• Proceedings of the Korea Information Processing Society Conference
• /
• 2007.05a
• /
• pp.328-329
• /
• 2007

본 논문은 로봇과 같이 외부 음향잡음에 노출되어 있는 상황 하에서, 대면하고 있는 사람이 입술을 움직여 발성하는 경우에만 음성인식 기능이 수행되도록 하기 위한 방안의 일환으로, 입술움직임 영상을 보다 정확히 추적하기 위한 테스트 환경 구현에 관한 것이다. 음성구간 검출과정에서 입술움직임 영상 추적결과의 활용여부는 입술움직임을 얼마나 정확하게 추적할 수 있느냐에 달려있다. 이를 위해 영상 프레임율 동적 제어, 칼라/이진영상 변환, 순간 캡쳐, 녹화 및 재생기능을 구현함으로써, 다각적인 방향에서 입술움직임 영상 추적기능을 확인해 볼 수 있도록 하였다. 음성/영상기능을 연동시킨 결과 약 99.3%의 연동성공율을 보였다.

• Journal of Korean Society for Geospatial Information Science
• /
• v.12 no.4 s.31
• /
• pp.35-43
• /
• 2004

Multibeam Echosounder system is the latest technology of a hydrographic survey utilized in producing an electronic nautical chart, obtaining a DEM with high precision, making a moving image by Swath surveying a wide area. As a fundamental study for improving the precision of MBES, we compared and analyzed measurements of DGPS and Motion sensor, and studied for the dynamic characteristics of vessel's movements. DGPS was installed in front and in the rear and on both side or the vessel and surveyed. The receiving precision of surveyed GPS results was obtained to the satisfactory extent that was possible to valuate the accuracy of Motion sensor as 0.0016$^{\circ}$ of the roll value and 0.0009$^{\circ}$ of the pitch value. The relationship between the values of heading, pitch, and roll in Motion sensor and the data of DGPS was proportional correlation. In addition, it is considered that deviations by elements like rapid turning and vibration of the vessel will be occurred, although the correlation of each deviation according to each amount or change is proportional. It is suitable that GPS installs in the central line of the vessel that is less affected than other places by waving because the amount of change in the tide level obtained from GPS survey and the value of heave are similar with the values taken by Motion sensor, and the velocity of GPS is different from installed places. The accuracy of the final result from MBES could be affected by the values of gyro and Motion sensor inputted to MBES processor because there were intervals of 15s and 13s of receiving time in gyro and Motion sensor respectively compared with the real-time measurements of DGPS.

• Journal of the Institute of Convergence Signal Processing
• /
• v.11 no.4
• /
• pp.289-297
• /
• 2010

In this paper, A method to prevent the external acoustic noise from being misrecognized as the speech recognition object is presented in the speech activity detection process for the speech recognition. Also this paper confirmed besides the acoustic energy to the lip movement image signals. First of all, the successive images are obtained through the image camera for personal computer and the lip movement whether or not is discriminated. The next, the lip movement image signal data is stored in the shared memory and shares with the speech recognition process. In the mean time, the acoustic energy whether or not by the utterance of a speaker is verified by confirming data stored in the shared memory in the speech activity detection process which is the preprocess phase of the speech recognition. Finally, as a experimental result of linking the speech recognition processor and the image processor, it is confirmed to be normal progression to the output of the speech recognition result if face to the image camera and speak. On the other hand, it is confirmed not to the output the result of the speech recognition if does not face to the image camera and speak. Also, the initial feature values under off-line are replaced by them. Similarly, the initial template image captured while off-line is replaced with a template image captured under on-line, so the discrimination of the lip movement image tracking is raised. An image processing test bed was implemented to confirm the lip movement image tracking process visually and to analyze the related parameters on a real-time basis. As a result of linking the speech and image processing system, the interworking rate shows 99.3% in the various illumination environments.

• Journal of Korean Ophthalmic Optics Society
• /
• v.16 no.2
• /
• pp.123-133
• /
• 2011

Purpose: The present study was conducted to analyze any difference in the movement of aspheric RGP lens by the amounts of keratometiric astigmatisms using keratometer and corneal topography. Methods: Corneal curvatures in thirty six eyes of males and females of with-the-rule keratometric astigmatisms in their twenties were measured by a keratometer and worn aspheric RGP lenses. Then, lens rotations, vertical and horizontal movements of lens by blinking were measured to compare with lens movements when aspheric RGP lenses were fitted by total keratometric astigmatisms using corneal topography. Results: The case having higher amount of central keratometric astigmatism was 61.1% of subjects, however, 36.1% of subjects showed higher total keratometric astigmatism indicating that central keratometric astigmatism was not always bigger than total keratometric astigmatism. Since over 0.25 diopter difference between total and central keratometric astigmatisms was shown in 19 eyes (52.8% of subjects), the prescription for lens fitting could be changed. Significant difference in horizontal movement was detected with increase of astigmatism when it compared based on the amount of keratometric astigmatism measured by a keratometer. However, there was no significant difference in lens rotation, horizontal and vertical movements by comparison with the amount of total keratometric astigmatism using a corneal topography. When central keratometric astigmatism measured by keratometer was bigger than total keratometric astigmatism estimated by corneal topography, bigger lens rotation was shown compared with opposite case. Also, the tendency of bigger lens rotation was measured with the increase of keratomatric astigmatism in the case of same prescription having same base curves with same amount of keratometric astigmatism but different curvatures. Conclusions: From the present study, we concluded that lens movements on cornea were not totally different when aspheric RGP lens fitted on with-the-rule astigmatism by keratometer and corneal topography. However, there was some difference in certain lens movements. Therefore, we concluded that further study on the relationship between the prescriptions for lens fitting should be conducted for improving the rate of successful lens fitting by keratometer or for the proper application of corneal topography for lens fitting.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2003.10a
• /
• pp.741-744
• /
• 2003

in this paper, we propose a dynamic-based compression system by creating mosaic background and transmitting the change information. A dynamic mosaic of the background is progressively integrated in a single image using the camera motion information. For the camera motion estimation, we calculate perspective projection parameters for each frame sequentially with respect to its previous frame. The camera motion is robustly estimated on the background by discriminating between background and foreground regions. The modified block-based motion estimation is used to separate the background region.

• Journal of Ocean Engineering and Technology
• /
• v.9 no.1
• /
• pp.36-46
• /
• 1995

빙판파괴 형태는 여러 모드의 합성이며 실제로 한 가지 양식으로 파괴되는 경우는 거의 일어나지 않는다. 이제까지 빙하중 해석 이론이나 방법은 한 가지 양식에 기준하는 것이었다. 이 논문에서는 합성모드로 빙판이 파괴될 때 해양구조물에 작용하는 빙하중 추정방법을 소개하여 모형 실험결과치와 그 결과를 비교하였다. 두 가지 합성모드에 대한 빙하중 추정방법인 비례파괴해석법 (Proportional Failure Method)과 국부경계해석법(Local Ice boundary Method)을 본논문에 소개하였으며, 이 두가지 방법과 함께 널리 알려진 Crushing 해석방법을 적용하여 정적 및 동적 구조물에 작용하는 빙하중을 산출/비교하였다. 동적구조물은 쇄빙선을 이용하였고, 쇄빙선이 SPM 터미널에 monopod로 연결되어있는 형태를 선택하였다. 모형 실험은 Finland의 Wartsila 실험실에서 실시 하였고, 이 실험을 통하여 쇄빙선에 작용하는 빙력 및 시간별 쇄빙선의 동적 움직임을 측정하였다. 이 논문에서는 위에서 소개된 세가지 방법으로 계산된 빙하중과 실험측정결과를 비교하였고, 이론적으로 추정한 쇄빙선의 운동을 실혐결과치와 비교하였다. Crushing방법으로 산출한 빙하중은 실제치보다 상당히 높았고, 비례파괴해석법은 Crushing 방법보다 정확한 결과를 보여주었으며, 국부경계해석법은 상당히 모형실험측정치와 가까웠다. 물론 쇄빙선의 움직임도 빙하중에 따라 변화가 심했고, 국부 경계해석법을 적용했을 때 실제 쇄빙선의 동적움직임을 가장 가깝게 추정할 수 있었다.

• Journal of KIISE
• /
• v.42 no.7
• /
• pp.910-918
• /
• 2015

This paper presents a parameter visualization technique to overcome the limitation of the naked eye in contrast-enhanced ultrasonography. A method is also proposed to compensate for the distortion and noise in ultrasound image sequences. Meaningful parameters for diagnosing liver disease can be extracted from the dynamic patterns of the contrast enhancement in ultrasound images. The visualization technique can provide more accurate information by generating a parametric image from the dynamic data. Respiratory motions and noise from micro-bubble in ultrasound data may cause a degradation of the reliability of the diagnostic parameters. A multi-stage algorithm for respiratory motion tracking and an image enhancement technique based on the Markov Random Field are proposed. The usefulness of the proposed methods is empirically discussed through experiments by using a set of clinical data.

• 한국노년학
• /
• v.29 no.4
• /
• pp.1261-1275
• /
• 2009

Age related decrease of muscle strength, balance, and gait abilities bring about physical inactivity in the elderly. Virtual reality (VR) training has been used successfully to rehabilitate functional balance and mobility in elderly subjects. This study was aimed at determining the effect of VR-based exercise programs by using a video game on the muscle strength, balance, and gait abilities in the elderly. 48 old people were randomly divided into two groups; VR-group (men: 11, women: 14, age: 68.42yrs) and control group (men: 10, women: 13, age: 67.58yrs). VR-group performed an exercise program twice a week for 8 weeks and control group had no intervention. The VR-based exercise program was composed of warm up(10 mins), VR-program(40 mins), and cool down(10mins). It was performed by playstation eyetoy play that provided visual and auditory feedback as well as movements of the upper and lower extremities. Muscle strengths of the knee and ankle were measured using manual muscle tester. Static balance was estimated using computerized posturography. Dynamic balance was measured by Timed up and go test (TUG), Functional reach test (FRT). 10m walk test and 6-min walk test were used to assess gait abilities. After the completion of the VR-exercise program, muscle strength, balance, and gait abilities were improved significantly (p<0.05). In conclusion, the VR-based exercise program showed improvement on the muscle strength, balance, and gait ability in the elderly. This exercise program is both effective and interesting for this age group.

• Journal of the HCI Society of Korea
• /
• v.5 no.2
• /
• pp.15-24
• /
• 2010

A Digilog Book is an augmented reality (AR) based next generation publication supporting both sentimental analog emotions and digitized multi-sensory feedbacks by combining a conventional printed book and digital contents. As a Digilog Book authoring software, ARtalet provides an intuitive authoring environment through 3D user interface in AR environment. In this paper, we suggest ARtalet authoring environment based trajectory editing method to generate and manipulate a movement path of an augmented 3D object on the Digilog Book. Specifically, the translation points of the 3D manipulation prop is examined to determine that the point is a proper control point of a trajectory. Then the interpolation using splines is conducted to reconstruct the trajectory with smoothed form. The dynamic score based selection method is also exploited to effectively select small and dense control points of the trajectory. In an experimental evaluation our method took the same time and generated a similar amount of errors as the usual approach, but reduced the number of control points needed by over 90%. The reduced number of control points can properly reconstruct a movement path and drastically decrease the number of control point selections required for movement path modification. For control manipulation, the task completion time was reduced and there was less hand movement needed than with conventional method. Our method can be applicable to drawing or curve editing method in immersive In-Situ AR based education, game, design, animation, simulation application domains.

• Progress in Medical Physics
• /
• v.23 no.3
• /
• pp.138-144
• /
• 2012

Dose distribution throughout the clinical organ range of motion was analyzed using a respiratory-motion simulator that was equipped with a polymer gel dosimeter and EBT2 film. The normoxic polymer gel dosimeter was synthesized from gelatin, MAA, HQ, THPC and HPLC. The gel dosimeter and EBT2 film were irradiated with Co-60 gamma rays that were moved along the x-axis and y-axis in ${\pm}1.5cm$ steps at five-second intervals. The field size was $5{\times}5cm^2$. The SSD was 80 cm and set to 10 Gy at a depth of 2 cm. The PDD at a depth of 50 mm was 75.2% in the ion chamber, 82.3% in the static state and 86.1% in the dynamic state in the gel dosimeter. The penumbra for the dynamic state target, which was measured using the gel dosimeter, averaged 10.89 mm, this is a 40.5% increase over the penumbra of the static state target of 7.74 mm. In addition, when measuring with gel dosimetry, the value for the penumbra is 36.6% smaller in the static state and 29.4% smaller in the dynamic state compared to measuring with film. The aim of this study was to investigate the dosimetric properties of a normoxic polymethacrylic acid gel dosimeter in static and dynamic states and to evaluate the potentiality as a relative dosimeter for dynamic therapeutic radiation.