• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.71-72
• /
• 2020

본 논문에서는 자동차 블랙박스를 사용하여 촬영된 비디오에서 자동차 사고 발생 여부를 판단하는 방법을 제안한다. 제안한 방법은 우선 객체 추적 과정에서 구한 조감도 좌표를 사용하여 각 차량 사이의 거리에 기반을 두고 교통사고 여부를 판단한다. 그런데 거리만을 사용하여 사고 여부를 판단하는 경우 자동차가 밀집된 주·정차 환경에서는 오검출의 확률이 높아질 수 있다. 이를 위해 각 차량에 대한 움직임 벡터를 계산하고 벡터 간의 정보(사잇각과 크기 등)를 사용하여 차량의 주·정차 여부를 판단한 후 사고 검출 대상에서 배제할 수 있도록 한다. 주·정차 판단 여부를 통해 사고 검출의 정확도를 향상할 수 있는 것을 실험적으로 확인하였다.

• Journal of Chest Surgery
• /
• v.31 no.12
• /
• pp.1212-1216
• /
• 1998

Background: Recently thoracoscopic surgery is widely applied in thoracic surgical field and hyperhidrosis is one of the most frequently operated diseases. Material and Method: From June 1997 to February 1998, 30 patients with hyperhidrosis underwent bilateral thoracic sympathectomy under thoracoscopy at Inje University Sanggye Paik Hospital. There were 10 males and 20 females whose mean age was 22.42±6.84 years ranging from 17 to 51. All patients underwent bilateral thoracic sympathectomy under semi-sitting position and two 5 mm sized trocars were inserted. Result: Mean operation time was 52.32±11.72 minutes and the mean elevation of palmar temperature after sympathectomy was 2.17±0.47℃. Eighteen patients(60%) complained compensatory hyperhidrosis. All patients except one were able to discharge at the operation day or postoperative one day. There were no recurrence during follow up from 2 to 8 months(mean 5.30±2.17 months). Conclusion: Thoracoscopic sympathectomy is simple and effective technique in hyperhidrosis and widely applied indication will be necessary. We conclude that further discussion should be made about the resection area and method to get maximal effect and minimal side effect.

• Journal of Chest Surgery
• /
• v.31 no.7
• /
• pp.692-696
• /
• 1998

For the management of a secondary spontaneous pneumothorax, videothoracoscopic surgery may offer the potential therapeutic benefits of a minimally invasive approach. We report on a series of 36 patients(33 men and 3 women) with a mean age of 56.3 years(range, 31 to 80 years) who underwent thoracoscopic surgical procedures for the treatment of secondary spontaneous pneumothorax. Twenty-one patients had emphysema and 20 patients had old pulmonary tuberculosis. Nineteen patients presented a persistent severe air leak more than 3 days preoperatively and 15 patients had more than one recurrence. Bullectomy or exclusion of the lesion was performed in 33 patients. Mechanical pleurodesis was performed in the entire patients, talc was sprayed in 22 and vibramycin in 14. Mild pleural adhesion at the upper lobe was shown in 10 patients and severe pleural adhesion in 7 patients. One patient with persistent air leak died of persistent air leak and respiratory failure. The mean postoperative stay was 7.0 days(range, 2 to 17 days). At a mean follow-up of 15.8 months (range, 5 to 45 months), no pneumothorax had recurred. In comparison with the result of the treatment for 112 patients with primary spontaneous pneumothorax, the operating time was not significantly longer and there were no more primary treatment failures, but the duration of postoperative chest drainage and hospital stay was longer. Videothoracoscopic surgery has proved to be an effective treatment for secondary spontaneous pneumothorax in elderly patients who represent high-risk candidates for thoracotomy.

• International Journal of Highway Engineering
• /
• v.10 no.2
• /
• pp.159-166
• /
• 2008

Video image processing systems (VIPS) offer numerous benefits to transportation models and applications, due to their ability to monitor traffic in real time. VIPS based on a wide-area detection algorithm provide traffic parameters such as flow and velocity as well as occupancy and density. However, most current commercial VIPS utilize a tripwire detection algorithm that examines image intensity changes in the detection regions to indicate vehicle presence and passage, i.e., they do not identify individual vehicles as unique targets. If VIPS are developed to track individual vehicles and thus trace vehicle trajectories, many existing transportation models will benefit from more detailed information of individual vehicles. Furthermore, additional information obtained from the vehicle trajectories will improve incident detection by identifying lane change maneuvers and acceleration/deceleration patterns. However, unlike human vision, VIPS cameras have difficulty in recognizing vehicle movements over a detection zone longer than 100 meters. Over such a distance, the camera operators need to zoom in to recognize objects. As a result, vehicle tracking with a single camera is limited to detection zones under 100m. This paper develops a methodology capable of monitoring individual vehicle trajectories based on image processing. To improve traffic flow surveillance, a long distance tracking algorithm for use over 200m is developed with multi-closed circuit television (CCTV) cameras. The algorithm is capable of recognizing individual vehicle maneuvers and increasing the effectiveness of incident detection.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.5
• /
• pp.423-430
• /
• 2013

In typical face recognition systems, the frontal view of face is preferred to reduce the complexity of the recognition. Thus individuals may be required to stare into the camera, or the camera should be located so that the frontal images are acquired easily. However these constraints severely restrict the adoption of face recognition to wide applications. To alleviate this problem, in this paper, we address the problem of tracking and recognizing faces in video captured with no environmental control. The face tracker extracts a sequence of the angle/size normalized face images using IVT (Incremental Visual Tracking) algorithm that is known to be robust to changes in appearance. Since no constraints have been imposed between the face direction and the video camera, there will be various poses in face images. Thus the pose is identified using a PCA (Principal Component Analysis)-based pose classifier, and only the pose-matched face images are used to identify person against the pre-built face DB with 5-poses. For face recognition, PCA, (2D)PCA, and $(2D)^2PCA$ algorithms have been tested to compute the recognition rate and the execution time.

• Journal of Chest Surgery
• /
• v.34 no.8
• /
• pp.621-625
• /
• 2001

For many years, 10mm videothoracoscope has been widely used in bullectomy of primary spontaneous pneumothorax. However we used a 2mm videothoracoscope to minimize operative wound. Thus, we compared the clinical results of bulllectomy using 2mm videothoracoscope with bullectomy using 10mm videothoracoscope. Material and method: We analyzed 118 patients who underwent VATS for primary spontaneous pneumothorax from April, 1998 to December, 2000. 2mm videothoracoscope was used in 53 patients(Group A) and 10mm videothoracoscope was used in 65 patients(Group B). The mean age was 20.2$\pm$6.9 years old in group A and 20.1$\pm$6.1 years old in group B. The mean follow up was 10.9$\pm$3.8 months in group A and 11.4$\pm$4.3 months in group B. Result: The operation time was shorter in group A than group B(55.7$\pm$22.9 minutes, 71.2$\pm$21.4 minutes, p<0.05). The duration of postoperative hospital stay was shorter in group A than group B(7.2$\pm$3.2 days, 9.2$\pm$3.6 days, p<0.05). The duration of postoperative chest tube indwelling was shorter in group A than group B(4.7$\pm$3.1 days, 6.3$\pm$2.8 days, p<0.05). The duration of postoperative air leakage(0.6$\pm$2.1 days, 1.0$\pm$2.4 days, p>0.05), the amount of analgesics(1.38$\pm$1.0 ampules, 1.7$\pm$1.4 ampules, p>0.05), the amount of analgesics(1.38$\pm$1.0 ampules, 1.7$\pm$1.4 ampules, p>0.05), postperative complications(2 cases, 7cases, p>0.05) and recurrences(1 case, 1 case, p>0.05) were not statistically different between two groups. Operative wound was smaller in group A than B. Conclusion: There were non adverse results in group A than group B. Furthermore, bullectomy using 2mm videothoracoscope brought us minimized operative wound and good cosmetic results. Thus, we could recommend bullectomy using 2mm videothoracoscope in primary spontaneous penumothorax.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.7 no.2
• /
• pp.82-85
• /
• 2014

It is helpful to use Intelligent Video Surveillance to replace and supplement the demerit which can possibly occur due to the mistake that can be made by human management. To accomplish this, it is essential that the system should digitalize image information from surveillance camera so that the system, itself, can be able to locate a object and to analyze the pattern of the object. Also, it is imperative that the system should have ability to operate a alarm and a entrance blocking system and to notify a situation to a security manager. Zooming a small object form a screen, however, requires a exact zooming ratio of the object and a shift of centric coordinate. In this paper, It is able to locate and observe closely a object from flexible background, regardless of the distance, by calculating a zooming ratio according to object moment, pan coordinate, and tilt coordinate.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.11 no.4
• /
• pp.189-196
• /
• 1999

In order to verify a numerical model for the calculation of wave motion around an offshore barrier in shallow water, laboratory physical experiments are necessary. In this study, sample experiments are carried out on the wave and wave induced current fields due to a sloping bottom topography and on that due to an isolated structure from the coastline. The water body is divided into 4 levels, in which the current tracking floaters are deployed to measure the wave induced currents. Data measurement was continued using the limited wave gauges and current tracking floaters including a video camera from the top. The wave heights for the preselected surface and time-averaged velocity distributions at each level were measured in detail. The distribution of wave and current fields was analyzed precisely combining the whole measured laboratory data. Moreover, comprehensive analyses were carried out on non-linearity of wave transformation in terms of skewness and atiltness.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.41 no.4
• /
• pp.9-21
• /
• 2004

The current paper proposes a genetic algorithm (GA)-based segmentation method that can automatically extract and track moving objects. The proposed method mainly consists of spatial and temporal segmentation; the spatial segmentation divides each frame into regions with accurate boundaries, and the temporal segmentation divides each frame into background and foreground areas. The spatial segmentation is performed using chromosomes that evolve distributed genetic algorithms (DGAs). However, unlike standard DGAs, the chromosomes are initiated from the segmentation result of the previous frame, then only unstable chromosomes corresponding to actual moving object parts are evolved by mating operators. For the temporal segmentation, adaptive thresholding is performed based on the intensity difference between two consecutive frames. The spatial and temporal segmentation results are then combined for object extraction, and tracking is performed using the natural correspondence established by the proposed spatial segmentation method. The main advantages of the proposed method are twofold: First, proposed video segmentation method does not require any a priori information second, the proposed GA-based segmentation method enhances the search efficiency and incorporates a tracking algorithm within its own architecture. These advantages were confirmed by experiments where the proposed method was success fully applied to well-known and natural video sequences.

• The Journal of the Korea Contents Association
• /
• v.10 no.4
• /
• pp.66-75
• /
• 2010

In Augmented Reality, it needs restoration and tracking of a real-time scene structure for the augmented 3D model from input video or images. Most of the previous approaches construct accurate 3D models in advance and try to fit them in real-time. However, it is difficult to measure 3D model accurately and requires long pre-processing time to construct exact 3D model specifically. In this research, we suggest a real-time scene structure analysis method for the wide indoor mobile augmented reality, using only generic models without exact pre-constructed models. Our approach reduces cost and time by removing exact modeling process and demonstrates the method for restoration and tracking of the indoor repetitive scene structure such as corridors and stairways in different scales and details.