• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.5
• /
• pp.518-528
• /
• 2014

In this paper, we propose a method to recognize the action direction of human by developing 4D space-time (4D-ST, [x,y,z,t]) features. For this, we propose 4D space-time interest points (4D-STIPs, [x,y,z,t]) which are extracted using 3D space (3D-S, [x,y,z]) volumes reconstructed from images of a finite number of different views. Since the proposed features are constructed using volumetric information, the features for arbitrary 2D space (2D-S, [x,y]) viewpoint can be generated by projecting the 3D-S volumes and 4D-STIPs on corresponding image planes in training step. We can recognize the directions of actors in the test video since our training sets, which are projections of 3D-S volumes and 4D-STIPs to various image planes, contain the direction information. The process for recognizing action direction is divided into two steps, firstly we recognize the class of actions and then recognize the action direction using direction information. For the action and direction of action recognition, with the projected 3D-S volumes and 4D-STIPs we construct motion history images (MHIs) and non-motion history images (NMHIs) which encode the moving and non-moving parts of an action respectively. For the action recognition, features are trained by support vector data description (SVDD) according to the action class and recognized by support vector domain density description (SVDDD). For the action direction recognition after recognizing actions, each actions are trained using SVDD according to the direction class and then recognized by SVDDD. In experiments, we train the models using 3D-S volumes from INRIA Xmas Motion Acquisition Sequences (IXMAS) dataset and recognize action direction by constructing a new SNU dataset made for evaluating the action direction recognition.

• Korean Business Review
• /
• v.22 no.1
• /
• pp.45-75
• /
• 2009

Previous researches of organizational citizenship behavior have been focused mainly on organizations, and there have been only a few studies on the organizational citizenship behavior of nonprofit organizations. In particular, few empirical studies have been made on the relations among variables affecting the organizational citizenship behavior of profit and nonprofit organizations. Thus, this study attempted comparative analysis. According to the result of the analysis, in profit organizations, the fairness of procedure, emotional commitment and continuous commitment had a significant effect on organizational citizenship behavior, as well as the fairness of distribution and perception of organizational support. In nonprofit organizations, on the contrary, the fairness of distribution, the fairness of procedure, and perception of organizational support were insignificant, and only emotional commitment and continuous commitment had a significant effect on organizational citizenship behavior. This study is meaningful in that it comparatively analyzed the effects of organization members' perception of fairness on organizational citizenship behavior in profit and nonprofit organizations, and its outcome may be utilized as a reference in future researches but it has a problem in external validity that poses a limitation in its generalization.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2021.06a
• /
• pp.301-302
• /
• 2021

본 논문에서는 움직임 정보와 시공간 주의 정보를 심층신경망을 이용하여 함께 활용한 행동 인식 방법을 제안한다. RGB 영상을 입력으로 사용하는 기존 방법과 달리 제안하는 방법은 움직임 정보를 입력으로 사용하여 시간적 특징 및 시공간 주의 정보를 추출하고, RGB 영상에서 추출한 공간적 특징에 시공간 주의 정보를 고려하게 하여 행동 인식 정확도를 향상시킨다. 실험 결과를 통해 행동 분류 정확도 및 연산 효율성이 기존 신경망보다 우수함을 보인다.

• 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.

• The Journal of the Korea Contents Association
• /
• v.16 no.4
• /
• pp.23-35
• /
• 2016

This study investigates the effects of authentic leadership and organizational supports on the organizational citizens behavior of public welfare facility employee. Structural equation model with four latent variables were constructed to test the hypothetical relationships between variables. Out of 230 people from welfare facilities in Yong-in City were sampled and 216 were answered the questionnaire. Results suggests that authentic leadership and organizational support perceptions were shown to have a positive(+) significant effects on the job engagement and organizational citizenship behavior. Authentic leadership and perceived organizational support are effected as a direct positive effect on job engagement, and the influence of perceived organizational support was recognized as greater fact than the authentic leadership. Variable 'job engagement' took a intermediating role between two independent variables and organizational citizenship behavior. Based on the hypothesis test results we might conclude that welfare facility employee whose task require emotional engagement need to be supported by systematic plan of material resources.

• Proceedings of the Korean Information Science Society Conference
• /
• 2010.06c
• /
• pp.507-511
• /
• 2010

휴먼 행동 인식은 크게 3D 모델 기반 방법과 템플릿 기반 방법으로 나눌 수 있다. 3D 모델 기반 방법은 휴먼의 포즈를 3D로 재구성한 뒤 특징을 추출하는 것으로 인식 정확도는 높으나 연산량이 많아 매우 비효율적이다. 반면 템플릿 기반의 방법은 간단하고 수행 시간이 빠르기 때문에 여러 논문들에서 채택되고 있다. 그러나 템플릿을 이용한다는 특성 때문에 시점, 행동 스타일의 변화 등에 따라 실루엣의 변화가 심해 인식 성능에 한계점을 가진다. 본 논문에서는 핵심-포즈들의 히스토그램으로 표현되는 핵심-포즈 분포와 광류의 변화를 이용하여 다중 시점에서의 휴먼 행동 인식 방법을 제안한다. 제안하는 방법은 IXMAS 데이터 셋을 이용한 실험에서 적은 수의 템플릿을 이용하면서도 평균 87.9%의 높은 인식률을 보였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2014.04a
• /
• pp.823-825
• /
• 2014

감시 카메라 환경에서 자동으로 그룹 행동을 인식하는 기술이 최근 많은 관심을 받고 있다. 본 논문에서 제안하는 그룹 해동 인식 시스템은 다른 추가 정보 없이 비디오 프레임만을 인풋으로 받아들여, 자동으로 보행자 탐지, 추적, 행동 인식까지 모두 포괄하는 시스템이다. 시공간 모션 패턴을 만들고 연결 요소들로 모델링 한 뒤 Hidden Markov Model (HMM)을 이용해 그룹 행동을 인식한다. 실험 결과, 기본 논문과 비교하였을 때, 비슷한 인식률을 보이면서 수행 시간을 약 25 배 정도로 획기적으로 단축하였다.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.17 no.3
• /
• pp.32-45
• /
• 2018

This study aims to compare the mutual perception gap on dangerous driving behavior between male and female drivers in multiple aspects, analyze them, and identify factors that trigger this different perception. To understand the mutual perception gap on dangerous driving behavior, DBQ(Driving Behavior Questionnaire) was applied as a rating scale. By applying results into the Co-oreintation model, this study compared the mutual perception gap between male drivers and female drivers and analyze results. In addition, factors that generate the perception gap between both genders were drawn by analyzing factors. This study suggested that objective consistency identified the perception gap that driving behaviors of others were more dangerous between two genders. In addition, subjective consistency was different as both genders assumed that the counterpart's driving behavior takes more risks than their own actual driving behaviors. In regard to the accuracy, men were aware that female driving behaviors are more dangerous than their behaviors. However, female driving behavior assumed by women was consistent with male perception in all factors, which indicated that women perceive men precisely. In addition, results were compared and analyzed in both perspectives of male drivers and female drivers by combining predictive models. Based on these results, both genders perceived that counterpart's driving behavior is more dangerous among both genders.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2005.11a
• /
• pp.225-228
• /
• 2005

본 논문에서는 생물의 2차원영상에서 4가지의 특징을 추출한 다음 약품에 대한 생물의 행동 패턴 반응에 대하여 의사결정나무를 적용하여 패턴의 인식 및 분류를 하였다. 생물의 행동패턴을 대변하는 물리적인 특징인 속도, 방향전환 각도, 이동거리에 대하여 각각 중간이상속도비율, FFT(Fast Fourier Transformation), 2차원 히스토그램 면적, 프렉탈, 무게중심을 사용하여 특징을 추출하였다. 이렇게 추출된 4가지의 특징변수들을 사용하여 의사결정나무 모델을 구성한 다음 생물의 약품 첨가에 대한 반응을 분석하였다. 또한 결과에서는 기존의 생물의 행동패턴 구분에 쓰였던 전형적인 기법(conventional methods)보다 본 연구에서 적용한 의사결정나무가 생물의 행동패턴이 가지는 물리적 요소에 대한 독해력을 가짐을 보임으로써 특정환경에서 이동행동에 대한 분석을 용이하게 하고자 하였다.

• 한국HCI학회:학술대회논문집
• /
• 2006.02b
• /
• pp.112-117
• /
• 2006

웨어러블 컴퓨터는 사용자를 중심으로 의복과 기술이 결합된 기기로서 직관적이며 유연한 인터페이스가 요구된다. 현재 직관적인 입력방식으로 음성인식과 동작인식에 대한 연구가 활발하게 진행되고 있다. 동작인식의 경우 손동작을 이용한 장갑형태가 가장 많으며, 대부분 사용자 행동의 의미를 고려하지 않은 인위적인 제스처로 학습을 필요로 한다. 본 연구에서는 사용자가 일상적으로 하는 행동에서 의미를 추출하고, 웨어러블 컴퓨터의 인터페이스로서 적용가능성을 보고자 한다. 행동은 자극에 대한 신체의 움직임이다. 문헌을 통하여 신체의 움직임에 대한 66개의 동사를 추출하고 구체적인 움직임에 구문조사를 실시하였다. 조사된 구문에 대한 상황과 의미를 조사한 결과 행동은 의미에 따라 감정표현, 의사전달, 정보교류, 자기제어, 기기제어, 무의식적, 의례적의 7가지로 분류할 수 있었다. 그 중 의사소통과 대상을 제어하기 위한 행동을 중심으로 접근하였다. 행동의 의미와 현재 사용되고 있는 UI의 의미를 비교하여 인터페이스를 대응시켜 보았다.