• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.6
• /
• pp.1-8
• /
• 2005

In this paper, we propose a two-stage head tracking algorithm adequate for real-time active camera system having pan-tilt-zoom functions. In the color convergence stage, we first assume that the shape of a head is an ellipse and its model color histogram is acquired in advance. Then, the min-shift method is applied to roughly estimate a target position by examining the histogram similarity of the model and a candidate ellipse. To reflect the temporal change of object color and enhance the reliability of mean-shift based tracking, the target histogram obtained in the previous frame is considered to update the model histogram. In the updating process, to alleviate error-accumulation due to outliers in the target ellipse of the previous frame, the target histogram in the previous frame is obtained within an ellipse adaptively shrunken on the basis of the model histogram. In addition, to enhance tracking reliability further, we set the initial position closer to the true position by compensating the global motion, which is rapidly estimated on the basis of two 1-D projection datasets. In the subsequent stage, we refine the position and size of the ellipse obtained in the first stage by using shape information. Here, we define a robust shape-similarity function based on the gradient direction. Extensive experimental results proved that the proposed algorithm performs head hacking well, even when a person moves fast, the head size changes drastically, or the background has many clusters and distracting colors. Also, the propose algorithm can perform tracking with the processing speed of about 30 fps on a standard PC.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.168.1-168
• /
• 2001

This article describes a novel model-based compensating neural network (NN) model developed to be used in our active binocular head controller, which addresses both the kinematics and dynamics aspects in trying to precisely track a moving object of interest to keep it in view. The compensating NN model is constructed using two classes of self-tuning neural models: namely Neural Gas (NG) algorithm and SoftMax function networks. The resultant servo controller is shown to be able to handle the tracking problem with a minimum knowledge of the dynamic aspects of the system.

• Korean Journal of Otorhinolaryngology-Head and Neck Surgery
• /
• v.61 no.12
• /
• pp.637-643
• /
• 2018

Radioimmunotherapy (RIT) is a therapy that takes advantage of the "cross-fire" effect of emitted radiation by radionuclides conjugated to tumor-directed monoclonal antibodies (mAb) (including those fragments) or peptides. While RIT has been successfully employed for the treatment of lymphoma, mostly with radiolabeled antibodies against CD20 [$^{90}yttrium$ ($^{90}Y$)-ibritumomab tiuxetan; $Zevalin^{(R)}$ and $^{131}iodine$ ($^{131}I)-tositumomab$; $Bexxar^{(R)}$], its use in solid tumors is more challenging, so far. Immuno-PET, a tool for tracking and quantification of mAbs with PET in vivo, is an exciting novel option to improve diagnostic imaging and guide mAb-based therapy. RIT in solid tumors including head and neck cancer may be an alternative treatment with advances in various biological, chemical, and treatment procedures, and it may help to reduce unnecessary exposure and enhance the therapeutic efficacy. Also, immuno-PET based on RIT might play an important role in cancer staging, in patients or targets selection of targeted therapeutics and in monitoring the response of targeted therapeutics as precision medicine. In this review, fundamentals of RIT/immune-PET and current knowledge of the preclinical/clinical trials in RIT for solid tumor including head and neck cancer are reviewed.

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.1107-1108
• /
• 2008

The purpose of this study is to develope a computer mouse using the head movements and eye blink in order to help the disability persons who can't move the hands or foot because of car accident or cerebral apoplexy. The mouse is composed of two gyro-sensors and photo sensor. The gryo-sensors detect the head horizontal and vertical angular velocities, respectively. The photo sensor detect the eye blink to perform click, double click, and to reset the head position. In the results, we could control the mouse points in real time using the proposed system.

• Transactions of the Society of Information Storage Systems
• /
• v.1 no.1
• /
• pp.67-72
• /
• 2005

This study proposes a design methodology to determine the optimum configurations of the optical flying head (OFH) for near-field recording systems. Since the OFH requires stricter static and dynamic characteristics of slider air-bearings within an optical tilt tolerance over the entire recording band, an optimum design to keep the focusing and tracking ability stable is essential. The desired flying characteristics considered in this study are to minimize the variation in flying height between the SIL and the disk from a target value, satisfying the restriction of the minimum flying height, to keep the pitch and roll angles within an optical tilt tolerance, and to ensure a higher air-bearing stiffness. Simulation results demonstrate the effectiveness of the proposed design methodology by showing that the static and dynamic flying characteristics of the optimally designed OFH are enhanced in comparison with those of the initial. The gap between the SIL and the disk can be kept at less than 100 nm even if the optical tilt tolerance of the SIL is considered.

• Journal of the Korea Computer Graphics Society
• /
• v.24 no.3
• /
• pp.49-59
• /
• 2018

Simulator sickness is one of the important side effect of virtual reality. Simulator sickness is influenced by various factors, and field of view (FOV) is one of them. The FOV is a viewing angle limited by the screen, and when the FOV is reduced, the simulator sickness is reduced, and the presence is lowered. Previous study developed a Dynamic FOV Restrictor (Center-fixed FOV Restrictor) to reduce simulator sickness while maintaining presence. It is a method that limits the FOV dynamically by reflecting the speed and angular velocity of the avatar. We also developed Eye-tracking Based Dynamic FOV Restrictor (Eye-tracking FOV Restrictor) by adding head rotations and eye movements. This study attempts to compare the simulator sickness and the presence of the No FOV Restrictor condition, the Center-fixed FOV Restrictor condition, and the Eye-tracking FOV Restrictor condition. The results showed that the simulator sickness of the Center-fixed FOV Restrictor condition is significantly lower than other two conditions. The results also showed that there were no significant differences in presence in three conditions. The interpretations and limitations of this study are discussed in this paper.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.5
• /
• pp.1162-1170
• /
• 2014

In this paper, an accurate remote gaze tracking method with two cameras is presented using a modified Starburst algorithm and honography normalization. Starburst algorithm, which was originally developed for head-mounted systems, often fails in detecting accurate pupil centers in remote tracking systems with a larger field of view due to lots of noises. A region of interest area for pupil is found using template matching, and then only within this area Starburst algorithm is applied to yield pupil boundary candidate points. These are used in improved RANSAC ellipse fitting to produce the pupil center. For gaze estimation robust to head movement, an improved homography normalization using four LEDs and calibration based on high order polynomials is proposed. Finally, it is shown that accuracy and robustness of the system is improved using two cameras rather than one camera.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.1
• /
• pp.31-37
• /
• 2011

Recently gantry-type robot with 3 axes rectangular coordinates have been studied in the many industrial production equipment and machinery fields. To acquire a good handling and motion performance of this robot, reducing the settling-time and securing the accurate-transfer positioning under high-speed conditions should be required. However when robot is moved in high-speed, the large inertia of robot can lead to serious vibration of robot's head. The time-delayed control characteristics of this robot can also lead to tracking error. In this research, the analysis of the effects of higher order positional-profile is carried out to assure high-speed performance and stiffness specifications. To remove the residual vibration caused by kinematic coupling effect of dual-servo gantry, we develop a dual-servo gantry of rotary type that moving frame of x-axis rotates about z-axis. In order to decrease the tracking error, the 3 type lead-filter through system identification was applied respectively. From the experimental results, it was shown that zero-order series leader-filter has the best performance about tracking error and settling time.

• Journal of KIISE
• /
• v.43 no.6
• /
• pp.645-652
• /
• 2016

Joint Attention (JA) has been known to play a key role in human social learning. However, relative impact of different interaction types has yet to be rigorously examined because of limitation of existing methodologies to simulate human-to-human interaction. In the present study, we designed a new JA paradigm with emulating human-avatar interaction and virtual reality technologies, and tested the paradigm in two experiments with healthy adults. Our results indicated that initiating JA (IJA) condition was more effective than responding JA (RJA) condition for social learning in both head and hand interactions. Moreover, the hand interaction involved better information processing than the head interaction. The implication of the results, the validity of the new paradigm, and limitations of this study were discussed.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.3
• /
• pp.147-156
• /
• 2024

This paper introduces the design of a turtle neck posture correction and prevention system for users of digital devices for a long time. The number of forward head posture patients in Korea increased by 13% from 2018 to 2021, and has not yet improved according to the latest statistics at the present time. Because of the nature of the disease, prevention is more important than treatment. Therefore, in this paper, we designed a system based on built-camera in most laptops to increase the accessiblility of the system, and utilize the features such as Pose Estimation, Face Landmarks Detection, Iris Tracking, and Depth Estimation of Google Mediapipe to prevent the need to produce artificial intelligence models and allow users to easily prevent forward head posture.