• Journal of the Korean Society for Precision Engineering
• /
• v.11 no.1
• /
• pp.80-88
• /
• 1994

In the automation of rigid parts mating process with the intelligent robots, Peg-In-Hole is the most available task since inserting is some analytic and needs suitable range of forces that can be controlled by induatrial manipulators. In this Peg-In-Hole process, it is very important to identify the contact state between tow parts, peg and hole, to build the strategies for robot motion that leads to avoid the jamming condition occurs during insertion process. In this paper, we adpopted 3 parameters for identification, lFzl, lFxy/Fzl, and lMxy/Fxyl, derived from axes value of Whitney's jamming diagram. Also, we defined the fuzzy membership functions for these parameters and developed the identification algorithm based on fuzzy inference method of max-product. As an experimental result, we obtained about 96% of identification ratio that could be raised up to industrial requirements by further research.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.01a
• /
• pp.77-82
• /
• 2022

GUI(Graphical User Interface)를 대신하는 차세대 인터페이스로서 NUI(Natural User Interace)에 기대가 모이는 것은 자연스러운 흐름이다. 본 연구는 NUI의 손가락 관절을 포함한 손동작 전체를 인식시키기 위해 웹캠과 카메라를 활용하여 다양한 배경과 각도의 손동작 데이터를 수집한다. 수집된 데이터는 전처리를 거쳐 데이터셋을 구축하며, ResNet50 모델을 활용하여 전이학습한 합성곱 신경망(Convolutional Neural Network) 알고리즘 분류기를 설계한다. 구축한 데이터셋을 입력시켜 분류학습 및 예측을 진행하며, 실시간 영상에서 인식되는 손동작을 설계한 모델에 입력시켜 나온 결과를 통해 가위바위보 게임을 구현한다.

• Progress in Medical Physics
• /
• v.17 no.3
• /
• pp.136-143
• /
• 2006

The respiratory gating radiation therapy which Irradiates only in the stable respiratory period with analyzing the periodic motion of a reflective marker on the patient's abdomen has been applied to the precise radiation treatment in order to minimize the effect of organ motion induced by the respiration. This respiratory gating system establishes irradiation region using the amplitude-based or phase-based method. Although phase-based method Is preferred because of the stability in the real treatment conditions, it has some limits to explain the exact correlation between the marker motion and organ motion. Even when the variation of amplitude which can introduce target motion considered as an error is produced, the phase-based method has the possibility to irradiate including the error positions. In this study, the error analysis program was developed for the verification of the tumor position's variation correlated with the variation of marker's amplitude which can be occurred during a phase-based respiratory sating treatment. The analysis program was tested with a virtual treatment record file and with a record file using moving phantom which were modified considering the irregular amplitude's variation simulating the real clinical situations. In both cases, accurate discrimination of error points and error calculation were produced. When the treatment record files of a real patient were analyzed with the program, the accurate recognition and calculation of the error points were also verified. The analysis program developed in this study will be applied as a useful tool for the analysis of errors due to the irregular variation of patients' respiration during the phase-base respiratory gating radiation treatment.

• 재활복지
• /
• v.22 no.3
• /
• pp.225-257
• /
• 2018

The purpose of this study is to find the application point of hearing augmentation technology development through examining the risk context experience of people with hearing impairment and the use of assistive device used as an alternative technology. Data of 355 people with hearing impairment with official disability grading was analyzed. The results of this study are first, research participants had no experience of recognizing any sound or vibration in situations highest in the order of means of transportation, material, and nature. Especially the ratio of being unable to recognize the sound and vibration of means of transportation was high, which implies the high possibility of people with hearing impairment experiencing risk. Secondly, the risk context that people with hearing impairment will most likely to experience are highest in the order of traffic accident, pedestrian accident, and daily life at home. Thirdly, the recognition of 2G phone/smart phone, vibrating digital alarm clock, light bar, vibrating wrist watch as assistive device for risk context awareness and notification was high and the satisfaction level of 2G phone/smart phone was the highest. Fourthly, the research participants had high recognition of assistive device for communication in the order of hearing aid, smart phone, videophone, cochlear implant and 2G phone and it was found that the satisfaction level and communication improvement level was the highest using the smart phone. Lastly, for the development of hearing augmentation technology the research participants recognized the importance of portable/wear convenience, price, and motion accuracy and for notification delivery means they preferred the method of using sight(text and light). Based on the results of this study policy and practical plans for hearing augmentation technology development for people with hearing impairment in risk context are proposed.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.10
• /
• pp.461-470
• /
• 2023

While speech animation generation employing deep learning has been actively researched for English, there has been no prior work for Korean. Given the fact, this paper for the very first time employs supervised deep learning to generate Korean speech animation. By doing so, we find out the significant effect of deep learning being able to make speech animation research come down to speech recognition research which is the predominating technique. Also, we study the way to make best use of the effect for Korean speech animation generation. The effect can contribute to efficiently and efficaciously revitalizing the recently inactive Korean speech animation research, by clarifying the top priority research target. This paper performs this process: (i) it chooses blendshape animation technique, (ii) implements the deep-learning model in the master-servant pipeline of the automatic speech recognition (ASR) module and the facial action coding (FAC) module, (iii) makes Korean speech facial motion capture dataset, (iv) prepares two comparison deep learning models (one model adopts the English ASR module, the other model adopts the Korean ASR module, however both models adopt the same basic structure for their FAC modules), and (v) train the FAC modules of both models dependently on their ASR modules. The user study demonstrates that the model which adopts the Korean ASR module and dependently trains its FAC module (getting 4.2/5.0 points) generates decisively much more natural Korean speech animations than the model which adopts the English ASR module and dependently trains its FAC module (getting 2.7/5.0 points). The result confirms the aforementioned effect showing that the quality of the Korean speech animation comes down to the accuracy of Korean ASR.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.3
• /
• pp.11-22
• /
• 2010

This paper is a study on implementation of intelligent image surveillance system using context information and supplements temporal-spatial constraint, the weak point in which it is hard to process it in real time. In this paper, we propose scene analysis algorithm which can be processed in real time in various environments at low resolution video(320*240) comprised of 30 frames per second. The proposed algorithm gets rid of background and meaningless frame among continuous frames. And, this paper uses wavelet transform and edge histogram to detect shot boundary. Next, representative key-frame in shot boundary is selected by key-frame selection parameter and edge histogram, mathematical morphology are used to detect only motion region. We define each four basic contexts in accordance with angles of feature points by applying vertical and horizontal ratio for the motion region of detected object. These are standing, laying, seating and walking. Finally, we carry out scene analysis by defining simple context model composed with general context and emergency context through estimating each context's connection status and configure a system in order to check real time processing possibility. The proposed system shows the performance of 92.5% in terms of recognition rate for a video of low resolution and processing speed is 0.74 second in average per frame, so that we can check real time processing is possible.

• The Journal of the Korea Contents Association
• /
• v.14 no.11
• /
• pp.519-532
• /
• 2014

The emerging technologies for the natural computer interaction can give manufacturers new opportunities of product innovation. This paper is the study on a method of human communication about a finger gestures interaction. As technological advance has been so rapid over the last few decades, the utilizing products or services will be soon popular. The purpose of this experiment are as follows; What is the usefulness of gesture interaction? What is the cognitive impact on gesture interaction users. The finger gestures interaction consist of poking, picking and grasping. By measuring each usability in 2D and 3D space, this study shows the effect of finger gestures interaction. The 2D and 3D experimental tool is developed by using LeapMotion technology. As a results, the experiments involved 48 subjects shows that there is no difference in usability between the gestures in 2D space but in 3D space, the meaningful difference has been found. In addition, all gestures express good usability in 2D space rather than 3D space. Especially, there are the attractive interest that using uni-finger is better than multi-fingers.

• Science of Emotion and Sensibility
• /
• v.14 no.4
• /
• pp.627-636
• /
• 2011

The purpose of this study is to develop the multi-modal interaction system. This system provides realistic and an immersive experience through multi-modal interaction. The system recognizes user behavior, intention, and attention, which overcomes the limitations of uni-modal interaction. The multi-modal interaction system is based upon gesture interaction methods, intuitive gesture interaction and attention evaluation technology. The gesture interaction methods were based on the sensors that were selected to analyze the accuracy of the 3-D gesture recognition technology using meta-analysis. The elements of intuitive gesture interaction were reflected through the results of experiments. The attention evaluation technology was developed by the physiological signal analysis. This system is divided into 3 modules; a motion cognitive system, an eye gaze detecting system, and a bio-reaction sensing system. The first module is the motion cognitive system which uses the accelerator sensor and flexible sensors to recognize hand and finger movements of the user. The second module is an eye gaze detecting system that detects pupil movements and reactions. The final module consists of a bio-reaction sensing system or attention evaluating system which tracks cardiovascular and skin temperature reactions. This study will be used for the development of realistic digital entertainment technology.

• The Journal of the Korea Contents Association
• /
• v.12 no.1
• /
• pp.91-102
• /
• 2012

Generally today's culture and the arts industry has been focusing more on economic value than the arts. Therefore this paper will elucidate the meaning of the culture and the arts can be a break though which can only include commercial and economic values but transcend its values ultimately. First of all, this paper will suggest an advanced 3D stereoscopic images by analysis of examples and environments of realistic media arts. Looking into the changes of related technologies and market environments, the motion-recognition technology, as seem in SF film "Minority report", has become a feasible technology. In the past, 3D stereoscopic images were shown in the theme park theatre and exhibition halls for group viewing. but recent 3D TV and display devices have changed those environments to personal. Since domestic researches of realistic media art has been little, this paper will analyze them respecting to three broad classifications. The results are : Firstly, in CAVE method, more impact capabilities of spectators are expected that they can manipulate interactive interfaces freely and the physical movements of spectators can operate interactively. Secondly, inter-network communications and expansion of viewers' perceptions are predicted by way of HMD method, sensor suites and communication equipments. Thirdly, combinations of HMD and motion tracking utilization is foreseen. With the convergent usages of these three features, we can prospect the possibilities of interactive 4D that spectators wearing 3D stereoscopic display devices can experience and make their own 3D stereoscopic images actively at the point of their views.

• Journal of radiological science and technology
• /
• v.39 no.4
• /
• pp.601-606
• /
• 2016

Because of non-coplanar therapy with couch rotation in respiratory gated radiation therapy, the recognition of marker movement due to the change in the distance between the infrared camera and the marker due to the rotation of the couch is called RPM (Real-time The purpose of this paper is to evaluate the accuracy of motion reflections (baseline changes) of 2D gating configuration (two dot marker block) and 3D gating configuration (six dot marker block). The motion was measured by varying the couch angle in the clockwise and counterclockwise directions by $10^{\circ}$ in the 2D gating configuration. In the 3D gating configuration, the couch angle was changed by $10^{\circ}$ in the clockwise direction and compared with the baseline at the reference $0^{\circ}$. The reference amplitude was 1.173 to 1.165, the couch angle at $20^{\circ}$ was 1.132, and the couch angle at $1.0^{\circ}$ was 1.083. At $350^{\circ}$ counterclockwise, the reference amplitude was 1.168 to 1.157, the couch angle at $340^{\circ}$ was 1.124, and the couch angle at $330^{\circ}$ was 1.079. In this study, the phantom is used to quantitatively evaluate the value of the amplitude according to couch change.