• The Journal of the Korea institute of electronic communication sciences
• /
• v.13 no.6
• /
• pp.1263-1268
• /
• 2018

In this paper, a video analysis is proposed to implement video surveillance system with deep learning object detection and probabilistic data association filter for tracking multiple objects, and suggests its implementation using GPU. The proposed video analysis technique involves object detection and object tracking sequentially. The deep learning network architecture uses ResNet for object detection and applies probabilistic data association filter for multiple objects tracking. The proposed video analysis technique can be used to detect intruders illegally trespassing any restricted area or to count the number of people entering a specified area. As a results of simulations and experiments, 48 channels of videos can be analyzed at a speed of about 27 fps and real-time video analysis is possible through RTSP protocol.

• The Journal of Korea Robotics Society
• /
• v.4 no.2
• /
• pp.130-138
• /
• 2009

Recently, people tracking technology is being required to various area including security application. This paper suggests a method to track people with multiple laser scanners to detect the waist part of human. Multi-target model and Kalman filter based estimation are employed to track the human movement. The proposed method is applied to a novel system to monitor the entrance area and to filter out the trespasser to pass through the door without identification. Experiments for various cases are performed to verify the usefulness of the developed system.

• Proceedings of the KIEE Conference
• /
• 2006.10b
• /
• pp.194-198
• /
• 2006

전국전인 초고속통신망이 구축되면서 인터넷을 통해 서비스되는 정보도 과거의 텍스트 기반의 서비스에서 정지영상, 동영상, 음성 등과 같은 멀티미디어 서비스가 주류를 이루고 있다. 웹캠이나 CCD 카메라로 촬영한 영상을 인터넷을 통해서 실시간으로 서비스할 수 있는 기술이 개발되면서 이를 이용하여 모니터링 서비스, 원격감시 시스템, 다자간 화상회의시스템, 출입관리, 동영상을 스트리밍 서버를 이용한 서비스, 인터넷 방송 등 다양한 분야에서 사용되고 있다. 본 연구에서는 웹 캠나 CCD 카메라를 통해 획득한 영상 중 필요로 하는 부분을 저장하여 향후에 사용할 수 있도록 하는 시스템 을 개발하는 것으로 동화상 캡처 드라이버와 인터페이스 처리 부분, 데이터 분석 처리 부분, 데이터 처리 부분을 C++ 프로그램을 사용하여 개발하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.1541-1544
• /
• 2015

최근 스마트폰으로 워터마크가 인쇄된 문서를 촬영하여 유출을 하는 범죄가 일어나고 있으며, 특별한 감시 방안이 없다. 이를 위해 정부 및 기업에서는 문서의 외부 유출을 막기 위해 복사기 및 팩스 장치에 워터마크 패턴 보호 기법을 탑재하여 광학적으로 불법 복제를 방지한다. 특히 기업에 출입시 스마트폰에 보안 앱들을 설치하고, 스마트폰으로 문서를 촬영할 경우 앱이 보안 문서를 인식하여 경고를 시스템에 알린다. 그러나 스마트폰으로 촬영된 영상은 카메라의 위치와 각도에 따라 왜곡 현상이 발생되어 워터마크가 훼손된다. 이렇게 훼손된 영상은 기존 워터마크 패턴 인식 방법으로는 정상적으로 인식 되지 않는 문제가 있다. 본 논문에서는 실험을 통하여 훼손된 워터마크를 보정하고 인식하는 알고리즘을 이용하여 인식률과 처리속도를 높인다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.1093-1096
• /
• 2021

우리는 1 인 가구가 늘어나고 있고 주거 침입 사고도 많이 발생하고 있는 현재 사회에 맞게 도어락에 보안을 강화하고, 집안에 CCTV 를 설치하여 감시하는 서비스를 제공하여 거주자의 불안감을 덜어내도록 한다. 사용한 H/W 는 아두이노와 지문인식센서로 도어락의 지문인증에, 라즈베리파이와 웹 캠은 도어락의 얼굴인증, CCTV 에 사용하여 구축했다. 또한 도어락 인증에 성공하면 집 모형의 문을 열어주기 위해 서보 모터를 사용했다. 사용한 S/W 는 데이터 저장, 얼굴 인증은 AWS 클라우드 서비스를 활용했고, 스마트폰 알람은 FCM 을 사용하였다. OpenCV 를 사용해 움직임 감지를 하고, Flask, Ngrok 를 활용해 실시간 스트리밍이 가능하도록 했다. 어플에서는 관리자가 데이터를 관리(조회, 추가, 삭제)를 할 수 있다.

• The Journal of the Korea Contents Association
• /
• v.10 no.1
• /
• pp.343-352
• /
• 2010

As a result of comparing and analyzing the related legislation of each nation, more superior legislative systems should be made to cope with a number of terrors effectively. And also it is required to devise some concrete regulations such as the following in superior legislative systems. First, because it is hard to collect information on terrorism and watch over suspects according to Communication Privacy Protection Law. More in-depth discussion into the issue of surveillance is needed for the protection of lives and property, although public concerns of privacy are a valid point of contention. Second, it is necessary to take complementary measures on immigration as surveillance, since the current Immigration Control Law has restrictions in many ways to hinder efforts to root out terrorists. Third, under the current law on financial activities, it is impossible to block influx of terror financing. Therefore it is necessary to come up with ways of making the punishment procedures. Fourth, considering that convicted terrorists get punished under the standard procedures and precedents, it is required to clearly differentiate between what the terror acts are and what terrorist groups are. Fifth, it is necessary to make use of the private security system to enhance the security system of national facilities.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.1
• /
• pp.464-469
• /
• 2019

A remote monitoring panel and control system was developed to control various valves and access control chambers, including gas shutoff valves used in CBR(Chemical, Biological and Radiological) facilities. The remote monitoring panel consisted of a main panel installed in the NBC (Nuclear, Biological and Chemical) control room and auxiliary panel installed in the clean room, and the size was divided into pure control and control including CCTV. This system can be monitored and controlled remotely according to the situation where an explosion door and gas barrier door can occur during war and during normal times. This system is divided into normal mode and war mode. In particular, it periodically senses the operation status of various valves, sensors, and filters in the CBR facilities to determine if each apparatus and equipment is in normal operation, and remotely alerts situation workers when repair or replacement is necessary. Damage due to the abnormal operation of each device in the situation can be prevented. This enables control of the blower, supply and exhaust damper, emergency generator, and coolant pump according to the state of shutoff valve and positive pressure valve in the occurrence of NBC, and prevents damage caused by abrupt inflow of conventional weapons and nuclear explosions.

• Journal of the Korea Computer Graphics Society
• /
• v.16 no.1
• /
• pp.1-7
• /
• 2010

With the widespread use of vision-based surveillance systems, the capability for person identification is now an essential component. However, the CCTV cameras used in surveillance systems tend to produce relatively low-resolution images, making it difficult to use face recognition techniques for person identification. Therefore, an algorithm is proposed for person identification in CCTV camera images based on the clothing. Whenever a person is authenticated at the main entrance of a building, the clothing feature of that person is extracted and added to the database. Using a given image, the clothing area is detected using background subtraction and skin color detection techniques. The clothing feature vector is then composed of textural and color features of the clothing region, where the textural feature is extracted based on a local edge histogram, while the color feature is extracted using octree-based quantization of a color map. When given a query image, the person can then be identified by finding the most similar clothing feature from the database, where the Euclidean distance is used as the similarity measure. Experimental results show an 80% success rate for person identification with the proposed algorithm, and only a 43% success rate when using face recognition.

• Journal of the Korean Society of Radiology
• /
• v.14 no.3
• /
• pp.279-287
• /
• 2020

Recently, interest in radiation protection is increasing because of the occurrence of accidents related to exposure dose. So, the nuclear safety act provides to install the shields to avoid exceeding the dose limit. In particular, when the worker conducts the non-destructive testing (NDT) without the fixed shielding structure, we should monitor the access to the workplace based on a constant dose rate. However, when we apply for permits for NDT work in these work environments, the consideration factors to the estimation of the distance and exposure dose are not legally specified. Therefore, we developed the excel model that automatically calculates the distance, exposure dose, and cost if we input the factors. We applied the assumption data to this model. As a result of the application, the distance change rate was low when the thickness of the lead blanket and collimator is above 25 mm, 21.5 mm, respectively. However, we didn't consider the scattering and build-up factor. And, we assumed the shape of the lead blanket and collimator. Therefore, if we make up for these limitations and use the actual data, we expect that we can build a database on the distance and exposure dose.

• Journal of Internet Computing and Services
• /
• v.13 no.6
• /
• pp.33-40
• /
• 2012

The cloud service has become the significant factor to save the IT operation cost and to improve the productivities in companies. It was introduced to Korea for enterprise services of major companies in 2008. As the increase of recognition for its effect, more small businesses and public institutions plan to introduce the cloud computing services. The cloud computing researches have only focused on the security threats and response technologies to them. Therefore, this research analyzed the importances of responses to security threats in specific domains. The domains were divided into managerial, physical, and technical security. The specific factors in three domains were used for the analysis in this research as well. The ordered logit model was used for the analysis and the analysis results showed that physical security and managerial security are considered to be significantly important in the cloud computing security. The results also presented that the security policy, the control and surveillance to service infrastructure, and application security are highly important in the respect of specific factors. This research will contribute to enterprises or institutions in Korea, which want to introduce the cloud computing services, by aiding the establishment of effective security strategies.