• Journal of Korea Multimedia Society
• /
• v.23 no.8
• /
• pp.977-985
• /
• 2020

Aiming at the problem of complex feature extraction and low accuracy in human action recognition, this paper proposed a network structure combining batch normalization algorithm with GoogLeNet network model. Applying Batch Normalization idea in the field of image classification to action recognition field, it improved the algorithm by normalizing the network input training sample by mini-batch. For convolutional network, RGB image was the spatial input, and stacked optical flows was the temporal input. Then, it fused the spatio-temporal networks to get the final action recognition result. It trained and evaluated the architecture on the standard video actions benchmarks of UCF101 and HMDB51, which achieved the accuracy of 93.42% and 67.82%. The results show that the improved convolutional neural network has a significant improvement in improving the recognition rate and has obvious advantages in action recognition.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2002.05d
• /
• pp.797-801
• /
• 2002

Information network technologies introduce a new education environment. Cyber education is growing rapidly as a field of practice especially in distance education system. The development of multimedia environment based on such technology as graphics, image, voice, and video, personal computer systems use has become the media for interactive teaching-teaming service. These features have made integrated multimedia education feasible. This research suggested a direction for the development of an interactive distance education system. I have developed an education system which cooperate problem bank and learning system. This system support arbitration of the relative difficulty in the problem bank database. An ongoing version of this research was evaluated. Those findings reveal several factors that influence how the proposed system can be tailored to the students' perspectives in order to come up with the enhanced version of this system.

• Korean Journal of Computational Design and Engineering
• /
• v.12 no.2
• /
• pp.126-136
• /
• 2007

Teleconferences have been used in business sectors to reduce traveling costs. Traditionally, specialized telephones that enabled multiparty conversations were used. With the introduction of high speed networks, we now have high definition videos that add more realism in the presence of counterparts who could be thousands of miles away. This paper presents a new technology that adds even more realism by telecommunicating with hand gestures. This technology is part of a teleconference system named SMS (Smart Meeting Space). In SMS, a person can use hand gestures to manipulate meeting data that could be in the form of text, audio, video or 3D shapes. Fer detecting hand gestures, a machine learning algorithm called SVM (Support Vector Machine) has been used. For the prototype system, a 3D interaction environment has been implemented with $OpenGL^{TM}$, where a 3D human skull model can be grasped and moved in 6-DOF during a remote conversation between distant persons.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.34S no.9
• /
• pp.23-30
• /
• 1997

In this paper, a decision feedback recurrent neural equalization (DFRNE) scheme is proposed for adaptive equalization problems. The proposed equalizer models a nonlinear infinite impulse response (IIR) filter. The modified Real-Time recurrent Learning Algorithm (RTRL) is used to train the DFRNE. The DFRNE is applied to both linear channels with only intersymbol interference and nonlinear channels for digital video cassette recording (DVCR) system. And the performance of the DFRNE is compared to those of the conventional equalizaion schemes, such as a linear equalizer, a decision feedback equalizer, and neural equalizers based on multi-layer perceptron (MLP), in view of both bit error rate performance and mean squared error (MSE) convergence. It is shown that the DFRNE with a reasonable size not only gives improvement of compensating for the channel introduced distortions, but also makes the MSE converge fast and stable.

• Journal of The Korean Association For Science Education
• /
• v.25 no.1
• /
• pp.26-40
• /
• 2005

Based on the Vygotskian perspective that a learner's thinking is constituted in his or her talk and the assumption that student talk in the classroom may occur in more than one way, this study examined discursive practices of students in Korean high school science classrooms. Data came from $11^{th}$ grade earth science classrooms where the Group Investigation (GI) method was implemented. Data source included verbatim transcripts developed from video recordings of class sessions in which students presented their science projects to the whole class and exchanged questions and answers during the presentations. The analysis of the videotape transcripts revealed five different modes of student talk, including 1) retrieving information, 2) reformulating information, 3) building on one's own experience, 4) elaborating current understanding, and 5) negotiating meanings with others. Considering that each of the five modes had different value for learning science, it was recommended that the teacher should engage students in more active modes of discourse and guide them into more sophisticated understanding of science.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.10b
• /
• pp.571-573
• /
• 2000

기존 분산 가상환경 시스템에서는 참여자들 사이의 언어 외적인 의사교환을 지원하기 위해 참여자의 아바타에 몸짓이나 얼굴 표정 등을 표현할 수 있도록 애니메이션 가능한 아바타를 사용한다. 하지만 아바타 애니메이션으로 참여자의 의사 및 감정 표현을 표현하는데는 한계가 있다. 따라서, 이 논문에서는 가상 환경 내의 다중 사용자들의 의사 교환 및 감정 표현을 극대화할 수 있는 방법으로 실시간 화상 대화 가상 환경 학습.훈련 시스템을 설계하였다. 설계한 시스템은 학습 참여자의 화상 및 음성 스트림을 전달함으로써 기존 응용들에 비해 풍부한 의사 교환을 지원하고, 가상 공간에서 학습에 필요한 다양한 모듈들을 포함하고 있다.

• International journal of advanced smart convergence
• /
• v.8 no.3
• /
• pp.145-150
• /
• 2019

Due to the development of science and technology and the emergence of new industries, the environmental change of the digital contents industry is rapidly progressing. The scope of technological development in the digital contents industry is affecting not only the entertainment industry but also various industries. Recently, with the development of digital convergence using realistic content, games, video, and VR have provided new opportunities for the growth of the content industry. The researcher determined that a new education system would need to be changed as the digital contents industry developed. For this purpose, an AHP questionnaire was conducted for experts with a high basic understanding of the education platform based on previous studies. We proposed a platform model for human resource development as an education system that meets the demand of digital contents industry. The education system for nurturing talents needed by future society should include elements that can interest the learning of users. The platform should not be approached from a system point of view, but should be developed from the content and user's point of view, considering the platform's original purpose.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.06a
• /
• pp.217-220
• /
• 2018

본 논문에서는 딥러닝을 활용한 비디오 보간법(video interpolation)에 대한 최근 모델들을 HD 급 비디오로 학습시키는 방법과 평가 성능을 비교 분석하는 것을 목표로 한다. 기존의 딥러닝을 활용한 비디오 보간법에 대해 제안된 모델들은 낮은 해상도의 비디오로 실험을 진행하였다. 반면 본 연구에서는 한정된 메모리를 가지고도 높은 해상도의 비디오를 학습시키기 위해서 패치 단위 데이터 셋을 구성하여 학습을 진행하였다. 평가 성능을 보이기 위해서 학습 데이터와 마찬가지로 패치 단위 평가와 전체 프레임 단위 평가 성능의 결과를 비교한다.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.15 no.6
• /
• pp.281-287
• /
• 2020

In this paper, we propose a method for estimating a walking direction by which a mobile robots follows a person using TRT (Tensor RT) pose, which is motion recognition based on deep learning. Mobile robots can measure individual movements by recognizing key points on the person's pelvis and determine the direction in which the person tries to move. Using these information and the distance between robot and human, the mobile robot can follow the person stably keeping a safe distance from people. The TRT Pose only extracts key point information to prevent privacy issues while a camera in the mobile robot records video. To validate the proposed technology, experiment is carried out successfully where human walks away or toward the mobile robot in zigzag form and the robot continuously follows human with prescribed distance.

• Journal of Korea Multimedia Society
• /
• v.24 no.6
• /
• pp.796-804
• /
• 2021

In computer vision, visual tracking method addresses the problem of localizing an specific object in video sequence according to the bounding box. In this paper, we propose a tracking method by introducing the feature correlation comparison into the siamese network to increase its matching identification. We propose a way to compute location of object to improve matching performance by a correlation operation, which locates parts for solving the searching problem. The higher layer in the network can extract a lot of object information. The lower layer has many location information. To reduce error rate of the object center point, we built a siamese network that extracts the distribution and location information of target objects. As a result of the experiment, the average center error rate was less than 25%.