• Proceedings of the Korea Society for Industrial Systems Conference
• /
• 2001.05a
• /
• pp.318-324
• /
• 2001

In this paper we propose the adaptive scheme to place more search points as long as the operation tapability of the motion estimator in the video codec permits. And the proposed algorithm takes advantage of the intuitive fact that the quality of the decoded video is more degraded as the spatial frequency of the corresponding block is increased due to the augmentation of local minima per unit area. Thererore, we propose the scheme to enhance the quality by locating relatively more search points in the block with high frequency components by analyzing the spatial frequencies of the video sequence. As a result, the proposed scheme can adaptively place more search points possibly permitted by the motion estimator and guarantees better quality compared to the TSS and FS.

• Archives of Plastic Surgery
• /
• v.38 no.3
• /
• pp.323-325
• /
• 2011

Purpose: Breast implant ruptures and displacement are problematic complications after augmentation mammoplasty. The authors report a patient whose cohesive silicone gel implant ruptured and migrated into the pleural cavity after augmentation mammoplasty. Methods: A 23-year-old female had received augmentation mammoplasty at a local clinic a week before visiting our hospital. When the patient's doctor performed a breast massage on the sixth postoperative day, the left breast became flattened. The doctor suspected a breast implant rupture and performed revision surgery. The implant, however, was not found in the submuscular pocket and no definite chest wall defect was found in the operative field. The doctor suspected implant migration into the pleural cavity, and after inserting a new breast implant, the doctor referred the patient to our hospital for further evaluation. The patient's vital signs were stable and she showed no specific symptoms except mild, intermittent pain in the left chest. A CT scan revealed the ruptured implant in the left pleural cavity and passive atelectasis. Results: The intrapleurally migrated ruptured implant was removed by video-assisted thoracic surgery (VATS). There were no adhesions but there was mild inflammation of the pleura. No definite laceration of the pleura was found. The patient was discharged on the first day after the operation without any complications. Conclusion: Surgeons should be aware that breast implants can rupture anytime and the injury to the chest wall, which may displace the breast implant into the pleural cavity, can happen during submuscular pocket dissection and implant insertion.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.10b
• /
• pp.454-456
• /
• 2001

본 논문에서는 비디오 영상열 내에 컴퓨터가 생성한 가상의 3D 영상을 이음새 없이 추가하기 위한 문제에 초점을 맞추고 있다. 2단계의 견고한 통계적인 메소드는 추적된 커브들의 모델-영상 대응점으로부터 보다 정확한 자세를 평가하기 위하여 자세 계산을 위해 사용되었다. 또한, 관점의 정확성 향상을 위하여 두 개의 연속하는 영상들간에 매치될 수 있는 핵심점을 카메라 움직임에 대한 상관관계 함수로 사용하여 매칭 에러와 reprojection 에러를 포함한 비용함수를 최소화함에 의해 관점을 향상시킨다. 비디오 영상내 객체 영상과 가상의 3D 영상간에 발생하는 폐색 공간문제를 해결하기 위하여 반 자동 알고리즘을 제안하였다.

• ETRI Journal
• /
• v.42 no.3
• /
• pp.411-419
• /
• 2020

In real-world intelligent transportation systems, accuracy in vehicle license plate detection and recognition is considered quite critical. Many algorithms have been proposed for still images, but their accuracy on actual videos is not satisfactory. This stems from several problematic conditions in videos, such as vehicle motion blur, variety in viewpoints, outliers, and the lack of publicly available video datasets. In this study, we focus on these challenges and propose a license plate detection and recognition scheme for videos based on a temporal matching prior network. Specifically, to improve the robustness of detection and recognition accuracy in the presence of motion blur and outliers, forward and bidirectional matching priors between consecutive frames are properly combined with layer structures specifically designed for plate detection. We also built our own video dataset for the deep training of the proposed network. During network training, we perform data augmentation based on image rotation to increase robustness regarding the various viewpoints in videos.

• Journal of Sensor Science and Technology
• /
• v.33 no.1
• /
• pp.18-23
• /
• 2024

Humanoid robots, designed to interact in human environments, require stable mobility to ensure safety. When a humanoid robot falls, it causes damage, breakdown, and potential harm to the robot. Therefore, fall detection is critical to preventing the robot from falling. Prevention of falling of a humanoid robot requires an operator controlling a crane. For efficient and safe walking control experiments, a system that can replace a crane operator is needed. To replace such a crane operator, it is essential to detect the falling conditions of humanoid robots. In this study, we propose falling detection methods using Convolution Neural Network (CNN) model. The image data of a humanoid robot are collected from various angles and environments. A large amount of data is collected by dividing video data into frames per second, and data augmentation techniques are used. The effectiveness of the proposed CNN model is verified by the experiments with the humanoid robot MAX-E1.

• Journal of Broadcast Engineering
• /
• v.7 no.1
• /
• pp.2-9
• /
• 2002

Recently. VR( Virtual Reality) applications such as virtual studio and virtual character are wifely used In TV programs. and AR( Augmented Reality) applications are also belong taken an interest increasingly. This paper introduces a virtual screen system. which Is a new AR application for broadcasting. The virtual screen system is a real-time video augmentation system by tracking a chroma-patterned moving panel. We haute recently developed a virtual screen system.'K-vision'. Our system enables the user to hold and morse a simple panel on which live video, pictures of 3D graphics images can appear. All the Images seen on the panel change In the correct perspective, according to movements of the camera and the user holding the panel, in real-time. For the purpose of tracking janet. we use some computer vision techniques such as blob analysis and feature tracking. K-vision can work well with any type of camera. requiring no special add-ons. And no need for sensor attachments to the panel. no calibration procedures required. We are using K-vision in some TV programs such as election. documentary and entertainment.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.532-534
• /
• 2022

본 논문에서는 미생 드라마 비디오들을 토대로 구축한 비디오 인물 개체 분할 데이터 집합인 MHIS를 소개하고, 등장인물 클래스 간의 심각한 데이터 불균형 문제를 효과적으로 해결하기 위한 새로운 비디오 데이터 보강 기법인 CDVA를 제안한다. 기존의 비디오 데이터 보강 기법들과는 달리, 새로운 CDVA 보강 기법은 비디오의 시공간적 맥락을 충분히 고려해서 부족한 인물 클래스의 훈련 비디오 데이터들을 추가 생성함으로써, 비디오 개체 분할 신경망 모델의 성능을 효과적으로 개선시킬 수 있다. 본 논문에서는 정량 및 정성 실험들을 통해, 제안 비디오 데이터 보강 기법의 우수성을 입증한다.

• Archives of Plastic Surgery
• /
• v.50 no.6
• /
• pp.557-562
• /
• 2023

Augmentation mammoplasty is one of the most popular cosmetic surgeries, but there is a high reoperation rate (29.7%) commonly due to capsular contracture, implant malpositioning, infection, and unsatisfactory size. Although infection only accounts for 2% of cases, its management is very challenging, especially with nontuberculous mycobacteria (NTM) infection. Breast prosthetic NTM infection is a rare but is a disastrous condition with an incidence of approximately 0.013%. Immediate salvage reimplantation is usually not suggested, and most studies recommend a gap of 3 to 6 months after combination antibiotics therapy before reimplantation. However, delayed reimplantation often leads to great psychological stress and struggle between the doctor and patient. We present the case report of successful reimplantation in treating prosthetic NTM infections in a 28-year-old female. We discuss a novel technique "transaxillary capsulorrhaphy" to correct the bottoming-out deformity. One year after the combination of antibiotics and surgery, the follow-up computed tomography scan showed complete remission of NTM without recurrence. We discuss the surgical technique in detail. The 1-year follow-up assessment (photos and dynamic video) revealed good cosmesis and reliable correction using the new technique. This report is the first formal description and discussion of one-stage reimplantation following NTM infections. Transaxillary capsulorrhaphy allows for a successful salvage operation when an implant is displaced. This approach provides highly favorable result in eastern women undergoing revision augmentation mammoplasty. This study reflects level of evidence V, considering opinions of respected authorities based on clinical experience, descriptive studies, or reports of expert committees.

• Journal of Broadcast Engineering
• /
• v.27 no.1
• /
• pp.44-55
• /
• 2022

In order to automatically provide information on fruits in agricultural related broadcasting contents, instance image segmentation of target fruits is required. In addition, the information on the 3D pose of the corresponding fruit may be meaningfully used. This paper represents research that provides information about tomatoes in video content. A large amount of data is required to learn the instance segmentation, but it is difficult to obtain sufficient training data. Therefore, the training data is generated through a data augmentation technique based on a small amount of real images. Compared to the result using only the real images, it is shown that the detection performance is improved as a result of learning through the synthesized image created by separating the foreground and background. As a result of learning augmented images using images created using conventional image pre-processing techniques, it was shown that higher performance was obtained than synthetic images in which foreground and background were separated. To estimate the pose from the result of object detection, a point cloud was obtained using an RGB-D camera. Then, cylinder fitting based on least square minimization is performed, and the tomato pose is estimated through the axial direction of the cylinder. We show that the results of detection, instance image segmentation, and cylinder fitting of a target object effectively through various experiments.

• The KIPS Transactions:PartB
• /
• v.13B no.5 s.108
• /
• pp.499-506
• /
• 2006

This Paper describes a fast and stable camera pose estimation method for real-time augmented reality systems. From the feature tracking results of a marker on a single frame, we estimate the camera rotation matrix and the translation vector. For the camera pose estimation, we use the shape factorization method based on the scaled orthographic Projection model. In the scaled orthographic factorization method, all feature points of an object are assumed roughly at the same distance from the camera, which means the selected reference point and the object shape affect the accuracy of the estimation. This paper proposes a flexible and stable selection method for the reference point. Based on the proposed method, we implemented a video augmentation system that inserts virtual 3D objects into the input video frames. Experimental results showed that the proposed camera pose estimation method is fast and robust relative to the previous methods and it is applicable to various augmented reality applications.