• 한국멀티미디어학회논문지
• /
• 제19권2호
• /
• pp.215-223
• /
• 2016

To reduce huge losses in pig farms, weaning pigs with weak immune systems are required to be carefully supervised. Even if various researches have been performed for livestock monitoring environment, segmenting each pig from touching pigs is still entrenched as a difficult problem. In this paper, we propose a real-time segmentation method for moving pigs by using motion information in a 24-h video surveillance system. The experimental results with the videos obtained from a domestic pig farm illustrated the possibility for segmenting by using our proposed method in real-time.

• 한국멀티미디어학회논문지
• /
• 제24권12호
• /
• pp.1682-1692
• /
• 2021

Digital Twin, one of the core technologies of the Fourth Industrial Revolution, is attracting attention as a very suitable technology for disaster monitoring such as fires and earthquakes. In this paper, we implement a system equipped with UWB RTLS(Ultra-Wideband Real Time Location System), real-time remote control, and video streaming, which are element technologies for disaster monitoring digital twin. Since the proposed system structure is based on a cloud server, the actual location of the UWB indoor positioning-based client is transmitted to the user device in real time and stored on the cloud server for statistical and data analysis. In addition, we demonstrate through experiments that outliers occurs when the value of RSSI(Received Signal Strength Indicator) decreases due to communication collisions between UWB Tags, and propose an RSSI outlier correction algorithm to solve this problem.

• 한국멀티미디어학회논문지
• /
• 제25권2호
• /
• pp.325-334
• /
• 2022

Digital twin has the advantages of quality improvement and cost reduction, so it is widely applied to various industries. In this paper, a method to implement the major technologies of digital twin easily and quickly is presented. These include data management and relay servers, real-time monitoring applications including remote control interfaces, and direct connection protocols for video streaming. In addition, an algorithm for controlling a two-wheeled vehicle with a 2D interface is also proposed. The implemented system performs near real-time synchronization between the real environment and the virtual space. The delay time that occurs in remote control of the vehicle in the real environment was compared with the results of applying the proposed delay time reduction method. In addition, in the case of 2D interface-based control, an algorithm that can guarantee the user experience was implemented and applied to the actual environment and verified through experiments.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권6호
• /
• pp.2483-2503
• /
• 2016

Traffic congestion is a severe problem in many modern cities around the world. Real-time and accurate traffic congestion identification can provide the advanced traffic management systems with a reliable basis to take measurements. The most used data sources for traffic congestion are loop detector, GPS data, and video surveillance. Video based traffic monitoring systems have gained much attention due to their enormous advantages, such as low cost, flexibility to redesign the system and providing a rich information source for human understanding. In general, most existing video based systems for monitoring road traffic rely on stationary cameras and multiple vehicle tracking method. However, most commonly used multiple vehicle tracking methods are lack of effective track initiation schemes. Based on the motion of the vehicle usually obeys constant velocity model, a novel vehicle recognition method is proposed. The state of recognized vehicle is sent to the GM-PHD filter as birth target. In this way, we relieve the insensitive of GM-PHD filter for new entering vehicle. Combining with the advanced vehicle detection and data association techniques, this multiple vehicle tracking method is used to identify traffic congestion. It can be implemented in real-time with high accuracy and robustness. The advantages of our proposed method are validated on four real traffic data.

• 한국정보통신학회논문지
• /
• 제20권5호
• /
• pp.937-941
• /
• 2016

본 논문에서는 전 세계 스마트폰 기기 시장을 양분하고 있는 안드로이드 스마트폰을 이용하여 원격지에 있는 영상을 실시간으로 확인할 수 있는 시스템을 설계하고 제안하였다. 이 무선 영상 전송 시스템은 개인이 실시간 현지 상황을 서버에 접속한 단말들에 전달하거나 이동 가능한 드론, 로봇 차량 등의 장치에 설치하여 현장 확인, 영상을 통한 보안 감시로 이용할 수 있을 것이다. 보안 감시 및 재난안전 예방을 위해 데이터를 긴급히 보내야하는 경우도 있다. 이러한 이용 분야들에 적용하면 응급상태나 재난예방, 보안감시에 있어 중요한 역할을 한다. 따라서 효율적인 실시간 스트리밍 전송을 위해서 본 논문에서는 병렬 TCP 통신 (parallel stream)을 이용하여 구현하였다. 결론적으로, 병렬 TCP 통신을 이용한 시스템의 효과를 다양한 환경에서 평가하고 성능 분석도 하였다.

• 한국공간구조학회논문집
• /
• 제19권4호
• /
• pp.103-110
• /
• 2019

The cable-based retractable membrane roof makes it impossible to maintain its shape and stiffness during driving process, unlike the hard-type retractable roof. Consequently, monitoring using a relatively simple wireless video transmission device is required. However, since video data has a bigger transmission rating than other monitoring data in terms of the structure velocity or acceleration, there is a need to develop transmission device that is easy to install and entails low maintenance cost. This paper studies on a real-time video transmission system for monitoring the cable-based retractable membrane roof while driving. A video transfer software, using the mobile network, is designed and the embedded system is constructed. Ultimately, the data transmission server is tested. Connecting a trolley to the system allows testing of the validity and efficiency of the developed system through the video data transmitted in the driving process. Result of the test shows that the developed system enables multi-device data transfer with monitoring via the mobile network.

• 한국해양공학회지
• /
• 제31권1호
• /
• pp.60-68
• /
• 2017

In this study, we analyzed the real time video image obtained from the video monitoring system to grasp the shoreline, beach width, and area change of Haeundae beach. The video monitoring techniques enabled continuous monitoring for a long period at a much lower cost than general survey methods. It was possible to grasp quantitative beach variation characteristics of Haeundae beach through image acquisition, rectification, and image processing of video images. According to the monitoring results, the erosion rate of Haeundae beach in spring and summer was -19.8% in 2014 and -6.7% in 2015. The erosion rate in 2016 was -6.4%, which showed that the erosion rate in spring and summer continued to decrease. In particular, the influence of the erosion at the time of typhoon CHABA was revealed to be smaller than in the past. It can be concluded that these variations were due to beach width expansion by beach nourishment and the installation of submerged breakwaters.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2007년도 추계학술대회 논문집 전기기기 및 에너지변환시스템부문
• /
• pp.229-231
• /
• 2007

The CCTV, closed circuit television, system is the most popular method to monitor some specific area. The CCTV-based monitoring system is composed of a lot of cameras installed the areas, and monitors to display the vision through the cameras. However, these systems have limitations to prevent some problems or to cope with the problems promptly, because they can carry out only the function that shows us the analogue images of the cameras. Especially, urban transit service area is the space where many people crowd in all at the same time and the space is not only wide but also distributed sporadically. This paper presents the efficient plan for video-based monitoring system to monitor urban transit service area. To build the efficient monitoring system, it is necessary to devide the monitoring area to appropriate sectors that should be composed to be displayed at a time. If the proposed method is used to construct the video-based monitoring system, the operating officers in the urban transit have the more direct and real images.

• Journal of Information Processing Systems
• /
• 제17권2호
• /
• pp.227-241
• /
• 2021

Object detection techniques based on deep learning such as YOLO have high detection performance and precision in a single channel video stream. In order to expand to multiple channel object detection in real-time, however, high-performance hardware is required. In this paper, we propose a novel back-end server framework, a real-time AI vision platform (RAVIP), which can extend the object detection function from single channel to simultaneous multi-channels, which can work well even in low-end server hardware. RAVIP assembles appropriate component modules from the RODEM (real-time object detection module) Base to create per-channel instances for each channel, enabling efficient parallelization of object detection instances on limited hardware resources through continuous monitoring with respect to resource utilization. Through practical experiments, RAVIP shows that it is possible to optimize CPU, GPU, and memory utilization while performing object detection service in a multi-channel situation. In addition, it has been proven that RAVIP can provide object detection services with 25 FPS for all 16 channels at the same time.

• Journal of Multimedia Information System
• /
• 제8권3호
• /
• pp.159-166
• /
• 2021

COVID-19 has dramatically changed people's daily life. Wearing masks is considered as a simple but effective way to defend the spread of the epidemic. Hence, a real-time and accurate mask wearing detection system is important. In this paper, a deep learning-based mask wearing detection system is developed to help people defend against the terrible epidemic. The system consists of three important functions, which are image detection, video detection and real-time detection. To keep a high detection rate, a deep learning-based method is adopted to detect masks. Unfortunately, according to the suddenness of the epidemic, the mask wearing dataset is scarce, so a mask wearing dataset is collected in this paper. Besides, to reduce the computational cost and runtime, a simple online and real-time tracking method is adopted to achieve video detection and monitoring. Furthermore, a function is implemented to call the camera to real-time achieve mask wearing detection. The sufficient results have shown that the developed system can perform well in the mask wearing detection task. The precision, recall, mAP and F1 can achieve 86.6%, 96.7%, 96.2% and 91.4%, respectively.