• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.47 no.2
• /
• pp.146-152
• /
• 2011

Underwater CCTV camera systems are increasingly replaced the traditional net approach of assessing the species, numbers and aggregation patterns of marine animals distributing around the artificial reefs installed in the inshore fishing grounds, in particular, in relation to the biological investigation of behavior and distribution patterns of target fishes. In relation to these needs, we developed a multi-directional underwater CCTV camera system to use in detecting and tracking marine animals in the artificial reef ground. The marine targets to be investigated were independently tracked by using a camera module toward the bottom and four camera modules installed in the interval of $90^{\circ}$ in horizontal plane and inclination of $45^{\circ}$ in vertical plane of the CCTV system without the overlap of video frames by each camera module. From the results of several field tests at sea, we believe that the developed multi-directional underwater CCTV camera system will contribute to a better understanding in evaluating the effect of artificial reefs installed in the inshore fishing grounds.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.498-500
• /
• 2022

CCTV protects people and assets safely by identifying dangerous situations and responding promptly. However, it is difficult to continuously monitor the increasing number of CCTV images. For this reason, there is a need for a device that continuously monitors CCTV images and notifies when abnormal behavior occurs. Recently, many studies using artificial intelligence models for image data analysis have been conducted. This study simultaneously learns spatial and temporal characteristic information between image data to classify various abnormal behaviors that can be observed in CCTV images. As an artificial intelligence model used for learning, we propose a multi-classification deep learning model that combines an end-to-end 3D convolutional neural network(CNN) and ResNet.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.863-865
• /
• 2022

본 프로젝트는 시간, 날씨, 미세먼지 농도, 캘린더, 뉴스 등을 포함한 기본적인 생활정보를 스마트 미러에 디스플레이 해주며 추가적으로 구글 어시스턴트를 활용해 음성인식으로 유튜브 재생, 인터넷 검색 등 다양한 기능을 내재하고 있다. 아울러 인체 감지 센서를 이용해 움직임이 감지되지 않으면 절전모드로 동작하다 움직임이 감지하면 일반 모드로 동작한다. 마지막으로 CCTV 기능을 내재하고 있어 CCTV 화면을 웹 애플리케이션을 통해 실시간 스트리밍 하며 사람 얼굴이 감지될 시 화면을 녹화하는 기능을 포함하고 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.807-809
• /
• 2020

기존의 CCTV 관리 체계는 사건·사고에 대한 신속한 조치가 불가능하고 정황 파악이나 증거자료 확보 등 사후조치의 성격이 강하다. 본 논문에서는 Mask R-CNN(Regions with CNN)을 이용하여 CCTV가 읽어 들이는 객체가 응급상황인지 판단하는 방법을 제시한다. 사람으로 인식되는 영역을 다층 퍼셉트론(MLP, Multi-Layer Perceptron)으로 학습시켜 해당 대상이 처한 상황을 인지하고 응급상황으로 인식되는 상황이 지속될 경우 관리 모니터를 통해 사용자에게 알림을 준다. 본 연구를 통해 실시간 상호작용적인 CCTV 관리 체계를 구축하여 도움이 필요한 사람의 골든타임을 놓치지 않게 될 것으로 기대한다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.12
• /
• pp.546-554
• /
• 2019

Typically, closed-circuit television (CCTV) monitoring is mainly used for post-processes (i.e. to provide evidence after an incident has occurred), but by using a streaming video feed, machine-based learning, and advanced image recognition techniques, current technology can be extended to respond to crimes or reports of missing persons in real time. The multi-CCTV cooperation technique developed in this study is a program model that delivers similarity information about a suspect (or moving object) extracted via CCTV at one location and sent to a monitoring agent to track the selected suspect or object when he, she, or it moves out of range to another CCTV camera. To improve the operating efficiency of local government CCTV control centers, we describe here the partial automation of a CCTV control system that currently relies upon monitoring by human agents. We envisage an integrated crime prevention service, which incorporates the cooperative CCTV network suggested in this study and that can easily be experienced by citizens in ways such as determining a precise individual location in real time and providing a crime prevention service linked to smartphones and/or crime prevention/safety information.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.273-275
• /
• 2021

본 논문에서는 기존 스마트주차관제 시스템의 한계로 인해 주차 관제의 사각지대에 있는 다세대 주택 주차 문제를 해결하는 솔루션을 제안한다. 기존 스마트 주차관제는 센서 기반의 고비용의 장비 및 시공비가 소요되며, 이러한 특성으로 인해 다세대 주택에 적용이 어렵다. 해당 문제를 해결하기 위해 본 논문은 기존 설비인 CCTV를 활용한 스마트 주차 관제 시스템을 제안하며, 해당 솔루션은 텐서플로 cnn중 알씨엔엔 RPN을 적용하여 차량 객체 인식 및 주차 공간 객체 인식을 구현하였으며, 다세대 주택 주변 CCTV 영상을 OpenCV를 활용하여 능동적이며 저비용의 스마트 주차 관제 방식을 구현하였으며 CCTV의 특성상 외곡되는 이미지를 OpenCV 이미지 변형을 통해 외곡 이미지를 복원하여 인식률을 높였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2011.05a
• /
• pp.816-819
• /
• 2011

The image recognition system using CCTV camera has been introduced to minimize not only loss of life and property but also traffic jam in the tunnel. In this paper, multi-object detection algorithm is proposed to track multi vehicles. The proposed algorithm is to detect multi cars based on Adaboost and to track multi vehicles to use template matching. As results of simulations, it is shown that proposed algorithm is useful for tracking multi vehicles.

• 한국정보통신설비학회:학술대회논문집
• /
• 2009.08a
• /
• pp.219-220
• /
• 2009

Many surveillance cameras used in security system are controlled with RS-485 communication protocol. In this situation, if RS-485 connection can be replaced with wireless connection using sensor network technology, an installation will become ease because of no wired connection and also a deployment of cameras will become free. This paper explains about the design of wireless sensor node and the necessary implementation for an operation, which can be replacing RS-485 connection for the development of CCTV control system based on wireless sensor network. The hardware platform of sensor node was designed based on MicaZ and the software was developed based on TinyOS. To control surveillance cameras deployed on wide area, the supporting of multi-hop also was implemented. With the result of experiment deploying on real environment, it was revealed that the controller could control cameras quickly with wireless.

• Proceedings of the KSR Conference
• /
• 2008.06a
• /
• pp.553-558
• /
• 2008

Advancement in information technology have enabled applying vision sensor to railway, such as CCTV. CCTV has been widely used in railway application, however the CCTV is a passive system that provide limited capability to maintain safety from boarding platform. The station employee should monitor continuously CCTV monitors. Therefore immediate recognition and response to the situation is difficultin emergency situation. Recently, urban transit operators are pursuing applying an unattended station operation system for their cost reduction. Therefore, an intelligent monitoring system is need for passenger's safety in railway. The paper proposes a vision based monitoring system and object detection algorithm for passenger's safety in railway platform. The proposed system automatically detects accident in platform and analyzes level of danger using image processing technology. The system uses stereo vision technology with multi-sensors for minimizing detection error in various railway platform conditions.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2014.04a
• /
• pp.936-938
• /
• 2014

폐쇄회로 TV는 우리의 생활에 밀접하게 접근할 수 있는 수준에 다다르게 되었다. 따라서 중요한 작업은 영상에서 우리가 원하는 개체를 검출해내는 것이라 할 수 있다. 그 중에서 사람의 모습을 촬영해서 사람의 특징을 추출하는 연구가 많이 진행되었고 이를 이용해서 실제 CCTV 영상을 토대로 개체를 검출해내는 시스템에 대해 고찰하였다. 여러 가지 개체 검출 알고리즘 중에서 오픈소스로 제공이 되며, 다중 개체를 검출하기 위해서 Haar-like feature를 이용한 개체 추출 알고리즘을 이용하여 CCTV 다중대체 검출에 대해 실험을 진행하였다. 정지영상에서는 정면을 응시하는 얼굴영역 검출에서는 높은 성능을 보이며 다른 각도에서는 차이가 있지만 무난한 성능을 보이지만 실시간에서는 보정 작업이 필요하게 되었다.