• Journal of the Korea Society of Computer and Information
• /
• v.25 no.5
• /
• pp.1-9
• /
• 2020

In this paper, we propose a model that performs more natural facial attribute editing by utilizing mask information in the hair and hat region. STGAN, one of state-of-the-art research of facial attribute editing, has shown results of naturally editing multiple facial attributes. However, editing hair-related attributes can produce unnatural results. The key idea of the proposed method is to additionally utilize information on the face regions that was lacking in the existing model. To do this, we apply three ideas. First, hair information is supplemented by adding hair ratio attributes through masks. Second, unnecessary changes in the image are suppressed by adding cycle consistency loss. Third, a hat segmentation network is added to prevent hat region distortion. Through qualitative evaluation, the effectiveness of the proposed method is evaluated and analyzed. The method proposed in the experimental results generated hair and face regions more naturally and successfully prevented the distortion of the hat region.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.6
• /
• pp.731-736
• /
• 2008

In this paper, we propose the movement detection algorithm by using virtual skeleton model. To do this, first, we eliminate error values by using conventioanl method based on RGB color model and eliminate unnecessary values by using the HSI color model. Second, we construct the virtual skeleton model with skeleton information of 10 peoples. After matching this virtual model to original image, we extract the real head silhouette by using the proposed circle searching method. Third, we extract the object by using the mean-shift algorithm and this head information. Finally, we validate the applicability of the proposed method through the various experiments in a complex environments.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.20 no.4
• /
• pp.144-152
• /
• 2016

This paper focuses on the experimental study for investigating the performance for lap splice of hooked or headed reinforcement in beam with different depths. In the experiment, seven specimens, with its variables as the lap length of headed or hooked bar, the existence of stirrups, etc., was manufactured. Bending test was conducted. Lap strengths by test were compared with the theoretical model based on KCI2012. The result showed that the cracks at failure mode occurred along the axial direction to a headed bar. The initial stiffness and the stiffness after initial crack were similar for all specimens. For HS series specimens without stirrups, a 25% increase in lap length was increased 11.8~18.1% maximum strengths. For HH series specimens without stirrups, a increase in lap length did not affect the maximum strengths because of the pryout failure of headed bar. For HS series specimens, the theoretical lap strengths based on KCI2012 considering the B grade lap and the reduction factor for stirrup were evaluated. They are smaller than the test strengths and can ensure the safety in terms of strength capacity. For HH series specimens, the stirrups in the lap zone are needed to prevent the pryout behaviour of headed bar.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2002.05a
• /
• pp.234-239
• /
• 2002

한국인 인체모델은 동적 환경에서 정면 및 측면 충돌에 대한 지체의 가속도를 얻을 수 있도록 개발되었다. 우선 GEBOD에 입력하기 위한 32개의 한국인 인체치수를 선별하고, 15개의 지체를 가진 한국인 인체모델을 구성한다. 손 동작의 감성평가에 이용하기 위해 손을 독립된 지체로 분리한 17개 지체의 인체모델을 완성한다. MADYMO를 통한 정면충돌 테스트에서는 Hybrid III에 비해 한국인의 머리와 흉부 가속도가 비교적 높게 나왔고, 측면충돌 테스트에서 흉추 1번의 가속도는 ISO에서 요구하는 범위의 상한값을 조금 벗어나는 결과를 얻었다.

• Journal of Auto-vehicle Safety Association
• /
• v.14 no.1
• /
• pp.62-67
• /
• 2022

This study is to construct the simple estimating model for the HIC15 of the driver dummy using the frontal impact test results. Test results of 9 vehicles of Hyundai Sonata from the MY2002~MY2020 USNCAP are utilized for constructing the linear regression model. The average accelerations extracted from the vehicle crash pulses are handled as the main factors. The average accelerations of 10 ms interval within 0~100 ms are calculated from the crash pulse data of 9 vehicles. The present estimating model of the HIC15 using the average accelerations of 10 ms interval in the 0~80 ms range shows good agreement with the tested value within 2.4% maximum error.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.18 no.5
• /
• pp.187-195
• /
• 2018

In this study, using real-time gaze tracking and head tracking method, we intended to quantitatively evaluate the deviation between the patient's head and gaze direction while minimizing inspection errors due to apraxia of conventional paper-based examination respectively. As a result, we developed a software that can quantitatively measure gaze and head movement information, and computerized the line bisection and star cancelation test, which are generally used as conventional paper test. In addition, for the rehabilitation training, contents corresponding to the visual technology of Warren's visual hierarchical model lower level are implemented and can be performed repetitively and independently. This allows the patient to actively participate in rehabilitation and quantitatively compare the degree of improvement.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.5
• /
• pp.1-8
• /
• 2010

In this paper, a sound externalization method is proposed for out-of-the-head localization in a headphone listening environment. In order to reduce timbre distortion by the conventional methods using a measured a head-related transfer function (HRTF) or early reflections, the proposed method integrates a model-based HRTF with reverberation. In addition, for improving frontal externalization performance, techniques such as decorrelation and spectral notch filtering are included. To evaluate the performance of the proposed externalization method, subjective listening tests are conducted by using different types of sound sources such as white noise, sound effects, speech, and music. It is shown from the test results that the proposed externalization method can localize sound sources farther away from out of the head than the conventional method.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.20 no.2
• /
• pp.64-69
• /
• 2012

Head injury is one of the most common cause of deaths in car-to-pedestrian collisions. To reduce the severity of such injuries, many international safety committees have performed headform impact test for pedestrian protection. In this paper, an adult headform impactor model is developed based on the finite element (FE) method and validated through the numerical simulation. The skin material of headform impactor is known as polyvinyl chloride skin (PVC) and its material was assumed as viscoelastic. The viscoelastic parameters of headform skin are identified by a series of trial and error methods. The new developed FE adult headform impactor is verified by the drop test and FE JARI adult headform impactor provided by Madymo program.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.15 no.1
• /
• pp.106-115
• /
• 2007

In this study, first, child headform model was built up, satisfying requirement in the headform validation test. Also, for decreasing both acceleration peak and deformation, a new hood with dome shaped forming in inner panel was investigated. Next, headform impact, complying with draft of EEVC W/G 17, on the central portion of the newly proposed hood were simulated for a steel hood and three aluminum hoods with different thickness for examining the material and thickness effect on HIC value and inner panel deformation. The analysis results explained that aluminum hoods with dome shaped forming in inner panel were highly promising not only for meeting headform safety regulations but also for leading to weight savings. Finally, hood edge design technology in order to reduce pedestrian injury due to the high stiffness of beam type edge and the rigid support, was discussed. Various types of the foam filled edge were designed and their headform safety performance were evaluated. The edge structure with foam filled in upper one third of section exhibited excellent results.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2004.04a
• /
• pp.61-67
• /
• 2004

This paper describes Three-Dimensional Listening Simulation System (3D-LSS) which is to analyze whistle sound related marine casualties, and is to evaluate the accident situations using 3D sound by Head Related Transfer Function. At first, the three-dimensional listening model from the analysis of accident situations is proposed, and then the reproduction and evaluation methods of 3D sounds are also discussed. The system is designed to explain the accident situations and to simulate the possible situations with GUI based graphics and 3D sound reproduction. The evaluation experiments using 3D-LSS are carried out with six cases that did not known whether it is true or not the blast and listening of the whistle sound between two vessels. As results of psychological assessments by five subjects, the six cases can be analyzed clearly by visual images and audio sounds, thus the usability of 3D-LSS as one of the judgment assistant system of marine casualty is verified.