2개의 휴대폰)에 대하여 적용하였다. 진동가속도의 최소값, 최대값, 평균값을 인공신경망의 학습에 사용해 본 결과, 평균값이 진동상태의 실시간 모니터링에 적합함을 확인하였다. 구축된 진단시스템은 실제 가스배관의 작동상태에 대하여 모니터링 가능함이 확인되었다.

• 대한기계학회논문집A
• /
• 제34권10호
• /
• pp.1351-1357
• /
• 2010

우리나라 주요하천의 수질오염감시를 목적으로 물벼룩을 이용한 생물감시장치가 설치, 운용되고 있다. 기기 목적상 유해물질에 대해 신뢰성 있는 신속한 독성경보를 내릴 수 있어야 하고, 무인원격측정기기이므로 계절별, 연간 하천의 물리적인 변화에도 측정의 신뢰성이 확보되어야 한다. 국내에 운영중인 장비는 물벼룩의 단위시간당 뛰는 횟수(Impulse)를 측정하는 방법과 유영형태를 분석하여 독성지수(Toxicity)로 나타내는 방법이 있다. 두 장비가 동일한 조건에서 운전되었음에도 가동률과 긴급점검횟수가 다르게 나타났으며 원인은 용기 내 기포발생과 압력차이 등 여러 가지가 있다. 본 연구의 목적은 기포와 미시적인 압력의 영향을 감소시켜 측정의 불확실성을 줄이는 것이고, 나아가 생물감시장치가 어떤 환경에 설치되더라도 수질오염감시의 목적을 정상적으로 달성하는 데 기여하는 것이다.

• International journal of advanced smart convergence
• /
• 제9권1호
• /
• pp.63-69
• /
• 2020

The rapid development in modern industrialization pollutant the water and atmospheric air across the globe that have a major impact on the human and livings health. In worldwide, every country government increasing the importance to improve the outdoor air pollution monitoring and control to provide quality of life and prevent the citizens and livings life from hazard disease. We proposed the environmental dust level detection method for outdoor facilities using sensor fusion technology to measure precise micro-dust level and monitor in realtime. In this proposed approach use the camera sensor and commercial dust level sensor data to predict the micro-dust level with data fusion method. The camera sensor based dust level detection uses the optical flow based machine learning method to detect the dust level and then fused with commercial dust level sensor data to predict the precise micro-dust level of the outdoor facilities and send the dust level informations to the outdoor air pollution monitoring system. The proposed method implemented on raspberry pi based open-source hardware with Internet-of-Things (IoT) framework and evaluated the performance of the system in realtime. The experimental results confirm that the proposed micro-dust level detection is precise and reliable in sensing the air dust and pollution, which helps to indicate the change in the air pollution more precisely than the commercial sensor based method in some extent.

• Journal of Forest and Environmental Science
• /
• 제38권2호
• /
• pp.128-132
• /
• 2022

Wild boars (Sus scrofa) not only cause crop damage and human casualties, but also facilitate the spread of many infectious diseases in domestic animals and humans. To determine the efficiency of a fencing system in blocking the movement of wild boars, long-term monitoring was performed in a fenced area in Bukhansan National Park using camera traps. Upon monitoring for a period of 46 months, there was a 72.6% reduction in the number of wild boar appearances in the fence-enclosed area, compared to that in the unenclosed area. For 20 months after the fence installation, the blocking effect of the fence was effective enough to reduce the appearance of wild boars by 92.6% in the fence-enclosed area, compared to that in the unenclosed area. The blocking effect of the fence remained effective for 20 months after its installation, after which its effectiveness decreased. Maintaining a fence for a long time is likely to lead to habitat fragmentation. It can also block the movement of other wild animals, including the endangered species - the long-tailed goral. This study suggests a 20-month retention period for the fences installed to inhibit the movement of wild boars in wide forests such as Gangwon-do in South Korea. To identify how long the blocking effect of the fences lasts, further studies are needed focusing on the length and height of the fence, and the conditions of the ground surface.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2012년도 춘계학술대회
• /
• pp.327-330
• /
• 2012

도시의 급격한 발전으로 공사의 증가가 증가하게 되고 이동 차량 또한 증가 하게 된다. 이는 자연히 시각 장애인들의 보행을 점점 더 어렵게 만든다. 이러한 어려움을 해결하고자 Android 기반의 Portable Navigation System을 도입하여 시각 장애인의 보행을 돕고, 서비스 센터에서 시각 장애인의 이동을 실시간으로 모니터링 하여서 시각 장애인의 보행에 도움을 주고자 한다. 노인이 서비스 센터에 배치되어 노인 인구 증가 문제의 해소 방안도 제공한다. 시각 장애인이 들고 다닐 수 있는 형태의 Android 기반의 Portable Navigation System은 GPS, Camera, Audio, wifi를 가지고 있어, GPS위치 정보와 Camera 영상 정보를 실시간으로 wifi망을 이용해 서비스 센터로 전송을 하여 주고, 서비스 센터에서 시각 장애인의 GPS Location 정보를 바탕으로 그 위치를 지도에 표시하고, Camera 영상 정보로 시각 장애인이 바라보고 있는 곳의 상황을 모니터링 하며, Audio를 통해, 실시간으로 대화를 통해서 길안내 해주는 Navigation System이다.