• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2000.11a
• /
• pp.89-92
• /
• 2000

Laser claddmg 1s thc deposition of material on the surface of a part or workpiece. Cladding of metals produces a 100% dense metallurgically-bonded coating with minimal dilution for enhanced corrosion, abrasion and wear resistance. Despite of minimal heat Input and reduced processing time, cladding quality 1s affected by various process condition such as laser power and feed rate. Therefore, it is necessary to develop the momtoring and control methods of laser cladding process for the best cladding quality. In this paper, laser cladding monitoring system using CCD camera for measuring cladding pool shape, and photo-diode sensor for detecting optical signal emitted from the cladding front is introduced The variables extracted using this system can be apphed to control the laser cladding system to achieve the best claddmg results..

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2003.06a
• /
• pp.955-958
• /
• 2003

Strip top mark is one of the major problem areas in hot strip coiling operation. The key for good coiling is having a precise detection instrument of strip head end and an understanding of QOC(quick open control) control algorithm and mechanism. Therefore, this study aims at developing QOC monitoring system that is useful for avoiding strip top mark at coiling process. In this study, strip movement between mandrel and unit roll(wrapper roll) was thoroughly studied using high speed camera. The monitoring system was developed to calculate QOC open time and to estimate optimal open time values for good coiling operation. Its performance has been proven by extensive field tests on downcoiler of #2 Hot Strip Mill Line in Pohang Works.

• Proceedings of the KSR Conference
• /
• 2005.11a
• /
• pp.915-920
• /
• 2005

Passenger safety is a primary concern of railway system but, it has been urgent issue that dozens of people are killed every year when they fall off from train platforms. Recently, advancements in IT have enabled applying vision sensors to railway environments, such as CCTV and various camera sensors. The objective of this work is to propose technical and system requirements for establishing intelligent monitoring system using camera equipments in urban transit system. We suppose the system is to determine automatically and in real-time whether anyone or anything is in monitoring area. To achieve the goal, we analyze recent image processing technologies for detection and recognition, and suggest possible direction of system development for applying urban transit system. According to the results, we expect the proposed system requirements will playa key role for establishing highly intelligent monitoring system in railway.

• Proceedings of the KSR Conference
• /
• 2008.11b
• /
• pp.1354-1359
• /
• 2008

In this paper, we propose a vision based passenger monitoring system for passenger's safety in railway station. Since 2005, Korea Railroad Research Institute (KRRI) has developed a vision based monitoring system, funded by Korean government, for passenger's safety in railway station. The proposed system uses various types of sensors, such as, stereo camera, thermal-camera and infrared sensor, in order to detects danger situations in platform area. Especially, detection process of the system exploits the stereo vision algorithm to improve detection accuracy. The paper describes the overall system configuration and proposed detection algorithm, and then verifies the system performance with extensive experimental results in a real station environment.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.14 no.1
• /
• pp.73-83
• /
• 2011

The opening status of Saemangeum sluice gate is an important factor to the coastal water qualities near Saemangeum dikes. The sluice gate opening information is important in analysing current velocity and water quality data measured at the Saemanguem observation tower as well as in determining boundary conditions of numerical simulation for coastal environment outside Saemangeum dikes. This study establishes unmanned camera monitoring system on Saemangeum observation tower using mini notebook and digital camera, and extracts information on the opening status from images automatically. Images are analysed using variance difference of images together with edge detection techniques in order to get correct information.

• Proceedings of the KOSOMBE Conference
• /
• v.1997 no.11
• /
• pp.475-477
• /
• 1997

We have analyzed the fluorescence image obtaining from green fluorescence protein (GFP). In order to monitor the fluorescence of specific gene, we used the amyloid precursor protein promoter which has been known to act as a major role in the development of Alzheimer's disease. The promoter from - 3.0 kb to + 100 base pair was inserted into the gene expression monitoring GFP vector purchased from Clontech. This construct was transfected into the PC 12 and fibroblast cells and the fluorescence image was captured by two kinds of methods. One is using cheaper CCD camera and other is SIT-CCD camera. or the higher sensitivity of the fluorescence image, we developed the multiple image grabbing program. As a results, the fluorescence image by conventional CCD camera have the similar sensitivity compared with that of the SIT-camera by applying the multiple image grabbing programs. By this system. it will be possible to construct the fluorescence monitoring system with lower cost. And gene expression in real time by fluorescence image will be possible without changing the fluorescence images.

• International Journal of Highway Engineering
• /
• v.20 no.1
• /
• pp.127-135
• /
• 2018

PURPOSES : Traffic cameras have been installed to reduce traffic accidents. The effectiveness of traffic cameras has been proved by dozens of studies, but recently questions over its effectiveness have been raised by a series of studies. In this study, the effectiveness of traffic cameras was analyzed with a focus on different road environments. METHODS : The effectiveness of the traffic cameras was analyzed by extracting the occurence frequency before and after camera installation. The effect of reduction was analyzed comprehensively considering the installation position, monitoring direction, and surrounding environment of traffic cameras. RESULTS : The result of this study is as follows. First, the installation of cameras in an area with relatively low accidental traffic was more effective. Secondly, the effect of camera installation on car-to-pedestrian collisions was better than that of car-to-car collisions. Thirdly, accidents tended to occur more frequently when cameras were installed in front of the accident-prone owing to the negative spill-over effect. CONCLUSIONS : The result can be used to guide placement of traffic cameras. Moreover, the installation of cameras with consideration of the road environment is expected to contribute to a reduction in traffic fatalities.

• Journal of Sensor Science and Technology
• /
• v.29 no.3
• /
• pp.194-200
• /
• 2020

Human detection is an important aspect in many video-based sensing and monitoring systems. Studies have been actively conducted for the automatic detection of humans in camera images, and various methods have been proposed. However, there are still problems in terms of performance and computational cost. In this paper, we describe a method for efficient human detection in the field of view of a camera, which may be static or moving, through multiple processing steps. A detection line is designated at the position where a human appears first in a sensing area, and only the one-dimensional gray pixel values of the line are monitored. If any noticeable change occurs in the detection line, corner detection and optical flow computation are performed in the vicinity of the detection line to confirm the change. When significant changes are observed in the corner numbers and optical flow vectors, the final determination of human presence in the monitoring area is performed using the Histograms of Oriented Gradients method and a Support Vector Machine. The proposed method requires processing only specific small areas of two consecutive gray images. Furthermore, this method enables operation not only in a static condition with a fixed camera, but also in a dynamic condition such as an operation using a camera attached to a moving vehicle.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.46-46
• /
• 2000

A quadruped monitoring robot is introduced. The robot has several features that poses arbitrary position thanks to a 4-wheel hive mechanism, transmits an image and command data via RF wireless communication, and moreover, the imaged date are transferred through a network communication. The robot plays a role in monitoring what is happening around the robot and covers wide range due to a moving camera operated by the 4-wheel mechanism. The robot system can be applied k versatile models based the distinguished techniques introduced in this paper

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2008.06a
• /
• pp.529-530
• /
• 2008