• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.3
• /
• pp.415-420
• /
• 2009

For the emergency detecting in general CCTV environment of our daily life, the monitoring by only images through CCTV information occurs some problems especially in cost as well as man power. Therefore, in this paper, for detecting emergency state dynamically through CCTV as well as resolving some problems, we propose our advanced speech recognition system. For the purpose of it, we adopt HMM(Hidden Markov Model) in our system to do a feature extraction. Also, we adopt Wiener filter technique for noise elimination in many information coming from on CCTV environment. In this paper, our system send only the emergency speech information to a manager to deal with emergency state effectively.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.6
• /
• pp.748-755
• /
• 2019

CCTV Systems have been operated in the variety of serveillance fields of the apartment, transportation, safety, physical security, and so on. And their uses are largely increasing as the CCTV transmission technology has been changed from analog to IP network way. Domestic industry has been working to upgrade from analog CCTV systems to High-Definition(HD) CCTV systems for recent years, which involves a few issues such as mixing with several transmission technologies and duplicated investment in each area because the technological analysis and criteria are specifically not arranged. This paper examines the technical issues of the transmission method between HD analog and HD IP CCTV systems, and induces the criteria of the cost analysis and its weighting factors for HD CCTV reformation. By simulating the cost analysis results of both the HD CCTV systems on apartment environment, this paper proposes the reference for the choice of HD CCTV system reformation.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.346-348
• /
• 2022

Many CCTVs are needed to monitor a physically large area. When installing CCTV indoors, the wiring environment is sufficient, so many CCTVs can be installed. However, wiring is relatively difficult outdoors. In addition, when monitoring a long distance, wiring costs to the monitoring site are incurred. Therefore, when installing CCTV at a physically long distance, it is necessary to apply wireless technology. In this study, the structure of the existing CCTV system was checked and the requirements for converting it to a wireless environment were derived. And according to the requirements, a wireless-based intelligent CCTV system was proposed. As a result, it was confirmed that the wireless-based intelligent CCTV proposed in this study operates normally in a wireless environment. This study was conducted based on the wifi environment, and additional research is needed to extend it to the mobile mobile telecommunication environment.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2017.11a
• /
• pp.139-141
• /
• 2017

화재는 다른 재난보다 확산 속도가 빠르기 때문에 신속하고 정확한 감지와 지속적인 감시가 요구된다. 최근, 신속하고 정확한 화재 감지를 위해, CCTV(Closed-Circuit TeleVision)으로 획득한 이미지를 기계학습(Machine Learning)을 이용해 화재 발생 여부를 감지하는 화재 감지 시스템이 주목받고 있다. 본 논문에서는 기계학습의 기술 중 정확도가 가장 높은 딥러닝(Deep Learning)기반의 CCTV 화재 감지 시스템을 제안한다. 본 논문의 시스템은 딥러닝 기술 적용뿐만이 아니라, CCTV 이미지 전처리 과정을 보완함으로써 딥러닝에서의 미지 데이터(unseen data)의 낮은 분류 정확도 문제인 과적합(overfitting)문제를 해결하였다. 본 논문의 시스템은 약 80,000 개의 CCTV 이미지 데이터를 학습하여, 90% 이상의 화재 이미지 분류 정확도의 성능을 보여주었다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.01a
• /
• pp.155-158
• /
• 2019

최근 지능형 CCTV 관제 시스템에 대한 수요가 증가하고 있다. CCTV 영상 데이터의 양이 폭발적으로 증가하고 있어 이를 분석하기 위한 기술의 발전이 필요한 실정이다. 대부분의 지능형 CCTV 관제 시스템은 영상 속 객체를 찾고 이 객체의 메타데이터를 통해 지능형 관제 시스템을 수행한다. 하지만 영상 속 객체의 로그가 항상 정확하지 않다. 현재의 객체 인식 기술로는 CCTV 영상의 밝기, 해상도 조건에 따라 성능의 차이가 심하고, 영상의 프레임 대비 빠르게 움직인 CCTV 영상 속 모든 객체를 사람이 인식하는 정도로 인식하기 어렵다. 이러한 이동 객체의 크기, 위치를 분석한 메타데이터에는 에러가 포함되기 쉽다. 본 논문에서는 지능형 CCTV 관제 시스템에서 분석한 영상 속 객체의 프레임 메타데이터 에러를 학습기반 실시간 에러 필터링 알고리즘을 통해 개선하여 에러가 필터링된 데이터를 사용하는 지능형 관제 시스템의 정확도 향상에 기여 할 것을 기대한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.317-318
• /
• 2020

본 논문에서는 얼굴검출 후 MobilnetV2의 방법을 이용하여 적은 연산량으로 CCTV가 실시간으로 마스크 착용 유무를 판단할 수 있는 방법을 제시하였다. 이를 통해 현재 이슈가 되고있는 코로나19 등 전염병의 전염 위험이 있는 주요 장소에서 인공지능 CCTV가 마스크 미착용자를 식별해 알려줌으로써 마스크 미착용자를 관리할 수 있는 방법을 제공하였다.

• Journal of the Society of Disaster Information
• /
• v.10 no.1
• /
• pp.105-115
• /
• 2014

In this research, we developed video analytic algorithms to detect water-level automatically and a system for proactive alarming using intelligent CCTV cameras. We applied these algorithms and a system to test-beds and verified for practical use. We made camera-selection policies and operation plans to keep the detection accuracy high and to optimize the suitability for the ever-changing weather condition, while the environmental factors such as camera shaking and weather condition can affect to detection accuracy. The estimation result of algorithms showed 90% detection accuracy for all CCTV camera types. For water level detection, NIR camera performed great. NIR camera performed over 95% accuracy in day or night, suitable in natural weather condition such as shaking condition, fog, and low light, needs similar installment skills with common cameras, and spends only 15% high cost. As a result, we practically tested water level detection algorithms and operation system based on intelligent CCTV camera. Furthermore, we expect the positive evidences when it is applied for public use.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.4
• /
• pp.189-198
• /
• 2023

As crimes frequently occur on the street, the spread of CCTV is increasing. However, due to the shortcomings of passively operated CCTV, the need for intelligent CCTV is attracting attention. Due to the heavy system of such intelligent CCTV, high-performance devices are required, which has a problem in that it is expensive to replace the general CCTV. To solve this problem, an intelligent CCTV system that recognizes low-quality images and operates even on devices with low performance is required. Therefore, this paper proposes a Saying CCTV system that can detect threats in real time by using the AWS cloud platform to lighten the system and convert images into text. Based on the data extracted using YOLO v4 and OpenPose, it is implemented to determine the risk object, threat behavior, and threat situation, and calculate the risk using machine learning. Through this, the system can be operated anytime and anywhere as long as the network is connected, and the system can be used even with devices with minimal performance for video shooting and image upload. Furthermore, it is possible to quickly prevent crime by automating meaningful statistics on crime by analyzing the video and using the data stored as text.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.12
• /
• pp.141-149
• /
• 2022

In this paper, we propose a design of CCTV enlcosure record management system based on blockchain. Since CCTV video records are transferred to the control center through enclosure, it is very important to manage the enclosure to prevent modulation and damage of the video records. Recently, a smart enclosure monitoring system with real-time remote monitoring and opening and closing state management functions is used to manage CCTV enclosures, but there is a limitation to securing the safety of CCTV video records. The proposed system detect modulated record and recover the record through hash value comparison by distributed stored record in the blockchain. In addition, the integrity verification API is provided to ensure the integrity of enclosure record received by the management server. In order to verify the effectiveness of the system, the integrity verification accuracy and elapsed time were measured through experiments. As a result, the integrity of enclosure record (accuracy: 100%) was confirmed, and it was confirmed that the elapsed time for verification (average: 73 ms) did not affect monitoring.

• Journal of Digital Contents Society
• /
• v.14 no.4
• /
• pp.447-454
• /
• 2013

As the surveillance CCTVs are increasing every year, big data image processing for the CCTV image data has become a hot issue. In this paper, we propose a Hadoop-based big data image processing technique to recognize a vehicle number from a large amount of automatic number plate images taken from CCTVs. We also implement the vehicle route tracking system that displays the moving path of the searched vehicle on Google Maps with the related information together. In order to evaluate the performance we compare and analysis the vehicle number recognition time for a lot of CCTV image data in Hadoop and the single PC environment.