• Journal of the Korea Society of Computer and Information
• /
• v.25 no.1
• /
• pp.55-61
• /
• 2020

With the development of deep learning technology and advances in computing power, video-based research is now gaining more and more attention. Video data contains a large amount of temporal and spatial information, which is the biggest difference compared with image data. It has a larger amount of data. It has attracted intense attention in computer vision. Among them, motion recognition is one of the research focuses. However, the action recognition of human in the video is extremely complex and challenging subject. Based on many research in human beings, we have found that artificial intelligence-like attention mechanisms are an efficient model for cognition. This efficient model is ideal for processing image information and complex continuous video information. We introduce this attention mechanism into video action recognition, paying attention to human actions in video and effectively improving recognition efficiency. In this paper, we propose a new 3D residual attention network using convolutional neural network based on two attention models to identify human action behavior in the video. An evaluation result of our model showed up to 90.7% accuracy.

• Journal of Broadcast Engineering
• /
• v.23 no.5
• /
• pp.598-605
• /
• 2018

Behavior awareness is a technology that recognizes human behavior through data and can be used in applications such as risk behavior through video surveillance systems. Conventional behavior recognition algorithms have been performed using the 2D camera image device or multi-mode sensor or multi-view or 3D equipment. When two-dimensional data was used, the recognition rate was low in the behavior recognition of the three-dimensional space, and other methods were difficult due to the complicated equipment configuration and the expensive additional equipment. In this paper, we propose a method of recognizing human behavior using only CCTV images without additional equipment using only RGB and depth information. First, the skeleton extraction algorithm is applied to extract points of joints and body parts. We apply the equations to transform the vector including the displacement vector and the relational vector, and study the continuous vector data through the RNN model. As a result of applying the learned model to various data sets and confirming the accuracy of the behavior recognition, the performance similar to that of the existing algorithm using the 3D information can be verified only by the 2D information.

• Korea journal of population studies
• /
• v.33 no.1
• /
• pp.1-25
• /
• 2010

This study looks into travel behavior differences by sex, gender role and economic status. Source for analysis in this study is from Time Use Survey conducted by Korea National Statistical Office in 2004. The sample considered of 3,122 women's time diaries and 2,678 men's, whose age range from 20-59. The results of the study show that married women, women with child under age 6 and unemployed women have less travel time quantity, travel during the daytime and use mass transportation than men and single women. However single women and working women, especially working women having high income level, show more similar patterns of travel behavior with men's which are quite unvarying regardless of marital, parental and economic status.

• Journal of the Korea Society for Simulation
• /
• v.20 no.4
• /
• pp.149-155
• /
• 2011

This paper presents simulations of advance evacuation analysis using a cellular automata model for passenger behavior in an emergency of passenger ship. The proposed cellular automata model divides the space in a uniform grid called "cell." Each passenger is located in a cell and moves to another cell according to a set of local rules assumed to be associated with the individual and crowd behaviors of the passengers. To verify the usefulness of the proposed cellular automata model, 11 tests, all of which are specified in International Maritime Organization Maritime Safety Committee/ Circulation 1238 (IMO MSC/Circ. 1238), were implemented, and it was confirmed that all the requirements of these tests had been met.

• Journal of Korean Society of Transportation
• /
• v.25 no.6
• /
• pp.171-183
• /
• 2007

Urban transport demand is derived from activity participation. A variety of individual daily activities based on the decisions on activity participation result in collective spatial behavior. The travel derived from the effort to overcome the spatially distributed locations of adjacent activities represents the detailed structural relationships among activities. An activity-based approach provides an important framework of analyzing contemporary urban daily life in the sense that it studies the interaction between individuals' daily decision making and social practice in time and space, on the one hand, and socio-spatial environment on the other. The current study identifies representative patterns of urban daily activity implementations and analyzes the correlation between representative patterns and individuals' characteristics and contextual characteristics. The study shows that urban daily activity patterns can be grouped in a limited number of representative patterns, which are systematically correlated with socio-spatial characteristics. The results provide related transportation policy implications.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.20 no.1
• /
• pp.209-220
• /
• 2009

The purpose of this study is to investigate the information behavior of the junior high school students in the public library and to find the effectiveness of the behavior analysis using a cognitive work analysis(CWA). Data was collected through a dept interview and an observation method. Results show that the students had four constraints when they searched materials for reports: relevant materials for reports, limitation of materials, opening hours, use possibility. There are three behavior types. A type is that students find materials on the shelf through searching an online catalog, then make a report using reading the materials. B type is that students find materials on the shelf and check out the materials. C type is that students find materials and check out them by library staff help. CWA can be used for the information behavior research on the library space. CWA can, however, apply for space redesign when various researches would be conducted about the information behavior.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.11a
• /
• pp.215-217
• /
• 2010

IT융합의 중요성이 강조되고 있는 IT 지식정보화 사회에 지능형 로봇의 발전은 끝없이 연구되고 있다. 미래 인간사회에 로봇이 미치는 영향은 아주 클 것으로 예상하고 있으며, 인간의 실생활과 로봇의 가상공간 세계는 점점 일체화 되어 갈 것으로 예측된다. 따라서 인간은 로봇의 활동과 행동을 좀 더 구체적이고 자세하게 제어할 필요가 있다. 최근 현실세계를 가상공간의 세계로 표현하고자 하는 연구가 활발히 진행되고 있으며, 가상공간을 활용한 미래의 세상 환경은 점점 많아 질 것으로 예상한다. 따라서 본 논문에서는 지능로봇 시뮬레이션 맵 자동생성을 위한 제어 동기화 설계를 연구하였다. 현실세계의 실제 로봇과 가상공간의 시뮬레이션 로봇을 동기화하여 하드웨어 로봇의 움직임에 따라 가상공간의 로봇이 맵을 자동으로 생성시킬 수 있는 방법을 연구하고 설계하여 실험하였다. 실제 로봇의 움직임을 3차원 가상공간으로 자동 생성하게 함으로서, 로봇의 제어를 좀 더 지능화 시킬 수 있을 뿐아니라, 여러 다양한 시뮬레이션 테스트 환경으로 응용할 수 있는 큰 장점이 있다. 또한 로봇을 활용한 가상공간 세계의 시뮬레이션은 미래 인간과 로봇이 함께하는 공존세계에 큰 역할을 할 수 있을 것으로 기대한다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.2
• /
• pp.190-195
• /
• 2007

As Ubiquitous era comes, it became necessary to construct environment which can provide more useful information to human in the spaces where people live like homes or offices. On this account, network of the peripheral devices of Ubiquitous should constitute efficiently. For it, this paper researched human pattern by classified motion recognition using sensors module data. (This data processing by Neural network and fuzzy algorithm.) This pattern classification can help control home network system communication. I suggest the system which can control home network system more easily through patterned movement, and control Ubiquitous environment by grasp human's movement and condition.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2009.11a
• /
• pp.247-250
• /
• 2009

본 연구는 가상 캐릭터인 3D Pooh 와의 감성 교감이 이루어지는 유아용 감성 교육 게임 개발이 목적이다. Web 카메라를 이용하여 사용자의 위치 정보 및 영역을 검출하고 사용자는 화면에 보이는 가상 공간에 손과 마커를 이용하여 행동을 가하게 된다. 사용자의 행동 입력 방식에 따라 Pooh 의 상태를 나타내는 게이지와 행동의 다양한 변화를 제공하며, 이로써 사용자들이 가상 캐릭터인 3D Pooh 와 인터렉션을 할 수 있도록 제공한다. 기존의 감성 교감 연구 방법 분석 결과 뇌파와 체온 등의 생리신호를 이용한 방법과 사용자의 행동패턴을 분석하는 방법 등이 있으며, 현재는 생리신호를 이용하는 방법이 더 많이 활용되고 있다. 생리신호 측정 시 사용자는 신체에 센서를 착용해야 하므로 착용 부담감과 움직임이 자유롭지 못하다는 단점이 있다. 본 프로그램은 기존 연구의 단점인 센서 착용의 부담감을 줄이고 자유롭고 편리한 인터렉션이 가능하도록 개발하였으며, 직관적인 인터페이스를 기반으로 유아들도 쉽고 편리하게 즐길 수 있도록 구현된 감성 교육 게임이 될 것으로 기대된다. 또한 카메라 이외의 다른 하드웨어 장치 사용을 최소화하여 경제성과 사용 편의성을 동시에 고려한 효율적인 유아용 감성 교육 게임으로 활용될 수 있다.

• Journal of Korea Multimedia Society
• /
• v.11 no.10
• /
• pp.1427-1435
• /
• 2008

It is worth it to properly present the behaviors of cyberspace and game characters. It is not so easy to manually supply the actions for all objects one by one, so we need to use crowd animation techniques in order to display automatically, realistically, and effectively. In this paper, we construct a ubiquitous cyber aquarium based on sensors, using the crowd behavior library, which is applied to programming crowd behavior in cyberspace and game applications. We use a sensor board to become aware of a person approaching the cyber aquarium, and according to the perceived distance, the objects in the cyber aquarium automatically react and behave accordingly.