• The KIPS Transactions:PartC
• /
• v.9C no.1
• /
• pp.9-16
• /
• 2002

As existing analog video surveillance systems could save and retrieve data only in a limited space within short distance, it had many constraints in developing into various application systems. However, on the back of development of the Internet and computer technologies, digital video surveillance systems can be controlled from a remote location by web browser without space limits. Moreover, data compression and management technologies with Index Search algorithm make it possible to efficiently handling, storing, and retrieving a large amount of data and further motion detection algorithm enhances a recording speed and efficiency for a practical application, that is, a practical remote recordable video surveillance system using our efficient algorithms as mentioned, called WebCam. The WebCam server system can intelligently record and save video images digitized through efficient database management, monitor and control cameras in a remote place through user authentication, and search logs.

• Journal of Satellite, Information and Communications
• /
• v.8 no.2
• /
• pp.6-11
• /
• 2013

Recently sports science is various attempts to improve the athletes' performances. Above all they collect a results for the data and analyze the movement of the players after the game. Based on this, they are utilized to complement the vulnerability and how to improve. However, this way is not able to understand the movement a player and the flow of the game in real time. Because they are analyzed to match results based on the data. Therefore it is possible to managed for performance enhancement used to IT technology during the game in real-time.

• Journal of the Institute of Convergence Signal Processing
• /
• v.11 no.4
• /
• pp.332-337
• /
• 2010

In this paper, we propose G-Robot framework implemented with the fusion technology called RITS(Robot Technology & Information Technology System) for robot control and remote monitoring using the mobile phone. In our implemented system, the mobile phone mounted on the robot controls the robot and sends the images to the mobile phone of the user. We can monitor surrounding area of the robot with mobile phone and control the movement of the robot by sending the data between mobile-phones. Also, if the predefined situation occurs to the robot, the mobile phone on the robot sends the data to the mobile-phone of the user. From the experimental result, we can conclude that it's possible to control the robot and monitor surrounding area of the robot in real time in the region where the 3G(Generation) communication is possible. In addition, we can control the robot using the bluetooth instead of the mobile phone communication if the robot is in visual range.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.1197-1199
• /
• 2003

ROCSAT-2 mission is to daily image over Taiwan and the surrounding area for disaster monitoring, land use, and ocean surveillance during the 5-year mission lifetime. The satellite will be launched in December 2003 into its mission orbit, which is selected as a 14 rev/day repetitive Sun-synchronous orbit descending over (120 deg E, 24 deg N) and 9:45 a.m. over the equator with the minimum eccentricity. National Space Program Office (NSPO) is developing a ROCSAT-2 Image Processing System (IPS), which aims to provide real-time high quality image data for ROCSAT-2 mission. A simulated ROCSAT-2 image, based on Level 1B QuickBird Data, is generated for IPS verification. The test image is comprised of one panchromatic data and four multispectral data. The qualification process consists of four procedures: (a) QuickBird image processing, (b) generation of simulated ROCSAT-2 image in Generic Raw Level Data (GERALD) format, (c) ROCSAT-2 image processing, and (d) geometric error analysis. QuickBird standard photogrammetric parameters of a camera that models the imaging and optical system is used to calculate the latitude and longitude of each line and sample. The backward (inverse model) approach is applied to find the relationship between geodetic coordinate system (latitude, longitude) and image coordinate system (line, sample). The bilinear resampling method is used to generate the test image. Ground control points are used to evaluate the error for data processing. The data processing contains various coordinate system transformations using attitude quaternion and orbit elements. Through the qualification test process, it is verified that the IPS is capable of handling high-resolution image data with the accuracy of Level 2 processing within 500 m.

• Annual Conference of KIPS
• /
• 2014.04a
• /
• pp.811-814
• /
• 2014

일본 후쿠시마 제일 원자력발전소의 대지진/쓰나미에 이은 원자로 건물 수소폭발 사고의 수습 과정에서 사용후 핵연료 저장조에 보관되어 있는 핵연료의 안전문제가 대두되었다. 사용후 핵연료의 잔열 성분을 냉각시키고, 그리고 사용후 핵연료가 방출하는 고선량 방사선을 차폐시키기 위해서 일정 깊이 이상의 수조에 사용후 핵연료를 저장한다. 사용후 핵연료 저장조에 냉각수 공급이 중단되면, 사용후 핵연료의 고유 잔열에 의해 수조의 물이 증발하여 수위가 감소하게 된다. 계속해서 냉각수 공급이 되지 않으면, 사용후 핵연료의 잔열은 증가하게 되고, 수조의 물은 비등하여 증발은 가속화 된다. 사용후 핵연료 저장조의 수위가 고갈되면 고선량의 감마선이 방출된다. 수조의 수위가 정상적일 경우 사용후 핵연료 저장조의 공기중 감마선 선량율은 0.15mSv/h 이다. 수조의 수위가 사용후 핵연료 상부 꼭대기를 기준으로 2m, 1m, 및 0m (핵연료 노출) 로 감소하게 되면, 사용후 핵연료 저장조의 공기중 감마선 선량율은 500mSv/h, 50Sv/h, 및 5kSv/h 로, 급격히 증가한다. 본 논문에서는 사용후 핵연료 저장조 감시카메라의 관측 성능을 평가하기 위해, 고성능 칼라 CCD 카메라에 대해서 1 kGy/h 의 고선량율로 감마선 조사실험을 수행하였다. 이에 대한 실험결과를 기술한다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.4
• /
• pp.580-585
• /
• 2010

In this paper, The object Tracking System is designed by SOPC based Nios II embedded processor and C2H compiler. And this system using single PTZ camera can effectively control IPs in the platform of SOPC based Nios II Embedded Processor and creating IP by C2H(C-To-Hardware) compiler for image-in/output, image-processing and devices of communication that can supply various monitoring information to network or serial. Accordingly, Special quality and processing speed of object tracking using high-quality algorism in the system is improved by hardware/software programming methods.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.2
• /
• pp.401-406
• /
• 2008

Fall event detection is one of the most common problems for elderly people, especially those living alone because falls result in serious injuries such as joint dislocations, fractures, severe head injuries or even death. In order to prevent falls or fall-related injuries, several previous methods based on video sensor showed low fall detection rates in recent years. To improve this problem and outperform the system performance, this paper presented a novel approach for fall event detection in the elderly using a subtraction between successive difference images and temporal templates in real time environment. The proposed algorithm obtained the successful detection rate of 96.43% and the low false positive rate of 3.125% even though the low-quality video sequences are obtained by a USB PC camera sensor. The experimental results have shown very promising performance in terms of high detection rate and low false positive rate.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.5
• /
• pp.251-256
• /
• 2021

Unlike general cameras, a high-speed camera capable of capturing a large number of frames per second can enable the advancement of some image processing technologies that have been limited so far. This paper proposes a method of removing undesirable noise from an high-speed input color image, and then detecting a human face from the noise-free image. In this paper, noise pixels included in the ultrafast input image are first removed by applying a bidirectional filter. Then, using RetinaFace, a region representing the person's personal information is robustly detected from the image where noise was removed. The experimental results show that the described algorithm removes noise from the input image and then robustly detects a human face using the generated model. The model-based face-detection method presented in this paper is expected to be used as basic technology for many practical application fields related to image processing and pattern recognition, such as indoor and outdoor building monitoring, door opening and closing management, and mobile biometric authentication.

• The Journal of Korean Institute of Next Generation Computing
• /
• v.15 no.6
• /
• pp.7-14
• /
• 2019

The automatic monitoring and detection of crowd behavior in the surveillance videos has obtained significant attention in the field of computer vision due to its vast applications such as security, safety and protection of assets etc. Also, the field of crowd analysis is growing upwards in the research community. For this purpose, it is very necessary to detect and analyze the crowd behavior. In this paper, we proposed a deep learning-based method which detects abnormal activities in surveillance cameras installed in a smart city. A fine-tuned VGG-16 model is trained on publicly available benchmark crowd dataset and is tested on real-time streaming. The CCTV camera captures the video stream, when abnormal activity is detected, an alert is generated and is sent to the nearest police station to take immediate action before further loss. We experimentally have proven that the proposed method outperforms over the existing state-of-the-art techniques.

• Advances in Computational Design
• /
• v.4 no.2
• /
• pp.73-90
• /
• 2019

The growth in the number of single-member households is a critical issue worldwide, especially among the elderly. For those living alone, who may be unaware of their health status or routines that could improve their health, a continuous healthcare monitoring system could provide valuable feedback. Assessing the performance adequacy of activities of daily living (ADL) can serve as a measure of an individual's health status; previous research has focused on determining a person's daily activities and extracting the most frequently performed behavioral patterns using camera recordings or wearable sensing techniques. However, existing methods used to extract common patterns of an occupant's activities in the home fail to address the spatio-temporal dimensions of human activities simultaneously. Though multiple sequence alignment (MSA) offers some advantages - such as inherent containment of the spatio-temporal data in sequence format, and rapid identification of hidden patterns - MSA has rarely been used to extract in-home ADL routines. This research proposes a method to extract a household occupant's ADL routines from a cumulative spatio-temporal data log of occupancy collected using a non-intrusive method (i.e., a tomographic motion detection system). The findings from an occupant's 28-day spatio-temporal activity log demonstrate the capacity of the proposed approach to identify routine patterns of an occupant's daily activities and to reveal the order, duration, and frequency of routine activities. Routine ADL patterns identified from the proposed approach are expected to provide a basis for detecting/evaluating abrupt or gradual changes of an occupant's ADL patterns that result from a physical or mental disorder, and can offer valuable information for home automation applications by enabling the prediction of ADL patterns.