• 해양환경안전학회지
• /
• 제29권4호
• /
• pp.389-394
• /
• 2023

근래 산업은 기계 자동화로 변화하고 있는 추세이며, 선박도 센서를 통해 기기 정보를 디지털 정보로 얻는다. 하지만 선박은 기기상태 점검을 위해 선원들이 정해진 시간마다 기관실을 순찰하며 기기들의 정보를 아날로그 게이지를 통해 확인하는데, 이는 순찰 중에 선원에게 발생할 수 있는 모든 안전 위험은 물론 시간과 기회비용 또한 소모된다. 자율이동로봇을 이용한 기관실 순찰 방법은 선원의 안전 위험은 물론 시간과 기회비용도 소모되지 않기 때문에 해결책으로 활발히 연구 중이다. 자율이동로봇을 이용한 아날로그 게이지 판독은 로봇이 게이지를 인식하기 위한 디지털화가 필요하다. 이를 위해 본 연구에서는 이미지 처리를 이용하였다. 아날로그 게이지 이미지는 이미지 전처리를 통해 노이즈 제거 및 특징을 부각 시켰다. 이미지 전처리를 완료한 이미지는 이미지 처리를 통해 아날로그 게이지의 중심점, 지침점, 최소값 및 최대값을 검출하였다. 이 점들을 연결한 직선을 통해 최소값부터 최대값까지의 각도 및 최소값부터 지침점까지의 각도를 획득하였다. 각도는 수식을 통해 현재 아날로그 게이지가 나타내고 있는 값을 디지털화하여 나타내었다. 실험을 통해 이미지 처리를 통한 아날로그 게이지의 디지털화가 잘되어 게이지의 현재 지시값을 근사하게 나타냄을 확인할 수 있었다. 본 알고리즘을 순찰로봇에 적용한다면 기관실 순찰을 위한 선원의 안전 위험 및 시간과 기회비용까지 보전 할 수 있을 것으로 사료된다.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2011년도 정기총회 및 추계학술대회 논문집
• /
• pp.2762-2767
• /
• 2011

With increasing use of wireless mobile devices like smartphone and tablet PC, telecommunication companies have been providing the internet service by installing a multitude of access points (AP) in subway stations. Most of these APs use frequency of 2.4 GHz band range and the three telecom providers (SKT, KT, LGT) are using the limited channels within this range without any regulations. The channels within 2.4GHz band are already saturated as the companies are setting up wireless AP even within the subway trains for better service. This can affect other 2.4GHz wireless devices used for other purposes with channel interference, etc. This study has tested and analyzed the effects of the wireless APs installed within the subway stations and trains for the internet service on ZigBee-based sensor network for the intelligent surveillance system of urban transit, which is currently being developed and installed.

• International Journal of Internet, Broadcasting and Communication
• /
• 제12권3호
• /
• pp.156-162
• /
• 2020

Wireless Sensor Network (WSN) field is mainly studied to monitor and characterize large-scale physical environments to track various environmental or physical conditions, such as temperature, pressure, wind speed and humidity. WSN can be used in various applications such as wild surveillance, military target tracking and monitoring, dangerous environmental exploration and natural disaster relief. We design probabilistic mobile models that apply to mobile ad hoc network mobile environments. A probabilistic shift model proposed by dividing the number of moving nodes and the distance of travel into two categories to express node movement characteristics. The proposed model of movement through simulation was compared with the existing random movement model, ensuring that the width and variation rate of the first node node node node (FND) was stable regardless of the node movement rate. In addition, when the proposed mobile model is applied to the routing protocol, the superiority of network life can be verified from measured FND values. We overcame the limitations of the existing random movement model, showing excellent characteristics in terms of energy efficiency and stable in terms of changes in node movement.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제16권2호
• /
• pp.131-139
• /
• 2016

Recognition of human motions has become a main area of computer vision due to its potential human-computer interface (HCI) and surveillance. Among those existing recognition techniques for human motions, head detection and tracking is basis for all human motion recognitions. Various approaches have been tried to detect and trace the position of human head in two-dimensional (2D) images precisely. However, it is still a challenging problem because the human appearance is too changeable by pose, and images are affected by illumination change. To enhance the performance of head detection and tracking, the real-time three-dimensional (3D) data acquisition sensors such as time-of-flight and Kinect depth sensor are recently used. In this paper, we propose an effective feature extraction method, called adaptive local binary pattern (ALBP), for depth image based applications. Contrasting to well-known conventional local binary pattern (LBP), the proposed ALBP cannot only extract shape information without texture in depth images, but also is invariant distance change in range images. We apply the proposed ALBP for head detection and tracking in depth images to show its effectiveness and its usefulness.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제6권5호
• /
• pp.1400-1420
• /
• 2012

Object detection and tracking using visual sensors is a critical component of surveillance systems, which presents many challenges. This paper addresses the enhancement of object detection and tracking via the combination of multiple visual sensors. The enhancement method we introduce compensates for missed object detection based on the partial detection of objects by multiple visual sensors. When one detects an object or more visual sensors, the detected object's local positions transformed into a global object position. Local and global information exchange allows a missed local object's position to recover. However, the exchange of the information may degrade the detection and tracking performance by incorrectly recovering the local object position, which propagated by false object detection. Furthermore, local object positions corresponding to an identical object can transformed into nonequivalent global object positions because of detection uncertainty such as shadows or other artifacts. We improved the performance by preventing the propagation of false object detection. In addition, we present an evaluation method for the final global object position. The proposed method analyzed and evaluated using case studies.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2009년도 춘계학술대회 논문집
• /
• pp.457-465
• /
• 2009

Subway system including light-rail transit system is the representative public urban transportation. Accordingly, Nothing is more important than the safety operation as well as passengers' convenience. Due to the fire disaster of Daegu subway on 2003, more strict regulations of detecting fire and of conducting on emergency circumstances. However, regardless of this improved management, it was reported that installations of lots of fire-detection facilities may be harm than good to operate subway system due to frequent malfunction of some fire-detection facilities. It may cause mis-alarm for fire and induces abnormal operation of subway due to the strict regulation; the train shall be stopped on emergency circumstances. Therefore, in this paper, new scheme on surveiling breaking-out-of fire in the station is suggested with new IT technologies, Wireless Sensor Network(WSN) and CCTVs. which were integrated with an intelligent software. This intelligent system enables to surveil breaking-out-of fire in real time through sensor network technology and watch the emergency site on CCTV as well. Through this system, subway organizers could cope with the emergency circumstance rapidly as well as judge precisely whether fire breaks out or not.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2014년도 제50차 하계학술대회논문집 22권2호
• /
• pp.107-108
• /
• 2014

현재의 지능형 안전 및 유지관리 방법은 자연재해 및 시설물 사용성능 향상 등의 환경변화 대응에 아직 미흡하고, 기술역량도 부족하다. 국내의 시설물의 점검 및 관리 시스템은 대부분 수작업으로 이루어진다. 이러한 수동적인 관리는 시설물의 상태 변화에 실시간으로 대응하지 못함으로서 여러 사고를 초래하기도 한다. 하지만 사람이 일일이 검사하는 수동적인 시설물 관리에서는 이러한 문제점을 완벽히 해결할 수 없으며, 시설물 관리를 위해 많은 유지보수 인력이 필요하지만 예산상의 문제로 인해 관리가 미흡하다. 본 논문에서는 4G 무선네트워크 기반의 영상카메라 및 감지센서 융합형 시각정보화 M2M 게이트웨이를 활용하여 간단한 시설물 관리 시스템 구성으로 인한 기존 원격 영상 감시 시스템과 차별화된 저전력, 저비용, 고효율, 고성능의 무인 시설물 관리 시스템을 설계하였다.

• 대한원격탐사학회지
• /
• 제26권6호
• /
• pp.629-644
• /
• 2010

A real-time image georeferencing system requires all inputs to be determined in real-time. The intrinsic camera parameters can be identified in advance from a camera calibration process while other control information can be derived instantaneously from real-time GPS/INS data. The bottleneck process is tie point acquisition since manual operations will be definitely obstacles for real-time system while the existing extraction methods are not fast enough. In this paper, we present a fast-and-automated image matching technique based on the KLT tracker to obtain a set of tie-points in real-time. The proposed work accelerates the KLT tracker by supplying the initial guessed tie-points computed using the GPS/INS data. Originally, the KLT only works effectively when the displacement between tie-points is small. To drive an automated solution, this paper suggests an appropriate number of depth levels for multi-resolution tracking under large displacement using the knowledge of uncertainties the GPS/INS data measurements. The experimental results show that our suggested depth levels is promising and the proposed work can obtain tie-points faster than the ordinary KLT by 13% with no less accuracy. This promising result suggests that our proposed algorithm can be effectively integrated into the real-time image georeferencing for further developing a real-time surveillance application.

• International Journal of Computer Science & Network Security
• /
• 제22권12호
• /
• pp.171-177
• /
• 2022

The number of people who own indoor plants is growing today, but as a result of their busy lifestyles-such as work or travel-as well as a lack of enthusiasm in caring for their plants, their plants wither. The use of an irrigation control system with a surveillance camera can assist such folks in taking care of their plants. Such a device can assist in remotely watering plants at predetermined times and checking on the health of the plants. The proprietors would be able to live comfortably without feeling bad thanks to this change. Internet access is required for this technology in order to monitor the plants and control the watering through apps. A sensor is installed in the soil to monitor soil humidity and send data to the microcontroller for irrigation, allowing the owner to schedule irrigation as they see fit and keep an eye on their plants all day. With the use of a remote irrigation control system, the plants will grow properly and be irrigated with the proper amount of water, and the owners will be so glad and delighted to watch their plants. Knowing the time and quantity of water are vital parts of the plant growth.

• 한국전자통신학회논문지
• /
• 제18권5호
• /
• pp.919-926
• /
• 2023

본 논문에서는 주야간 움직임 감지 시스템 개발을 위한 주야간 촬영이 가능한 카메라 시스템을 구현하였다. 이를 위해 CMOS 이미지 센서는 물론 IR-LED를 이용하여 야간에도 선명한 영상 캡처가 가능하도록 설계하였다. 또한 칼라모델 분리를 통해 비교적 단순한 움직임 감지 알고리즘을 제안하였다. 칼라모델에서 H채널만 추출한 후, 영상을 블럭으로 나눈 다음 연속 프레임간의 평균 색상값을 이용하여 블록 매칭방식을 적용함으로써 움직임을 감지할 수 있다. 촬영 중 움직임이 감지되면 자동으로 경보음이 울리면서 화면을 캡처하여 PC에 저장할 수 있는 주야간 움직임 감지 시스템을 구현하였다.