• Journal of Advanced Marine Engineering and Technology
• /
• v.40 no.4
• /
• pp.336-341
• /
• 2016

This paper presents an implementation of a communication network in wind turbines, which exploits the power-line communication system (PLC). We used an inductive coupling unit and a multi-interface device to connect a data-communication terminal to the power line, to ensure that stable communication was possible at various electric current and voltage values of the generator. The results of the operation tests conducted on an operational wind turbine showed that the implemented PLC demonstrated a transmission rate of at least 43 Mbps with a 100% success rate. Moreover, a real-time image was transmitted. Thus, the system could be a useful alternative for implementing a communication network in wind turbines that does not require additional channels. Since the presented system is easy to implement, and can support various interfaces for data communication, it will be quite useful when a real-time monitoring system is launched in wind turbines.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.12
• /
• pp.1834-1843
• /
• 2016

DVRs are the most common recording and displaying devices used for surveillance. Video compression plays a key role in DVRs for saving storage; the video compression standard, H.264/AVC, has recently become the dominant choice for DVRs. DVRs require various display modes, such as fast-forward, backward play, and pause; these are called trick modes. The implementation of precise trick mode play requires a very high decoding capability or a very intelligent scheme in order to handle the high computation complexity. The complexity is increased in many surveillance applications where more than one camera is used to monitor multiple spots or to monitor the same area using various angles. An implementation of a trick mode play and a frame buffer management scheme for the hardware-based H.264/AVC codec for multi-channel is presented in this paper. The experimental results show that exact trick mode play is possible using a standard H.264/AVC video codec with keyframe encoding feature at the expense of bitstream size increase.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39C no.11
• /
• pp.1104-1113
• /
• 2014

Future combat systems can be represented as the NCW (Network Centric Warefare), which is based on the concept of Sensor-to-Shooter. A wireless video sensor networking technology, one of the core components of NCW, has been actively applied for the purpose of tactical surveillance. In such a surveillance sensor network, multi-composite sensors, especially consisting of image sensors are utilized to improve reliability for intrusion detection and enemy tracing. However, these sensors may cause a problem of requiring very high network capacity and energy consumption. In order to alleviate this problem, this paper proposes an image data transmission scheme based on resource reservation. The proposed scheme can make it possible to have more reliable image data transmission by choosing proper multiple interfaces, while trying to control resolution and compression quality of image data based on network resource availability. By the performance analysis using NS-3 simulation, we have confirmed the transmission reliability as well as energy efficiency of the proposed scheme.

• 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.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2010.11a
• /
• pp.100-103
• /
• 2010

In this paper we propose a method of detecting moving object in H.264/AVC bitstream by representing the $4{\times}4$ block partition units as nodes of graph. By constructing hierarchical graph by taking into account the relation between nodes and the spatial-temporal relations between graphs in frames, we are able to track small objects, distinguish two occluded objects, and identify objects that move and stop alternatively.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.11a
• /
• pp.165-168
• /
• 2019

The advancement in technology has led to the enormous use of multimedia applications. The video/image recorded by such applications provides critical information that can be used as a visual evidence. However, owing to the adequacy in using different editing tools, it is susceptible to malicious alterations. Thus, the reliability or the integrity of the visual information should be verified before using it as an evidence. In this paper, we propose an integrity verification method for the surveillance system using randomized hashing. The integrity value of the surveillance data is generated using the randomized hashing and elliptic curve cryptography (ECC), which is used later for the validation. The experimental results obtained from the embedded accident data recorder (ADR) system shows that the proposed method is very efficient and provides a high level of security.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2007.02a
• /
• pp.83-86
• /
• 2007

비디오에서의 물체 추적은 컴퓨터비젼(computer vision)의 주요 연구 분야로 지능형 로봇, 무인 감시 체제 등의 영역의 핵심 기술로 여겨지고 있다. 본 논문에서는 다중물체추적을 통해 카메라로 부터 입력된 동영상에서 특정 장소를 지나가는 사람들을 추적함으로서, 그 지역에서의 인구의 이동 패턴을 추출하고 자 한다. 물체 추적은 블롭 추적(blob tracking) 방식을 이용하며, 이를 위해 정확한 전경물체 추출, 추출된 이미지 블롭(blob)과 기존 트랙과의 연결, 새로운 물체(사람)의 등장과 퇴장등의 작업을 수행한다. 추적된 물체들이 궤적을 통해, 시간의 변화에 따른 그 지역에서의 인구의 밀도, 주 이동 경로, 방향 등의 변화를 추출한다. 이러한 통계치는 해당 지역의 개발 정책 수립 및 시장성 조사를 위한 2차 데이타로 활용할 수 있다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.10c
• /
• pp.307-312
• /
• 2006

멀티미디어의 비중이 커짐에 따라 컴퓨터 과학 각 분야에서 독자적인 기술들을 이용하여 실제 응용 및 시스템을 구축하고 있다. 하지만 멀티미디어 동영상 내에서 객체의 행위 단독적인 움직임을 수치로만 표현하여 자료를 처리함에 따라 의미를 해석하는 것이 부자연스럽고 정확한 숫자에 부합하는 행동의 검출이 어렵다. 본 논문에서는 멀티미디어 동영상의 기본적인 행위를 추출하고 이를 추상화, 정형화하여 보다 상위단계로 접근을 유도하여 멀티미디어 데이터에 대한 접근을 용이하게 하기위한 방법에 대하여 논의하였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2007.06a
• /
• pp.149-152
• /
• 2007

비전 연구에 있어서 객체 추적은 무엇보다도 중요시 되어 왔다. 특히 비디오 감시 시스템에서의 객체 추적은 매우 중요하다. 본 논문에서는 영상 내에서 움직이는 객체를 추출하고 객체내의 다중 후보블록의 통계적 특징을 이용한 추적 시스템을 구성하였다. 객체를 추적하기 위해서는 먼저 움직이는 객체 추출이 선행되어야 한다. 객체 추출은 영상 내에서 배경 프레임과 매 프레임에서의 현재 프레임간의 차 연산에 의한 가중치를 이용하여 객체의 움직임을 판단하고 추출하였다. 움직이는 객체는 본 논문에서 제안한 다중 후보 블록 알고리즘을 수행하여 추적에 필요한 통계 값을 획득한다. 통계 값으로는 방향성에 필요한 블록의 중심 좌표 값과 객체추적에 필요한 객체간의 매칭 정도를 사용하였다. 본 논문에서 제안한 추적 시스템은 민감한 빛의 변화에도 강건하였으며, 특정 블록에 대해서만 연산 수행을 수행하므로 컴퓨터의 연산을 줄여 실시간 추적도 가능하다.

• Proceedings of the KIEE Conference
• /
• 2005.05a
• /
• pp.176-178
• /
• 2005

In the images of a video camera employed for surveillance, detecting targets by extracting foreground image is of great importance. The foreground regions detected, however, include not only moving targets but also their shadows. This paper presents a novel technique to detect shadow pixels in the foreground image of a video camera. The image characteristics of video cameras employed, a web-cam and a CCD, are first analysed in the HSV color space and a pixel-level shadow detection technique is proposed based on the analysis. Compared with existing techniques where unified criteria are used to all pixels, the proposed technique determines shadow pixels utilizing a fact that the effect of shadowing to each pixel is different depending on its brightness in background image. Such an approach can accommodate local features in an image and hold consistent performance even in changing environment. In experiments targeting pedestrians, the proposed technique showed better results compared with an existing technique.