• Journal of Korea Multimedia Society
• /
• v.19 no.8
• /
• pp.1345-1360
• /
• 2016

In this paper, we propose a new real-time human detection under omni-directional cameras for visual surveillance purpose, based on CNN with unified detection and AGMM. Compared to CNN-based state-of-the-art object detection methods. YOLO model-based object detection method boasts of very fast object detection, but with less accuracy. The proposed method adapts the unified detecting CNN of YOLO model so as to be intensified by the additional foreground contextual information obtained from pre-stage AGMM. Increased computational time incurred by additional AGMM processing is compensated by speed-up gain obtained from utilizing 2-D input data consisting of grey-level image data and foreground context information instead of 3-D color input data. Through various experiments, it is shown that the proposed method performs better with respect to accuracy and more robust to environment changes than YOLO model-based human detection method, but with the similar processing speeds to that of YOLO model-based one. Thus, it can be successfully employed for embedded surveillance application.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.3
• /
• pp.183-192
• /
• 2009

ADESS(Adverse drug event surveillance system) is the system which distinguishes adverse drug events using adverse drug signals. This system shows superior effectiveness in adverse drug surveillance than current methods such as volunteer reporting or char review. In this study, we built clinical data mart(CDM) for the development of ADESS. This CDM could obtain data reliability by applying data quality management and the most suitable clustering number(n=4) was gained through the reproducibility assessment in unsupervised learning techniques of knowledge discovery. As the result of analysis, by applying the clustering number(N=4) K-means, Kohonen, and two-step clustering models were produced and we confirmed that the K-means algorithm makes the most closest clustering to the result of adverse drug events.

• Journal of Digital Convergence
• /
• v.18 no.9
• /
• pp.265-275
• /
• 2020

The burden of injury is widely considered to be very severe in our society. Nonetheless, we don't have enough data for injury surveillance. The objective of this research is to select and supplement CORE DATA for injury surveillance. For this purpose, this study had analyzed the literature such as the Quality Assessment Report about 'Causes of Death Statistics', 'Health Insurance Statistics' and 'Hospital Discharge Injury Surveillance' according to the six dimension of Statistics Quality. The analysis result is that 'Cause of Death Statistics' and 'Health Insurance Statistics' have the usefulness as the CORE DATA for injury surveillance. But there is a significant shortcoming in the Health Insurance Statistics, which is that there is a lack of the data about the external causes of injury. For supplementing the defect, this study proposes the system that the medical institutions should obligatorily report the external causes of injury when claim National Health Insurance Medical Care Expenses. As the results of this system, we can expect 'Establishing of Injury pyramid', 'Data Connecting with the National Pension' and 'Improving the Promptness of Injury Data'. And we expect the follow-up study for the realization of this system.

• Journal of agricultural medicine and community health
• /
• v.32 no.3
• /
• pp.139-153
• /
• 2007

Injury in agriculture is a serious public health issue with a major impact on the lives of Korean farmers. It is one of the leading causes of death and is also a major cause of longand short-term disability. In 2001, the social cost of one accident in agricultural machinery was estimated as 97.7-97.8 million won that is 4 fold of farm household income in Korea. Effective prevention and control of injuries requires a system of surveillance that monitors the incidence of injuries, their causes, treatment and outcomes. This requires an integrated system of data collection, analysis and interpretation and communication. Creating effective injury surveillance system in Korea requires to establish a framework for a national agenda. Discussions regarding the development of the framework should address, but not be limited to issues related to Data Holdings and Linkages; Capacity and Skills; Communication; Interconnection; and Surveillance Products. Ideally, an injury surveillance system would meet the information requirements across all sectors, while allowing each to have the ongoing information it needs for its policy and programming needs. This study was carried out to develop a surveillance system of agricultural injuries in Korea. Study subjects were residents who lived in a typical agricultural area (Yangpyung area in Kyung-gi province). The main data sources were reports of village headmen, compared with data of 'National Emergency Management Agency', 'National Health Insurance Corporation', 'Insurance of National Agricultural Cooperative', and 'Emergency Medical Centers'. Each data were reviewed to validate the strengths and weaknesses.

• 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.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.2
• /
• pp.27-39
• /
• 2015

As a radar based air surveillance hits the limit along with the growing air traffic needs, a new air surveillance technology called ADS-B has emerged. ADS-B provides more accurate position information with a shorter interval, and aircraft equipped with ADS-B transponders can check each other's location. However not all aircraft are equipped with ADS-B transponders, and aircraft with different ADS-B data links cannot check each other's location. To address these problems a TIS-B service, which broadcasts information that a radar is tracking, and an ADS-R service, which cross-broadcasts information of different ADS-B data links, have been emerged. In this paper, we design and implement a centralized TIS-B server for broadcasting air traffic situation which is capable of providing a TIS-B service and an ADS-R service at the same time. The implemented TIS-B server has been verified with a configured ADS-B ground system, by receiving ADS-B surveillance data and radar surveillance data followed by generating surveillance data for providing a TIS-B service and an ADS-R service and simulating broadcast of those generated surveillance data.

• Journal of Advanced Navigation Technology
• /
• v.20 no.4
• /
• pp.336-343
• /
• 2016

Future air navigation system (FANS) Committee overcomes the limitations of traditional systems, the development of worldwide new system that allows the development of air traffic management have been determined to be necessary. In order to accommodate the rapid increase in aircraft traffic and maximize the safe air navigation efficiency, ICAO is recommending a new performance-based communications and surveillance (PBCS) system. However, although utilizing wireless data link in the case of korea currently, the introduction of the PBCS is not performed normally. In this paper, we review the concept of PBCS, and aviation developed countries look to the applied case of PBCS. It also analyzes trends and status and problems of Korea and introduce future policy directions for CNS/ATM system improvement.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.1
• /
• pp.162-168
• /
• 2018

The UAV(Unmanned Aerial Vehicle) system, including the drone of a variety of fields, which has become an issue and utilized in various fields, has begun to develop in military fields and is actively developed in the commercial field. In various types of UAV systems, which have been developed recently, the communication system that is responsible for the connection between the ground control unit and the UAVs is called the data link. Especially, common data link used in military UAVs is required stability of communication to transmit surveillance and reconnaissance intelligence information and UAV's status. In this paper, the requirement for a modem was defined to secure the communication stability of the common data link used in surveillance UAVs. And, the design of the data link modem to satisfy applicable specifications was proposed. The proposed modem design was verified through the performance measurement of the implemented systems.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.5 no.3
• /
• pp.405-417
• /
• 2001

In this paper, since we currently using surveillance system of analog type bring about waste of resource and efficiency deterioration problems, we describe new solution that design and implementation to the digital surveillance system of new type applying compression techniques and encoding techniques of image data using MPEG-2 international standard. Also, we proposed fast motion estimation algorithm requires much less than the convectional digital surveillance camera system. In this paper a fast motion estimation algorithm is proposed the MPEG-2 video encoding. This algorithm is based on a hybrid use of the block matching technique and gradient technique. Also, we describe a method of moving object extraction directly using MPEG-2 video data. Since proposed method is very simple and requires much less computational power than the conventional object detection methods. In this paper we don't use specific H/W and this system is possible only software encoding, decoding and transmission real-time for image data.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.13 no.1
• /
• pp.169-174
• /
• 2018

There are many CCTV cameras connected to the video surveillance and monitoring center for the safety of citizens, and it is difficult for a few monitoring agents to monitor many channels of videos. In this paper, we propose an intelligent video surveillance system utilizing a safety map to efficiently monitor many channels of CCTV camera videos. The safety map establishes the frequency of crime occurrence as a database, expresses the degree of crime risk and makes it possible for agents of the video surveillance center to pay attention when a woman enters the crime risk area. The proposed gender classification method is processed in the order of pedestrian detection, tracking and classification with deep training. The pedestrian detection and tracking uses Adaboost algorithm and probabilistic data association filter, respectively. In order to classify the gender of the pedestrian, relatively simple AlexNet is applied to determine gender. Experimental results show that the proposed gender classification method is more effective than the conventional algorithm. In addition, the results of implementation of intelligent video security system combined with safety map are introduced.