• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.3
• /
• pp.117-122
• /
• 2023

Gaze estimation, which automatically recognizes where a user is currently staring, and object detection based on estimated gaze point, can be a more accurate and efficient way to understand human visual behavior. in this paper, we propose a method to detect the objects within the region of interest around the gaze point. Specifically, after estimating the 3D gaze point, a region of interest based on the estimated gaze point is created to ensure that object detection occurs only within the region of interest. In our experiments, we compared the performance of general object detection, and the proposed object detection based on region of interest, and found that the processing time per frame was 1.4ms and 1.1ms, respectively, indicating that the proposed method was faster in terms of processing speed.

• 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.

• Korean Journal of Applied Biomechanics
• /
• v.27 no.1
• /
• pp.35-43
• /
• 2017

Objective: The purpose of this study was to determine how gaze angle affects muscle activity and kinematic variables during treadmill walking and to offer scientific information for effective and safe treadmill training environment. Method: Ten male subjects who have no musculoskeletal disorder were recruited. Eight pairs of surface electrodes were attached to the right side of the body to monitor the upper trapezius (UT), rectus abdominis (RA), erector spinae (ES), rectus femoris (RF), bicep femoris (BF), tibialis anterior (TA), medialis gastrocnemius (MG), and lateral gastrocnemius (LG). Two digital camcorders were used to obtain 3-D kinematics of the lower extremity. Each subject walked on a treadmill with a TV monitor at three different heights (eye level; EL, 20% above eye level; AE, 20% below eye level; BE) at speed of 5.0 km/h. For each trial being analyzed, five critical instants and four phases were identified from the video recording. For each dependent variable, one-way ANOVA with repeated measures was used to determine whether there were significant differences among three different conditions (p<.05). When a significant difference was found, post hoc analyses were performed using the contrast procedure. Results: This study found that average and peak IEMG values for EL were generally smaller than the corresponding values for AE and BE but the differences were not statically significant. There were also no significant changes in kinematic variables among three different gaze angles. Conclusion: Based on the results of this study, gaze angle does not affect muscle activity and kinematic variables during treadmill walking. However, it is interesting to note that walking with BE may increase the muscle activity of the trapezius and the lower extremity. Moreover, it may hinder proper dorsiflexion during landing phase. Thus, it seems to reasonable to suggest that inappropriate gaze angle should be avoided in treadmill walking. It is obvious that increased walking speed may cause a significant changes in biomechanical parameters used in this study. It is recommended that future studies be conducted which are similar to the present investigation but using different walking speed.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.6A
• /
• pp.497-502
• /
• 2012

In this paper, we present an immersive videoconferencing system that enables gaze correction between users in the internet protocol TV (IPTV) environment. The proposed system synthesizes the gaze corrected images using the depth estimation and the virtual view synthesis algorithms as one of the most important techniques of 3D video system. The conventional processes, however, causes several problems, especially temporal inconsistency of a depth video. This problem leads to flickering artifacts discomforting viewers. Therefore, in order to reduce the temporal inconsistency problem, we exploit the joint bilateral filter which is extended to the temporal domain. In addition, we apply an outlier reduction operation in the temporal domain. From experimental results, we have verified that the proposed system is sufficient to generate the natural gaze-corrected image and realize immersive videoconferencing.

• Journal of KIISE:Software and Applications
• /
• v.30 no.12
• /
• pp.1228-1238
• /
• 2003

This paper presents a new and practical method based on computer vision for detecting the monitor position where the user is looking. In general, the user tends to move both his face and eyes in order to gaze at certain monitor position. Previous researches use only one wide view camera, which can capture a whole user's face. In such a case, the image resolution is too low and the fine movements of user's eye cannot be exactly detected. So, we implement the gaze detection system with dual camera systems(a wide and a narrow view camera). In order to locate the user's eye position accurately, the narrow view camera has the functionalities of auto focusing and auto panning/tilting based on the detected 3D facial feature positions from the wide view camera. In addition, we use dual R-LED illuminators in order to detect facial features and especially eye features. As experimental results, we can implement the real-time gaze detection system and the gaze position accuracy between the computed positions and the real ones is about 3.44 cm of RMS error.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.52-55
• /
• 2009

With the recent development of virtual reality, it has been actively investigated to develop user interfaces for immersive interaction. Immersive user interfaces improve the efficiency and the capability of information processing in the virtual environment providing various services, and provide effective interaction in the field of ubiquitous and mobile computing. In this paper, we propose an virtual reality platform "My Workspace" which renders an 3D virtual workspace by using an immersive user interface. We develop an interface that integrates an optical see-through head-mounted display, a Wii remote controller, and a helmet with infrared LEDs. It estimates the user's gaze direction in terms of horizontal and vertical angles based on the model of head movements. My Workspace expands the current 2D workspace based on monitors into the layered 3D workspace, and renders a part of 3D virtual workspace corresponding to the gaze direction. The user can arrange various tasks on the virtual workspace and switch each task by moving his head. In this paper, we will also verify the performance of the immersive user interface as well as its usefulness with the usability test.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.7
• /
• pp.93-99
• /
• 2015

In this paper, we propose a gaze correction method for realistic video teleconferencing. Typically, cameras used in teleconferencing are installed at the side of the display monitor, but not in the center of the monitor. This system makes it too difficult for users to contact each eyes. Therefore, eys contact is the most important in the immersive videoconferencing. In the proposed method, we use the stereo camera and the depth camera to correct the eye contact. The depth camera is the kinect camera, which is the relatively cheap price, and estimate the depth information efficiently. However, the kinect camera has some inherent disadvantages. Therefore, we fuse the kinect camera with stereo camera to compensate the disadvantages of the kinect camera. Consecutively, for the gaze-corrected image, view synthesis is performed by 3D warping according to the depth information. Experimental results verify that the proposed system is effective in generating natural gaze-corrected images.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.257-259
• /
• 1996

This paper presents the active eye system for tracking a moving object in 3D space. A prototype system able to track a moving object is designed and implemented. The mechanical system ables the control of platform that consists of binocular camera and also the control of the vergence angle of each camera by step motor. Each camera has two degrees of freedom. The image features of the object are extracted from complicated environment by using zero disparity filtering(ZDF). From the cnetroid of the image features the gaze point on object is calculated and the vergence angle of each camera is controlled by step motor. The Proposed method is implemented on the prototype with robust and fast calculation time.

• Proceedings of the IEEK Conference
• /
• 1998.10a
• /
• pp.883-886
• /
• 1998

In order to detect the user's gaze position on a monitor by computer vision, the accurate estimations of 3D positions and 3D motion of facial features are required. In this paper, we apply a EKF(Extended Kalman Filter) to estimate 3D motion estimates and assumes that its motion is "smooth" in the sense of being represented as constant velocity translational and rotational model. Rotational motion is defined about the orgin of an face-centered coordinate system, while translational motion is defined about that of a camera centered coordinate system. For the experiments, we use the 3D facial motion data generated by computer simulation. Experiment results show that the simulation data andthe estimation results of EKF are similar.e similar.

• Journal of Broadcast Engineering
• /
• v.11 no.1 s.30
• /
• pp.80-90
• /
• 2006

A simple 2D gaze tracking method using single camera and Purkinje image is proposed. This method employs single camera with infrared filter to capture one eye and two infrared light sources to make reflection points for estimating corresponding gaze point on the screen from user's eyes. Single camera, infrared light sources and user's head can be slightly moved. Thus, it renders simple and flexible system without using any inconvenient fixed equipments or assuming fixed head. The system also includes a simple and accurate personal calibration procedure. Before using the system, each user only has to stare at two target points for a few seconds so that the system can initiate user's individual factors of estimating algorithm. The proposed system has been developed to work in real-time providing over 10 frames per second with XGA $(1024{\times}768)$ resolution. The test results of nine objects of three subjects show that the system is achieving an average estimation error less than I degree.