• Journal of IKEEE
• /
• v.23 no.3
• /
• pp.777-784
• /
• 2019

A pre-fire awareness and automatic notification system are required because it is possible to minimize the damage if the fire situation is precisely detected after a fire occurs in a place where people are unusual or in a mountainous area. In this study, we developed a RaspberryPi-based fire recognition system using Faster-recurrent convolutional neural network (F-RCNN) and single shot multibox detector (SSD) and demonstrated a fire alarm system that works with power line communication. Image recognition was performed with a pie camera of RaspberryPi, and the detected fire image was transmitted to a monitoring PC through an inductive power line communication network. The frame rate per second (fps) for each learning model was 0.05 fps for Faster-RCNN and 1.4 fps for SSD. SSD was 28 times faster than F-RCNN.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.12
• /
• pp.1535-1541
• /
• 2019

To carry out safe and rapid decontamination in radiological accident areas, acquisition of various information on radiation sources is needed. In particular, to figure out the location and distribution of radiation sources is essential for rapid follow-up and removal of contaminants as well as minimizing worker damage. The radiation distribution detection device is used to obtain the position and distribution information of the radiation source. In the case of a radiation distribution detection device, a detection sensor unit is generally composed of a single sensor, and the detection range is limited due to the physical characteristics of the single sensor. We applied a calibration detector for controlling the detection sensitivity of a single sensor for radiation detection and improved the limited detection range of radiation dose rate. Also, gamma irradiation test confirmed the improvement of radiation distribution detection range.

• International Journal of Automotive Technology
• /
• v.6 no.1
• /
• pp.9-14
• /
• 2005

An experimental investigation has been carried out to reveal the atomization process of the diesel fuel spray. The spray injected through a single hole nozzle was taken by a camera on the opposite side of a stroboscope for macroscopic observation or a nanolite for microscopic observation. The effect of nozzle aspect ratio was analyzed with disintegration phenomena of the diesel spray. Based on the enlarged spray photograph, atomization process was observed in detail and further the spray cone angle was measured under various ambient pressures. The result shows that atomization of diesel spray in early stage of injection is mainly progressed in the vicinity of spray periphery region except the region close to the nozzle exit and spray head region. The spray cone angle is nearly constant under the pressurized condition, while it decreases with elapsing time under the atmospheric condition.

• Proceedings of the KSME Conference
• /
• 2007.05b
• /
• pp.2067-2072
• /
• 2007

Understanding of the impinging behavior of an electrically charged spray is essential in determining appropriate operating conditions for electro-spraying of paints, surface coating materials and insecticides. In the present work, as an initial step, the wall impact of an electrically charged droplet has been experimentally investigated. The charged drops were directed on the surface of a paraffin wax, and the impinging behavior was visualized and recorded using a CCD camera to identify the impingement regime. The spread-rebound boundary for the charged drop turned out to be smaller compared to that for an electrically neutral droplet under the same surface condition. The shift of the transition criterion is considered to be due to the discrepancy between the maximum spread ratio of the electrically charged droplet and that of the neutral droplet.

• Proceedings of the KSME Conference
• /
• 2007.05b
• /
• pp.2579-2584
• /
• 2007

A digital micro holographic particle tracking velocimetry (HPTV) system consisting of a high-speed camera and a single laser with acoustic optical modulator (AOM) chopper was established. The digital micro HPTV system was applied to water flow in a micro curved-tube for measuring instantaneous 3-D velocity field data consecutively. The micro curved-tube is using to reproduce the dorsal aorta or utilize in various lap-on-a-chip. The temporal evolution of a three-dimensional water flow in the micro curved-tube (the curvature, ${\kappa}$=1/${\phi}$, 2/${\phi}$, 4/${\phi}$, 8/${\phi}$) of 100 ${\mu}m$ and 300 ${\mu}m$ inner diameters was obtained and mean velocity field distribution was obtained by statistical-averaging the instantaneous velocity fields.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2004.04a
• /
• pp.177-182
• /
• 2004

This study presents the application of aerial photographs and KOMPSAT-1 Electro-Optical Camera(EOC) imagery in detecting the change of an urban area that has been rapidly growing. For the study, we used multi-time images which were acquired by two different sensors. For all of the images, the coordinate reference system and scale were first made identical through the 1st and 2nd geometric corrections and then image resampling were carried out to spatial resolution of 7m to detect changes under the same conditions. The Image Differencing was employed as a change detection technique. It was confirmed to be able to detect the changes of terrestrial surface like building, structure and road features from aerial photos and KOMPSAT EOC images with single band. The changes could be detected to some extent with the images acquired from different kinds of sensors as well as the same kinds of sensors.

• Proceedings of the KSR Conference
• /
• 2011.05a
• /
• pp.1161-1166
• /
• 2011

A camera is mounted vertically downwards viewing the people heads from the top. This configuration is successful in people counting technique especially when only a few isolated people pass through a counting region in a non-crowded situation. Thus, this paper describes object counting which detects and count moving people using mixture of gaussian and motion vector. This method is intended to estimates the number of people in outdoor environment. This method use single gaussian background modeling which is more robust an noise and has adaptiveness. The experimental results that is based on mixture of gaussian and motion vector is also helpful to design intelligent surveillance.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.11 no.4
• /
• pp.1-5
• /
• 2002

A 110 m diameter aspheric metal secondary mirror for a test model of an earth observation satellite camera was fsbricated by ultra-precision single point diamond turning (SPDT). Aluminum alloy for mirror substrates is known to be easily machinable, but not polishable due to its ductility. A harder material, Ni, is usually electrolessly coated on an A1 substrate to increase the surface hardness for optical polishing. Aspheric metal secondary mirror without a conventional polishing process, the surface roughness of Ra=10nm, and the form error of Ra=λ/12(λ=632.8nm) has been required. The purpose of this research is to find the optimum machining conditions for reflector cutting of electroless-Ni coated A1 alloy and apply the SPDT technique to the manufacturing of ultra precision optical components of metal aspheric reflector.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2004.10a
• /
• pp.737-741
• /
• 2004

A mobile robot system is developed which is remotely controlled by a haptic master called ‘PHANTOM’. The mobile robot has 4 ultrasonic sensors and single CCD camera which detects the distance from a mobile robot to obstacles in the environment and sends this information to a haptic master. For more convenient remote control, haptic rendering process is performed like viscosity forces and obstacle avoidance forces. In order to show the effectiveness of the developed system, we experiment that the mobile robot runs through the maze and the time is checked to complete the path of the maze with/without the haptic information. Through this repeated experiments, haptic information proves to be useful for remote control of a mobile robot.

• Proceedings of the KIEE Conference
• /
• 2008.10b
• /
• pp.339-340
• /
• 2008

로봇의 현재 위지 추적은 무인 로봇 자동 항법시스템의 중요 기술로 센서 데이터로부터 로봇의 위치를 결정하고 환경맵을 구성하는 것이다. 기존 방법으로는 초음파, 레이저 등의 거리 측정 센서를 이용해 로봇의 전역 위치를 찾는 방법과 스테레오 비전을 통한 방법이 개발되었다. 거리 측정 센서만으로 로봇위치 추적 알고리즘은 계산량이 감소하고 비용이 적게 들지만 센서오차율 및 환경장애에 따른 오류가 크다. 이에 반해 스테레오 비전 시스템은 3차원 공간영역을 정확히 측정할 수 있지만 계산량이 많아 고사양의 시스템을 요구하고 알고리즘 구현에 어려움이 있다. 따라서 본 논문에서는 단일 카메라 영상과 PSD(position sensitive device) 센서를 사용하여 로봇의 현재 위치를 추적하고 환경맵을 구성하여 자율이동이 가능한 시스템을 제안한다.