• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.1
• /
• pp.667-670
• /
• 2005

As security and surveillance have become the center of interest, remote controlled CCTV(Closed-Circuit Television) market has been formed while rapid development of digital image compression technology and Internet triggered the advent of web cameras. The characteristic of web camera is that it can provide users with higher quality image than CCTV at any place where Internet access is available. However, As for the system administrator, the existing web camera have disadvantage in that they allows users only. who are connected to the server of the web camera, to see the image from it. In this paper, in order to make up for this defect, designed multi-vision interface showing multi images on single screen and, for the purpose of the improvement in efficiency, the functions of saving images and of scheduling the time to save the images.

• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.1373-1378
• /
• 2006

대용량의 네트워크 인프라가 확대되고, 네트워크를 통한 DV, HD 급의 고화질 비디오 전송이 보편화 되면서, 고화질의 비디오에 몰입감, 현실감을 증진시키기 위한 스테레오 HD 비디오 전송이 가능하게 되었다. 본 논문은 IP 네트워크를 통해서 스테레오 HD 비디오 전송을 가능하게 해주는 소프트웨어 기반의 HD 비디오 전송 시스템에서 효과적으로 몰입감과 입체감을 제공하기 위해 충족되어야 하는 좌우 영상의 동기화에 필요한 요소들을 다룬다. 제안된 동기화 기법은 수신 측에서 최종적으로 동기화된 좌우 영상을 통해 스테레오 HD 비디오를 얻기 위해서 좌우 카메라로부터 영상의 획득 시, 획득된 영상의 네트워크 전송 시, 또 수신된 영상의 재생 시 좌우 영상의 동기화한다. 결과적으로 동기화 된 좌우 영상을 통하여 몰입감과 현실감을 가지는 스트레오 HD 비디오를 실시간으로 감상할 수 있다.

• Proceedings of the IEEK Conference
• /
• 2003.07a
• /
• pp.145-148
• /
• 2003

본 논문에서는 TCP/IP 기반에서 웨이블릿 변환과 신경회로(Neural Network)를 이용하여 실시간으로 동영상 전송을 위한 알고리즘에 대해 연구하였다. 우선, 서버에서 카메라를 이용하여 영상을 획득한다. 획득한 영상에 대해 2 단계 웨이블릿 변환을 한 후, 인터넷을 통하여 수신 측으로 전송한다. 그 다음, 수신 측에서는 동영상을 보이기 위해, 제한된 시간 안에 수신한 이미지 프레임(image frame)만을 가지고 역웨이블릿변환을 하여 보여주게 된다. 만약 네트워크에 혼잡이 발생하게 되면 소량의 이미지 프레임 만을 전송하도록 하였다. 수신 측에서는 네트워크의 혼잡 정도를 송신 측에 특별한 목적으로 제안된 프레임을 전송함으로써 알려주도록 하였으며, 송신 측에서는 이러한 정보를 수신한 후 역전파 신경회로(back-propagation neural network)를 이용하여 송신할 데이터의 양(data rate)을 조절하여줌으로써 네트워크 속도에 대처하도록 하였다. 이러한 방법을 통해서 우리는 네트워크의 혼잡에 알맞게 조정된 동영상의 스트림(stream)을 보낼 수 있었다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.05a
• /
• pp.493-495
• /
• 2016

In this paper, we propose an alternative method of collecting image data and changing nodes in wireless sensor networks based sensing disaster systems configured with zigbee using quad copter. It is difficult to observe a wide area caused by existing fixed video cameras in the wireless sensor network system using a conventional image-based. Also the nodes don't have provide to alternate methodology in situations when missing due to a disaster or destruction. In this paper, to use wearing the IP camera and the communication node to the quad copter, it provides a method to take advantage of as improving an alternative node of the reliability of the sensor node. The results show to improve the reliability of the sensor nodes and real-time status information through a video quad Copt than conventional systems.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.10a
• /
• pp.677-680
• /
• 2008

Miniaturization of equipments which have wireless network function and sensor have changed utilization method of computer in daily life, and have contributed to development for ubiquitous computing environment. In this paper, we design camera control system based wireless mobile and web-environmental through which nurse, doctor and family of patient can share and observe the information on condition of patient in hospital. Besides, this camera control system makes it possible to integrate diverse equipments of hospital into one system, and to conduct remote control function which can be applied to the patient control system. It is impossible to control shooting direction of camera apparatus in a remote area for observing patient in a hospital room through general web camera. So in this paper, we showed new design; we attached step motor which can rotate 360 degrees to web camera, and the step motor can operate through control board. Besides, we developed application for two environments, mobile and web-based environment, which enables us to offer proper efficiency in accordance with condition of observer through observation of control and collected image data.

• Proceedings of the Korea Contents Association Conference
• /
• 2008.05a
• /
• pp.116-120
• /
• 2008

Smart Camera provides intelligent vision functionalities which can interpret captured video, extract context-aware information and execute a necessary action in real-timeliness in addition to the functionality of network cameras which transmit the compressed acquired videos through networks. Intelligent vision algorithms demand tremendous computations so that real-time processing of computation of intelligent vision algorithms as well as compression and transmission of videos simultaneously is too much burden for a single CPU. Davinci processor of Texas Instruments is a popular ASSP(Application Specific Standard Product) which has dual core architecture of ARM core and DSP core and provides various I/O interfaces as well as networking interface and video acquiring interface necessary for developing digital video embedded applications. In this paper, we report the results of designing and implementing S/W for Davinci-based smart camera. We implement a face detection as an example of vision application and verify the implementation works well. In the future, for the development of a smart camera with more broad and real-time vision functionalities, it is necessary to study about more efficient vision application S/W architecture and optimization of vision algorithms on DSP core of Davichi processor.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.10
• /
• pp.411-420
• /
• 2019

Camera model identification has been a subject of steady study in the field of digital forensics. Among the increasingly sophisticated crimes, crimes such as illegal filming are taking up a high number of crimes because they are hard to detect as cameras become smaller. Therefore, technology that can specify which camera a particular image was taken on could be used as evidence to prove a criminal's suspicion when a criminal denies his or her criminal behavior. This paper proposes a deep learning model to identify the camera model used to acquire the image. The proposed model consists of four convolution layers and two fully connection layers, and a high pass filter is used as a filter for data pre-processing. To verify the performance of the proposed model, Dresden Image Database was used and the dataset was generated by applying the sequential partition method. To show the performance of the proposed model, it is compared with existing studies using 3 layers model or model with GLCM. The proposed model achieves 98% accuracy which is similar to that of the latest technology.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.05a
• /
• pp.599-600
• /
• 2013

In this paper, a platform of portable cultural assets surveillance system is designed in order to prevent the theft of cultural assets. The platform was designed to take into account the characteristics of the cultural assets for minimizing of the damage of cultural assets. The platform is composed of the portable cultural assets surveillance system and the collaboration network protocol among th surveillance system. If an intruder steals the cultural assets and moves according to the scheduled route, it is expected that the platform has a great role because the platform of portable cultural assets surveillance system can performs the continuous tracking by the collaboration network.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.1 s.33
• /
• pp.157-166
• /
• 2005

The Hair part of Cosmetology is development with Ubiquitous age. In this paper, 1 would design and implement for Ubiquitous Hair Changing on Ubiquitous network. Hair artist have customer's features in use digital camera for operating hair beauty. They are agree with hair design and style in monitor on internet at customer's choose in digital contents of cut, permanent, up-style, dye, long hair from web server. After operation on customer's hair from image of mobile terminal, hair artists take a photograph of customer's face and update it on internet. Customer's features was saved in her's mobile terminal. I would contribute to development of Beauty Information Society that the design of Ubiquitous Hair Changing System and the implement of digital hair contents that on-line internet system Sl mobile terminal were applied by Ubiquitous Network.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.10a
• /
• pp.221-224
• /
• 2019

본 논문에서는 엣지 컴퓨팅을 무인 마켓에 도입하여 엣지 컴퓨팅의 효율성을 확인하고, 로컬 네트워크의 효율적인 대역폭 할당을 위한 두 가지 방법을 제안한다. 무인 마켓과 같이 엄청난 양의 데이터를 필요로 하고 만들어내는 서비스에서는 데이터들을 클라우드로 전송하여 소비자가 불편함을 느끼지 못하도록 빠르게 처리하는 것은 불가능에 가깝다. 그래서 우리는 Amazon Go 를 벤치마킹한 무인 마켓에 엣지 컴퓨팅을 도입하여 이를 구현한다. 그리고 구현한 시스템에서 엣지 컴퓨팅 외에 클라우드 컴퓨팅, 모바일 장치를 적용하여 처리할 때의 응답 시간을 분석하여 엣지 컴퓨팅의 높은 성능을 확인한다. 또한, 구현한 무인 마켓에서 데이터 전송의 효율성을 더욱 높이기 위해 카메라 단위와 매대 단위의 대역폭 할당 기법을 제안한다. 카메라 단위로는 모션 인식기술을 활용하여 움직임이 감지될 때만 각 이미지 프로세스에서 요구되는 고해상도로 송신하는 기법을 제안한다. 매대 단위로는 네트워크에서 수용 가능한 대역폭 임계치에 도달하지 못하게 하기 위해 매대 별 우선순위에 따른 대역폭 할당 스케줄링 기법을 제안한다. 그 결과로 평균 소모대역폭과 최대 소모대역폭을 비교하여 제안한 두 가지 기법이 기존의 방법에 비해 성능을 향상시키는 것을 보인다.