• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.11
• /
• pp.465-472
• /
• 2022

In this paper, the style synthesis network is trained to generate style-synthesized video through the style synthesis through training Stylegan and the video synthesis network for video synthesis. In order to improve the point that the gaze or expression does not transfer stably, 3D face restoration technology is applied to control important features such as the pose, gaze, and expression of the head using 3D face information. In addition, by training the discriminators for the dynamics, mouth shape, image, and gaze of the Head2head network, it is possible to create a stable style synthesis video that maintains more probabilities and consistency. Using the FaceForensic dataset and the MetFace dataset, it was confirmed that the performance was increased by converting one video into another video while maintaining the consistent movement of the target face, and generating natural data through video synthesis using 3D face information from the source video's face.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.10a
• /
• pp.1137-1140
• /
• 2019

가상현실(Virtual Reality, VR), 증강현실(Augmented Reality, AR), 혼합현실(Mixed Reality, MR) 분야에 유용한 인간 컴퓨터 인터페이스 기술은 필수적이다. 특히 휴먼 손동작 인식 기술은 직관적인 상호작용을 가능하게 하여, 다양한 분야에서 편리한 컨트롤러로 사용할 수 있다. 본 연구에서는 뎁스 영상 기반의 1 인칭 시점 손동작 인식을 위하여 손동작 데이터베이스 생성 시스템을 구축하여, 손동작 인식기 학습에 필요한 1 인칭(Egocentric View Point) 데이터베이스를 촬영하여 제작한다. 그리고 모바일 Head Mounted Device(HMD) VR 을 위한 뎁스 영상 기반 1 인칭 시점 손동작 인식(Hand Pose Recognition, HPR) 딥러닝 Deep Residual Network 를 구현한다. 최종적으로, 안드로이드 모바일 디바이스에 학습된 Residual Network Regressor 를 이식하고 모바일 VR 에 실시간 손동작 인식 시스템을 구동하여, 모바일 VR 상 실시간 3D 손동작 인식을 가상 물체와의 상호작용을 통하여 확인 한다.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.3
• /
• pp.150-159
• /
• 2022

This paper presents an implementation of detecting whether a helmet is worn and there is a fall accident through individual image analysis in real-time from extracting the image objects of several workers active in the industrial field. In order to detect image objects of workers, YOLO, a deep learning-based computer vision model, was used, and for whether a helmet is worn or not, the extracted images with 5,000 different helmet learning data images were applied. For whether a fall accident occurred, the position of the head was checked using the Pose real-time body tracking algorithm of Mediapipe, and the movement speed was calculated to determine whether the person fell. In addition, to give reliability to the result of a falling accident, a method to infer the posture of an object by obtaining the size of YOLO's bounding box was proposed and implemented. Finally, Telegram API Bot and Firebase DB server were implemented for notification service to administrators.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.16 no.3
• /
• pp.115-122
• /
• 2016

This paper proposes a system to detect driver's cognitive state by internal and external information of vehicle. The proposed system can measure driver's eye gaze. This is done by concept of information delivery and mutual information measure. For this study, we set up two web-cameras at vehicles to obtain visual information of the driver and front of the vehicle. We propose Gestalt principle based selective attention model to define information quantity of road scene. The saliency map based on gestalt principle is prominently represented by stimulus such as traffic signals. The proposed system assumes driver's cognitive resource allocation on the front scene by gaze analysis and head pose direction information. Then we use several feature algorithms for detecting driver's characteristics in real time. Modified census transform (MCT) based Adaboost is used to detect driver's face and its component whereas POSIT algorithms are used for eye detection and 3D head pose estimation. Experimental results show that the proposed system works well in real environment and confirm its usability.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.2C
• /
• pp.141-149
• /
• 2007

Associating the shoulder line with head location of the human body is useful in verifying, localizing and tracking persons in an image. Since the head line and the shoulder line, what we call ${\Omega}$-shape, move together in a consistent way within a limited range of deformation, we can build a statistical shape model using Active Shape Model (ASM). However, when the conventional ASM is applied to ${\Omega}$-shape fitting, it is very sensitive to background edges and clutter because it relies only on the local edge or gradient. Even though appearance is a good alternative feature for matching the target object to image, it is difficult to learn the appearance of the ${\Omega}$-shape because of the significant difference between people's skin, hair and clothes, and because appearance does not remain the same throughout the entire video. Therefore, instead of teaming appearance or updating appearance as it changes, we model the discriminative appearance where each pixel is classified into head, torso and background classes, and update the classifier to obtain the appropriate discriminative appearance in the current frame. Accordingly, we make use of two features in fitting ${\Omega}$-shape, edge gradient which is used for localization, and discriminative appearance which contributes to stability of the tracker. The simulation results show that the proposed method is very robust to pose change, occlusion, and illumination change in tracking the head and shoulder line of people. Another advantage is that the proposed method operates in real time.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.701-706
• /
• 2009

We proposed the device to control a computer with only a head and eye blinks so that disabilities by car accidents can use a computer. Because they have paralysis of their upper extremities such as C4~C5 paraplegics and cerebral palsy, they cannot efficiently access a general keyboard/mouse not using hands and foots. The cursor position was estimated from a gyro-sensor which can measure head movements, and the mouse event such as click/double click from opto-sensors which can detect eye blinks. The sensor was put on the proper goggle in order not to disturb the visual field. The performance of the proposed device was compared to a general optical mouse, and was used both relative and absolute coordinate in cursor positioning control. The recognition rate of click and double-click was 86% of the optical mouse, the speed of cursor movement by the proposed device was not much different from the mouse. The overall accuracy was 80%. Especially, the relative coordinate is more convenience and accuracy than the absolute coordinate, and can reduce the frequency of reset to prevent the accumulative error.

• Korean Journal of Head & Neck Oncology
• /
• v.13 no.2
• /
• pp.180-186
• /
• 1997

Objectives: Salivary gland tumors pose considerable difficulty in diagnostic and prognostic assessment based on the histopathologic features alone. We studied the expression of type IV collagen and fibronectin in salivary gland tumors with special emphasis on the differential diagnostic significance. Materials and Methods: We did immunohistochemical stain on paraffin embedded tissues of 33 benign and 24 malignant salivary gland tumors using monoclonal antibody for type IV collagen and polyclonal antibody for fibronectin. Results: 1) Well preserved linear basement membrane-like staining of type IV collagen was detected in duct-cell-derived benign salivary gland tumors. But pleomorphic adenoma exhibited a heterogeneous pattern as focal augmentation and interruption. 2) In malignant tumors, type IV collagen was distributed in an irregular, interrupted manner or completely absent. Adenoid cystic carcinomas displayed a marked staining of the basal membrane associated substances in the pseudocysts. 3) The staining pattern of fibronectin was similar to that of type IV collagen execpt more dense in the stroma. 4) Salivary gland tumors which have a prominent myoepithelial cell component revealed a particular deposition of basement membrane materials adjacent to the myoepithelial cells. Conclusion: The study of the basal membrane substances may be helpful for differential diagnosis of benign and malignant salivary gland tumors and identifying special features of salivary gland tumors such as pseudocystic pattern of adenoid cystic carcinoma. Also we think that the myoepithelial cells contribute to the formation of basement membrane materials.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.10a
• /
• pp.725-728
• /
• 2014

Continue to have an increasingly violent crimes against children every year, and as you know all seriousness is classified as a felony. However, efforts to reduce the underlying crime is low. Therefore, it is necessary to solve this problem, the security system. Is to protect the children and adults that exist that can pose a threat to children to identify and monitor tracking method in this paper. Was based on a Korean standard body size of a person, such as keys, arm length, leg length, head vertical length, head width proposed method. Also, separate the adults and children through the comparison of the reference value, the ratio and the ratio of the number of pixels of the detected object, the proposed method. Processing speed is fast because it detects only a specific object region in the entire image in the handling method in the proposed method the five nine minutes. The advantage is to enable comparison of the specific object, through which there is.

• Proceedings of the KIEE Conference
• /
• 2011.07a
• /
• pp.1934-1935
• /
• 2011

In order for a service robot to perform several tasks, basically autonomous navigation technique such as localization, mapping, and path planning is required. The localization (estimation robot's pose) is fundamental ability for service robot to navigate autonomously. In this paper, we propose a new system for point pattern matching based visual global localization using spot lightings in ceiling. The proposed algorithm us suitable for system that demands high accuracy and fast update rate such a guide robot in the exhibition. A single camera looking upward direction (called ceiling vision system) is mounted on the head of the mobile robot and image features such as lightings are detected and tracked through the image sequence. For detecting more spot lightings, we choose wide FOV lens, and inevitably there is serious image distortion. But by applying correction calculation only for the position of spot lightings not whole image pixels, we can decrease the processing time. And then using point pattern matching and least square estimation, finally we can get the precise position and orientation of the mobile robot. Experimental results demonstrate the accuracy and update rate of the proposed algorithm in real environments.

• Korean Journal of Applied Biomechanics
• /
• v.29 no.2
• /
• pp.71-77
• /
• 2019

Objective: The aim of this study was to investigate postural control strategies on smart phone use during gait in over 50-year-old adults. Method: 8 elderly subjects (age: $55.5{\pm}3.29yrs$, height: $159.75{\pm}4.20cm$, weight: $62.87{\pm}8.44kg$) and 10 young subjects (age: $23.8{\pm}3.19yrs$, height: $158.8{\pm}5.97cm$, weight: $53.6{\pm}5.6kg$) participated in the study. They walked at a comfortable pace in a gaitway of ~8 m while: 1) reading text on a smart phone, 2) typing text on a smart phone, or 3) walking without the use of a phone. Gait parameters and kinematic data were evaluated using a three-dimensional movement analysis system. Results: The participants read or wrote text messages they walked with: slower speed; lesser stride length and step width; greater flexion range of motion of the head; more flexion of the thorax in comparison with normal walking. Conclusion: Texting or reading message on a smart phone while walking may pose an additional risk to pedestrians' safety.