• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.1
• /
• pp.15-22
• /
• 2017

With the advance of Internet Technology, various social network services are created and used by users. Especially, the use of smart devices makes that multimedia contents can be used and distributed on social network services. However, since the crime rate also is increased by users with illegal purposes, there are needs to protect contents and block illegal usage of contents with multimedia forensics. In this paper, we propose a multimedia forensic technique which is identifying the video source. First, the scheme to acquire the sensor pattern noise (SPN) using morphology filtering is presented, which comes from the imperfection of photon detector. Using this scheme, the SPN of reference videos from the reference device is estimated and the SPN of an unknown video is estimated. Then, the similarity between two SPNs is measured to identify whether the unknown video is acquired using the reference device. For the performance analysis of the proposed technique, 30 devices including DSLR camera, compact camera, camcorder, action cam and smart phone are tested and quantitatively analyzed. Based on the results, the proposed technique can achieve the 96% accuracy in identification.

• Proceedings of the Korean Society of Medical Physics Conference
• /
• 2004.11a
• /
• pp.122-125
• /
• 2004

In radiotherapy of tumors in liver, enough planning target volume (PTV) margins are necessary to compensate breathing-related movement of tumor volumes. To overcome the problems, this study aims to obtain patients' body movements by using a moving phantom and an ultrasonic sensor, and to develop respiration gating techniques that can adjust patients' beds by using reversed values of the data obtained. The phantom made to measure patients' body movements is composed of a microprocessor (BS II, 20 MHz, 8K Byte), a sensor (Ultra-Sonic, range 3 cm ${\sim}$3 m), host computer (RS232C) and stepping motor (torque 2.3Kg) etc., and the program to control and operate it was developed. The program allows the phantom to move within the maximum range of 2 cm, its movements and corrections to take place in order, and x, y and z to move successively. After the moving phantom was adjusted by entering random movement data(three dimensional data form with distance of 2cm), and the phantom movements were acquired using the ultra sonic sensor, the two data were compared and analyzed. And then, after the movements by respiration were acquired by using guinea pigs, the real-time respiration gating techniques were drawn by operating the phantom with the reversed values of the data. The result of analyzing the acquisition-correction delay time for the three types of data values and about each value separately shows that the data values coincided with one another within 1% and that the acquisition-correction delay time was obtained real-time (2.34 ${\times}$ 10$^{-4}$sec). This study successfully confirms the clinic application possibility of respiration gating techniques by using a moving phantom and an ultra sonic sensor. With ongoing development of additional analysis system, which can be used in real-time set-up reproducibility analysis, it may be beneficially used in radiotherapy of moving tumors.

• Radiation Oncology Journal
• /
• v.22 no.4
• /
• pp.316-324
• /
• 2004

Purpose : In radiotherapy of tumors in liver, enough planning target volume (PTV) margins are necessary to compensate breathing-related movement of tumor volumes. To overcome the problems, this study aims to obtain patients' body movements by using a moving phantom and an ultrasonic sensor, and to develop respiration sating techniques that can adjust patients' beds by using reversed values of the data obtained. Materials and Methods : The phantom made to measure patients' body movements is composed of a microprocessor (BS II, 20 MHz, 8K Byte), a sensor (Ultra-Sonic, range $3\~3$ m), host computer (RS232C) and stepping motor (torque 2.3 Kg) etc., and the program to control and operate it was developed. The program allows the phantom to move within the maximum range of 2 cm, its movements and corrections to take place In order, and x, y and z to move successively. After the moving phantom was adjusted by entering random movement data (three dimensional data form with distance of 2 cm), and the phantom movements were acquired using the ultra sonic sensor, the two data were compared and analyzed. And then, after the movements by respiration were acquired by using guinea pigs, the real-time respiration gating techniques were drawn by operating the phantom with the reversed values of the data. Results : The result of analyzing the acquisition-correction delay time the three types of data values and about each value separately shows that the data values coincided with one another within $1\%$ and that the acquisition-correction delay time was obtained real-time $(2.34{\times}10^{-4}sec)$. Conclusion : This study successfully confirms the clinic application possibility of respiration gating techniques by using a moving phantom and an ultrasonic sensor. With ongoing development of additional analysis system, which can be used in real-time set-up reproducibility analysis, it may be beneficially used in radiotherapy of moving tumors.

• Proceedings of the Korea Society for Energy Engineering kosee Conference
• /
• 2000.11a
• /
• pp.139-153
• /
• 2000

원자력 시스템의 안전성 획득을 위한 제어기기의 설계는 시스템의 동특성 모델에 대한 해석과 정상 운전을 저해할 수 있는 반응도 섭동 평가가 우선되어야 한다. 각 노형에 대한 동특성 모델 해석은 시스템의 고유한 응답특성을 평가할 수 있는 기반을 마련하는 것이며, 정상상태에서의 반응도의 섭동(reactivity perturbation) 평가는 과도 상태에서 시스템의 안전성 및 제어능 평가를 위한 제반 자료를 제공한다.(중략)

• Proceedings of the Korean Association of Geographic Inforamtion Studies Conference
• /
• 2010.06a
• /
• pp.296-297
• /
• 2010

본 연구는 비디오카메라와 GPS/MEMS IMU를 이용하여 동영상과 위치/자세 데이터를 동시에 취득하는 방법을 제안하고 시스템을 구축하였다. 구축된 시스템에 실시간 영상 georeferencing 알고리즘을 적용한다면 데이터 취득과 동시에 georeferenced 동영상을 획득할 수 있을 것으로 기대된다. 또한 이로부터 신속하게 대상물의 3차원 모델 등의 다양한 공간정보를 구축하여 증강현실 등에 활용될 수 있을 것이다. 향후 정확도 검증을 통해 시스템의 효용성을 입증할 것이다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.10b
• /
• pp.496-498
• /
• 2001

GIS를 이용한 원격 탐사 방법으로, 기존의 항공촬영을 위한 전용 항공기와 전용 촬영 장비를 사용하는 대신 경비행기와 소형 video-camera를 이용하여 비교적 저렴한 비용으로 자료 획득이 가능하다. 그러나 기존의 황공촬영 방식과 달리, 이 Video-GIS 방식은 좁은 시야각과 촬영 자세가 쉽게 변하는 문제점을 가지고 있으며, 동영상에서 각 영상 frame을 일일이 추출하여 수작업으로 mosaic하여 하나의 큰 영상을 만들어야 하는 단점이 있었다. 본 논문에서는 이러만 수동작업 영상 mosaic를 자동화하는 새로운 방법을 제시 하고자 한다.

• Proceedings of the Korean Association of Geographic Inforamtion Studies Conference
• /
• 2004.03a
• /
• pp.543-550
• /
• 2004

컴퓨터의 발전에 따라 현재 제4세대 수치사진측량의 활용도가 광범위하게 진행되고 있다. 특히 비디오동영상을 이용하여 실용적이며, 비전문가들도 활용할 수 있는 부분들이 증가하고 있다. 이러한 현시점에서 국가산업의 중추적인 시설물 도로분야에서 도로안전진단과 유지관리목적으로 도로정보획득 및 도로정보수집에 많은 연구를 하고 있다. 따라서, 본 연구에서는 실용성, 경제성이 있는 비전문가용인 디지털비디오 동영상을 이용하여 도로중심선의 3차원 위치정보를 추출하여 도로정보화사업의 기본적인 자료로 제공되리라 판단된다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.366-369
• /
• 2021

본 논문에서는 동영상에서 일련의 과정을 거쳐 얻었던 학습데이터를 보다 간편하고 빠른 속도로 획득하는 방법을 제안한다. 음성과 영상 스트림을 처리하는 ffmpeg을 이용해 영상을 프레임화하고, 딥 러닝 기반의 YOLO 알고리즘을 사용하여 객체를 검출한다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.3
• /
• pp.439-445
• /
• 2021

Low-cost, ultra-high-speed cameras, made possible by the development of image sensors and small displays, can be very useful in image processing and pattern recognition. This paper introduces an algorithm that corrects irregular lighting from a high-speed image that is continuously input with a slight time interval, and which then obtains an exposed skin color region that is the area of interest in a person from the corrected image. In this study, the non-uniform lighting effect from a received high-speed image is first corrected using a frame blending technique. Then, the region of interest is robustly obtained from the input high-speed color image by applying an elliptical skin color distribution model generated from iterative learning in advance. Experimental results show that the approach presented in this paper corrects illumination in various types of color images, and then accurately acquires the region of interest. The algorithm proposed in this study is expected to be useful in various types of practical applications related to image recognition, such as face recognition and tracking, lighting correction, and video indexing and retrieval.

• Proceedings of the KAIS Fall Conference
• /
• 2011.12b
• /
• pp.445-448
• /
• 2011

본 논문은 그룹화된 객체별 깊이정보를 차등 적용한 2D/3D 동영상 변환 기법에 관한 연구이다. 기존의 연구에서는 프레임의 움직임 정보와 기하학적 깊이 단서를 이용해 깊이정보를 추출하여 2D/3D 동영상 변환을 한다. 그러나 영상의 움직임 정보를 획득할 수 없는 영역의 경우 정확한 깊이정보를 얻을 수 없어 해당 영역의 3D 효과를 얻을 수 없는 문제점이 있다. 제안하는 기법에서는 객체 및 배경을 추출하고 움직임 정보와 기하학적 단서를 이용한 깊이정보를 그룹화된 객체별 차등 적용하여 움직임 정보가 없는 영역에서도 3D 효과를 얻을 수 있는 방법을 제안한다. 최종적으로 원본 영상과 생성된 깊이맵을 DIBR(Depth Image Based Rendering) 과정을 통해 3D 동영상을 생성한 결과 움직임 정보가 없는 영역에서도 3D 효과를 얻을 수 있었다.