• Journal of Korea Society of Digital Industry and Information Management
• /
• v.14 no.1
• /
• pp.77-85
• /
• 2018

This paper proposes a robust digital video stabilization algorithm to extract and track an object, which uses a phase correlation-based motion correction. The proposed video stabilization algorithm consists of background stabilization based on motion estimation and extraction of a moving object. The motion vectors can be estimated by calculating the phase correlation of a series of frames in the eight sub-images, which are located in the corner of the video. The global motion vector can be estimated and the image can be compensated by using the multiple local motions of sub-images. Through the calculations of the phase correlation, the motion of the background can be subtracted from the former frame and the compensated frame, which share the same background. The moving objects in the video can also be extracted. In this paper, calculating the phase correlation to track the robust motion vectors results in the compensation of vibrations, such as movement, rotation, expansion and the downsize of videos from all directions of the sub-images. Experimental results show that the proposed digital image stabilization algorithm can provide continuously stabilized videos and tracking object movements.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.9C
• /
• pp.859-868
• /
• 2006

H.264에서 다중참조 프레임을 사용한 움직임 예측 방법은 단일 참조프레임을 이용한 움직임 예측보다 더 많은 시간적 중복성을 제거하여 부호화 효율을 높이거나 채널에러에 강인하게 부호화하기 위해 사용된다. 하지만 다중 참조 프레임을 이용하여 움직임 예측을 하는 것은 단일의 참조 프레임을 이용하는 것보다 많은 계산량을 요구하기 때문에 비디오 인코더의 복잡도를 증가시키게 된다. 본 논문에서는 다중참조 프레임을 사용한 움직임 예측을 화질 열화 없이 적은 복잡도로서 가능하게 하는 알고리즘을 제안한다. 움직임 예측 절차의 복잡도를 줄이기 위해, 제안한 알고리즘에서는 연속되는 프레임 사이에 구성된 움직임 벡터맵을 이용하여 움직임벡터를 추정한다. 제안한 방식은 추정된 움직임벡터를 작은 탐색영역에서 보정하는 방식을 적용하기 때문에 기존의 방식들에 비해 적은 복잡도가 요구된다. 제안된 방법으로 추정된 움직임벡터는 각 참조프레임들에 대해 최적의 움직임 벡터를 효과적으로 추적하기 때문에 부호화 된 영상의 화질은 전 탐색영역 움직임 예측 알고리즘을 이용한 결과와 매우 비슷하다. 제안된 방식은 세가지 단계로 구성된다. (a) 연속되는 두 개의 프레임 사이에 벡터맵을 구성한다. (b) 벡터맵에 있는 요소벡터를 이용하여 시간적 움직임 벡터를 구성한다. (c) 마지막으로, 임시 움직임 벡터를 좁은 탐색영역에서 보정한다. 컴퓨터 실험을 통해 제안된 방식의 효율성을 입증하였다. 제안된 방식과 기존의 방식들과의 비교를 위해 H.264 부호화기에서 움직임 예측 모듈에 의해 소비된 CPU 시간을 측정하였다. 컴퓨터 실험을 통해 알 수 있듯이 제안된 방식에 의해 부호화된 영상의 화질은 기존 방식과 을 통해 얻은 영상화질과 거의 같으면서 알고리즘 복잡도는 크게 줄어드는 것을 볼 수 있다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.12C
• /
• pp.727-737
• /
• 2011

This paper presents an implementation scheme of real-time lane and vehicle detection system with FPGA and DSP. In this type of implementation, defining the functionality of each device in efficient manner is of crucial importance. The FPGA is in charge of extracting features from input image sequences in reduced form, and the features are provided to the DSP so that tracking lanes and vehicles are performed based on them. In addition, a way of seamless interconnection between those devices is presented. The experimental results show that the system is able to process at least 15 frames per second for video image sequences with size of $640{\times}480$.

• Journal of Digital Contents Society
• /
• v.8 no.3
• /
• pp.371-376
• /
• 2007

Many modules such as controller, sensor, telematics terminal, navigation, audio and video are connected each other via vehicle network (CAN, MOST, etc). Futhermore, users can have ITS or internet services in moving by connecting to wireless mobile network. These network capabilities can cause a lots of security issues such as data hacking, privacy violation, location tracking and so on. Some possibilities which raise a breakdown or accident by hacking vehicle operation data (sensor, control data) are on the increase. In this paper, we propose a security module which has encryption functionalities and can be used for vehicle network system such as CAN, MOST, etc. This security module can provide conventional encryption algorithms and digital signature processing functionality such as DES, 3-DES, SEED, ECC, and RSA.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.05a
• /
• pp.830-833
• /
• 2016

자동차 번호판 인식은 대중적인 감시 기술 중의 한 종류로서, 주어진 비디오나 영상 내 광학문자 인식을 수반한다. 고속도로나 국도 상에 과속 단속 시스템, 재형 건물이나 유통센서 및 주차장 등에서 주차 정산 시스템, 고속도로 톨 게이트에서 hi-pass 에러 및 불법 도주 차량 잔속 시스템, 전국 주요 도로 불법 주 정차 단속 시스템, 공공기관, 기업 출퇴근 시간 확인 및 외부 차양 안내 시스템 등의 지능형 교통 시스템(ITS)이나 국도 상에 범위 차량 검거 시스템, 사건 발생 시 주요 도로상에 설치된 CCTV를 통해 용의 차량 이동 추적 시스템, 이동식 범죄 차량 조회, 버스에 탑재된 버스 전용차선 위반 단속들의 지능형 방범 시스템 등에 활용하고 있다. 번호판 인식은 자동차 번호판 국부화, 번호판의 크기, 차원, 명암대비, 밝기를 조정하는 정규화, 개별문자를 얻어내는 문자 분할, 문자를 인식하는 광학 문자 인식, 번호판의 형태, 크기, 위치 들이 연도별, 지역별로 차이가 있는 번호판들의 데이터베이스를 비교하여 구문 분석을 하는 절차를 거친다. 본 논문에서는 EmguCV를 이용하여 구현한 번호판 감지를 수행하여 위치를 찾아내고, 오픈 소스 광학 문자 인식 엔진으로 잘 알려져 있는 테서렉트 OCR을 이용하여 번호판의 문자를 인식하는 자동 인식 프로그램을 구현하고 기술하였다.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.5 no.3
• /
• pp.309-314
• /
• 2010

In this paper, an intelligent security camera over internet is proposed. Among ISC methods, watersheds based methods produce a good performance in segmentation accuracy. But traditional watershed transform has been suffered from over-segmentation due to small local minima included in gradient image that is input to the watershed transform. And a zone face candidates of detection using skin-color model. last step, face to check at face of candidate location using SVM method. It is extract of wavelet transform coefficient to the zone face candidated. Therefore, it is likely that it is applicable to read world problem, such as object tracking, surveillance, and human computer interface application etc.

• Journal of Chest Surgery
• /
• v.40 no.7 s.276
• /
• pp.492-498
• /
• 2007

Background: Malignant pleural effusion is a common condition in neoplastic patients and palliative therapy is the usual treatment. Talc has been generally accepted to be the most effective sclerosant for chemical pleurodesis, but the optimal route of administration remains controversy. We compared the results of video-assisted thoracoscopic talc poudrage (VTP) with administering a bedside talc slurry through a chest tube (BTS) for the treatment of malignant pleural effusion. Material and Method: From December 2004 to May 2006, 20 patients with malignant pleural effusion underwent chemical pleurodesis via VTP (group A, n=10), and BTS (group B, n=10). Result: The durations of chest tube placement after the procedure were $7.0{\pm}4.0$ days (group A) and $6.7{\pm}3.6$ days (group B). The hospital stays were $24.3{\pm}9.4$ days (group A) and $30.7{\pm}21.5$ days (group B), respectively. The symptoms of dyspnea were much more improved in group A (p-value=0.014) after discharge (mean f/u group $A=8.5{\pm}2.2$ months, group B $8.0{\pm}7.4$ months). The collapsed portions of lung were better expanded in group A than in group B (p-value=0.011). Conclusion: We recommend VTP for the selected patients with malignant pleural effusion because of the advantages of dissecting the fibrous peel to relieve the atelectasis and dyspnea, and excising the pleura for diagnosis with direct viewing of the lesion.

• Journal of Chest Surgery
• /
• v.29 no.10
• /
• pp.1081-1089
• /
• 1996

Pulmonary atresia with intact ventricular septum has continued to have a high surgical mortality and morbidity. This mAy attribute to the non-uniformity of the anomaly. We reviewed a total of 34 infants with pulmonary atresla and intact ventricular septum managed in this hospital between 1987 and 1995. Mean age and body weight were 57.2 (range, 3-208) days and 4.1 (range, B.3∼6.8) kg. The preoperative Z-value of the diameter of the tricuspid valve was less than -2 in 85.2% of patients and less than -4 in 33. 3% . It is well correlated w th right ventricular cavity size (n=27. r10.68, p< 0.05). Coronary artery-right ventricular fistulas were identified in 3 patients, and right ventricular dependency was suspected in 1 Over All hospital mortality was 23.5%(8/34), although it decreased to 16.6%(4124) in 1990s. Subsequent procedures were performed in 6 patients between 3 days and 58 months after Initial palliation : one bidirectional cavopulmonary shunt and 1 Fontan operation after systemic-pulmonary shunt, 3 transannular patch + atrial septal defect closure and 1 additional systemic-pulmonary shunt after polmonary valvectomy or valvotomy. Changes of Z-values of the diameter of tricuspid valve have been followed up in 11 patients between 1 and 66 months postoperatively. Z-values were increased In 5 out of 8 transannular right ventriculAr outflow tract enlargement group and in 1 out of 3 pulmonary valvectomy or valvotomy group. Our data suggest that tailoring a treatment to right ventricular cavity size and coronary anom lies may improve the surgical outcome. A Z-value of the tricuspid valve diameter could be used.

• Journal of Chest Surgery
• /
• v.32 no.3
• /
• pp.294-298
• /
• 1999

Background: Video-assisted thoracoscopic surgery(VATS) has been established as a new method for treatment of spontaneous pneumothorax. We compared the clinical results of VATS with those of thoracotomy performed during the recent 5 years. Material and Method: We analyzed 126 patients whose medical records were available among the 154 patients who underwent operations for spontaneous pneumothorax from 1992 to 1996. The mean age was 27.1 years(15 to 75 years). 87 patients were operated on by VATS(Group A) and the other 39 by thoracotomy(Group B). The mean follow-up period was 14.7 months. Result: The operation time was shorter in group A than in group B(90.6${\pm}$38.6minutes: 117.2${\pm}$58.9minutes, p<0.05). The duration of postoperative hospital stay was shorter in group A than in group B(6.7${\pm}$4.2: 9.4${\pm}$3.3 days, p<0.05). The amount of analgesics(nalbuphin HCl, ketoprofen) used postoperatively were 2.4${\pm}$2.8 ampules in group A, which is less than the 6.5${\pm}$5.6 ampules in group B(p<0.05). The number of staples used in group A was smaller(2.7${\pm}$1.3 in group A, 1.76${\pm}$1.1 in group B, p<0.05). The duration of chest tube indwelling(4.3${\pm}$4.0 days in group A, and 5.6${\pm}$3.0 days in group B, NS), the recurrence rate(13.8% in group A, 2.6% in group B, NS), and the duration of air leakage(1.3${\pm}$3.3 days in group A, and 1.0${\pm}$2.5days in group B, NS) were not statistically different between the two groups. Conclusion: The application of VATS for the treatment of spontaneous pneumothorax has brought in better clinical results(shorter operation time, shorter hospital stay, less pain, and better cosmetic merits) than the thoracotomy without increasing any morbidity. However no advantages in recurrence rates and duration of postoperative air leakages are revealed.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.46 no.2
• /
• pp.84-91
• /
• 2009

This paper presents an online partial 3D modeling methodology that uses a mobile augmented reality system and aerial photographs, and a tracking methodology that compares the 3D model with a video image. Instead of relying on models which are created in advance, the system generates a 3D model for a real building on the fly by combining frontal and aerial views. A user's initial pose is estimated using an aerial photograph, which is retrieved from a database according to the user's GPS coordinates, and an inertial sensor which measures pitch. We detect edges of the rooftop based on Graph cut, and find edges and a corner of the bottom by minimizing the proposed cost function. To track the user's position and orientation in real-time, feature-based tracking is carried out based on salient points on the edges and the sides of a building the user is keeping in view. We implemented camera pose estimators using both a least squares estimator and an unscented Kalman filter (UKF). We evaluated the speed and accuracy of both approaches, and we demonstrated the usefulness of our computations as important building blocks for an Anywhere Augmentation scenario.