• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.7
• /
• pp.913-918
• /
• 2007

Human motion analysis is an important research subject in human-robot interaction (HRI). However, before analyzing the human motion, silhouette of human body should be extracted from sequential images obtained by CCD camera. The intelligent robot system requires more robust silhouette extraction method because it has internal vibration and low resolution. In this paper, we discuss the hybrid silhouette extraction method for detecting and tracking the human motion. The proposed method is to combine and optimize the temporal and spatial gradient information. Also, we propose some compensation methods so as not to miss silhouette information due to poor images. Finally, we have shown the effectiveness and feasibility of the proposed method through some experiments.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.6
• /
• pp.755-759
• /
• 2009

The ability to recognize human emotion is one of the hallmarks of human-robot interaction. Especially, speaker-independent emotion recognition is a challenging issue for commercial use of speech emotion recognition systems. In general, speaker-independent systems show a lower accuracy rate compared with speaker-dependent systems, as emotional feature values depend on the speaker and his/her gender. Hence, this paper describes the realization of speaker-independent emotion recognition by rejection using confidence measure to make the emotion recognition system be homogeneous and accurate. From comparison of the proposed methods with conventional method, the improvement and effectiveness of proposed methods were clearly confirmed.

• ETRI Journal
• /
• v.39 no.5
• /
• pp.643-651
• /
• 2017

Human age estimation is one of the key factors in the field of Human-Robot Interaction/Human-Computer Interaction (HRI/HCI). Owing to the development of deep-learning technologies, age recognition has recently been attempted. In general, however, deep learning techniques require a large-scale database, and for age learning with variations, a conventional database is insufficient. For this reason, we propose an age estimation method using artificially generated data. Image data are artificially generated through 3D information, thus solving the problem of shortage of training data, and helping with the training of the deep-learning technique. Augmentation using 3D has advantages over 2D because it creates new images with more information. We use a deep architecture as a pre-trained model, and improve the estimation capacity using artificially augmented training images. The deep architecture can outperform traditional estimation methods, and the improved method showed increased reliability. We have achieved state-of-the-art performance using the proposed method in the Morph-II dataset and have proven that the proposed method can be used effectively using the Adience dataset.

• The Journal of Korean Institute of Next Generation Computing
• /
• v.15 no.3
• /
• pp.16-24
• /
• 2019

Recently, research on emotion recognition based on EEG has attracted great interest from human-robot interaction field. In this paper, we propose a method of labeling using image-based EEG topography instead of evaluating emotions through self-assessment and annotation labeling methods used in MAHNOB HCI. The proposed method evaluates the emotion by machine learning model that learned EEG signal transformed into topographical image. In the experiments using MAHNOB-HCI database, we compared the performance of training EEG topography labeling models of SVM and kNN. The accuracy of the proposed method was 54.2% in SVM and 57.7% in kNN.

• Journal of Climate Change Research
• /
• v.7 no.2
• /
• pp.205-215
• /
• 2016

The relationship between the climate and the number of heat-related patients in South Korea was analysed in this study. The number of the patients was 1,612 during the summer 2011 to 2015 according to the Heat-related Illness (HRI) surveillance system. The coefficient of determination between the number of the patients and the daily maximum temperature was higher than that between the number of them and the other elements: the daily mean/minimum temperature and relative humidity. The thresholds of daily maximum and minimum temperature in metropolitan cities (MC) were higher than those in regions except for MC (RMC). The higher the maximum and minimum temperature became, the more frequently the heat-related illness rate was observed. The regional difference of this rate was that the rate in RMC was higher than that in MC. Prolonged heat wave and tropical night tended to cause more patients, which continued for 20 days and 31 days of maximum values, respectively. On the other hand, the relative humidity was not proportional to the number of the patients which was rather decreasing at over 70% of relative humidity.

• Journal of Semiconductor Engineering
• /
• v.2 no.2
• /
• pp.130-135
• /
• 2021

Recently, deep neural networks (DNNs) are actively used for action control so that an autonomous system, such as the robot, can perform human-like behaviors and operations. Unlike recognition tasks, the real-time operation is essential in action control, and it is too slow to use remote learning on a server communicating through a network. New learning techniques, such as reinforcement learning (RL), are needed to determine and select the correct robot behavior locally. In this paper, we propose an energy-efficient DNN processor with a LUT-based processing engine and near-zero skipper. A CNN-based facial emotion recognition and an RNN-based emotional dialogue generation model is integrated for natural HRI system and tested with the proposed processor. It supports 1b to 16b variable weight bit precision with and 57.6% and 28.5% lower energy consumption than conventional MAC arithmetic units for 1b and 16b weight precision. Also, the near-zero skipper reduces 36% of MAC operation and consumes 28% lower energy consumption for facial emotion recognition tasks. Implemented in 65nm CMOS process, the proposed processor occupies 1784×1784 um2 areas and dissipates 0.28 mW and 34.4 mW at 1fps and 30fps facial emotion recognition tasks.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.152-152
• /
• 2023

하천의 건강성을 평가하기 위해 일반적으로 수생태계 건강성 지표(TDI, BMI, FAI, HRI, RVI)가 사용되고 있다. 이 지표는 5가지 등급으로 구분하여 매우 좋음(A), 좋음(B), 보통(C), 나쁨(D), 매우나쁨(E)으로 구분된다. 하지만, 하천의 건강성 관점에서 수질, 토지이용, 지리적 특성, 경관지수와의 상관성을 바탕으로 어떤 영향을 미치는지에 대한 연구가 필요하다. 본 연구에서는 하천의 수생태계 건강성에 영향을 미치는 환경적 인자들과의 관계성을 분석하여 수생태계 건강성이 '좋음'에 해당되는 하천으로 분류하고자 한다. 이를 통해 환경적 인자들의 임계값을 산출하여 하천 관리에 대한 구체적인 우선순위 설정 방안을 제안하고자 한다. 낙동강대권역을 대상으로 수질, 토지이용, 지리적 특성, 경관지수의 여러 변수 중 수생태계 건강성과의 관계에서 대표성을 나타낼 수 있는 환경적 인자를 선정하기 위하여 정준상관분석(CCA)을 수행하였다. 또한 모델 기반의 클러스터 분석을 활용하여 소권역별로 수생태계 건강성이 '좋음'에 해당할 확률을 파악하고, 여기에 해당하는 소권역에 대하여 각각의 환경적 인자에 대한 임계값을 정량적으로 평가하였다. 본 연구에서는 하천의 환경 인자들과의 관계를 분석하여 수생태계 건강성을 평가하고 하천 관리에 대한 구체적인 우선순위를 파악하는 방법을 제안한다. 주성분 분석 및 모델 기반 클러스터 분석을 사용하여 각 소권역에 대한 환경 인자의 임계값을 평가하고, 정책 결정자들이 하천의 건강성을 유지하고 개선할 수 있는 정보를 제공할 수 있다.

• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.148-153
• /
• 2006

인간-컴퓨터 상호작용(HCI) 기술은 과거 컴퓨터란 어렵고 소수의 숙련자만이 다루는 것이라는 인식을 바꾸어 놓았다. HCI 는 컴퓨터 사용자인 인간에게 거부감 없이 수용되기 위해 인간과 컴퓨터가 조화를 이루는데 많은 성과를 거두어왔다. 컴퓨터 비전에 기반을 두고 인간과 컴퓨터의 상호작용을 위하여 사용자 의도 및 행위 인식 연구들이 많이 행해져 왔다. 특히 손을 이용한 제스처는 인간과 인간, 인간과 컴퓨터 그리고 최근에 각광받고 있는 인간과 로봇의 상호작용에 중요한 역할을 해오고 있다. 본 논문에서 제안하는 손 추출 및 추적 알고리즘은 비전에 기반한 호출자 인식과 손 추적 알고리즘을 병행한 자연스러운 손 추출 및 추적 알고리즘이다. 인간과 인간 사이의 상호간의 주의집중 방식인 호출 제스처를 인식하여 기반하여 사용자가 인간과 의사소통 하는 것과 마찬가지로 컴퓨터/로봇의 주의집중을 끌도록 하였다. 또한 호출 제스처에 의해서 추출된 손동작을 추적하는 알고리즘을 개발하였다. 호출 제스처는 카메라 앞에 존재할 때 컴퓨터/로봇의 사용자가 자신에게 주의를 끌 수 있는 자연스러운 행동이다. 호출 제스처 인식을 통해 복수의 사람이 존재하는 상황 하에서 또한 원거리에서도 사용자는 자신의 의사를 전달하고자 함을 컴퓨터/로봇에게 알릴 수 있다. 호출 제스처를 이용한 손 추출 방식은 자연스러운 손 추출을 할 수 있도록 한다. 현재까지 알려진 손 추출 방식은 피부색을 이용하고 일정 범위 안에 손이 존재한다는 가정하에 이루어져왔다. 이는 사용자가 제스처를 하기 위해서는 특정 자세로 고정되어 있어야 함을 의미한다. 그러나 호출 제스처를 통해 손을 추출하게 될 경우 서거나 앉거나 심지어 누워있는 상태 등 자연스러운 자세에서 손을 추출할 수 있게 되어 사용자의 불편함을 해소 할 수 있다. 손 추적 알고리즘은 자연스러운 상황에서 획득된 손의 위치 정보를 추적하도록 고안되었다. 제안한 알고리즘은 색깔정보와 모션 정보를 융합하여 손의 위치를 검출한다. 손의 피부색 정보는 신경망으로 다양한 피부색 그룹과 피부색이 아닌 그룹을 학습시켜 얻었다. 손의 모션 정보는 연속 영상에서 프레임간에 일정 수준 이상의 차이를 보이는 영역을 추출하였다. 피부색정보와 모션정보로 융합된 영상에서 블랍 분석을 하고 이를 민쉬프트로 추적하여 손을 추적하였다. 제안된 손 추출 및 추적 방법은 컴퓨터/로봇의 사용자가 인간과 마주하듯 컴퓨터/로봇의 서비스를 받을 수 있도록 하는데 주목적을 두고 있다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.6C
• /
• pp.593-603
• /
• 2009

In this paper, we propose a new integrated computer vision system designed to track multiple human beings and extract their silhouette with an active stereo camera. The proposed system consists of three modules: detection, tracking and silhouette extraction. Detection was performed by camera ego-motion compensation and disparity segmentation. For tracking, we present an efficient mean shift based tracking method in which the tracking objects are characterized as disparity weighted color histograms. The silhouette was obtained by two-step segmentation. A trimap is estimated in advance and then this was effectively incorporated into the graph cut framework for fine segmentation. The proposed system was evaluated with respect to ground truth data and it was shown to detect and track multiple people very well and also produce high quality silhouettes. The proposed system can assist in gesture and gait recognition in field of Human-Robot Interaction (HRI).

• Journal of The Korean Association of Information Education
• /
• v.10 no.1
• /
• pp.155-161
• /
• 2006

Robots evolve from tools to information media since they generates information by interacting with human. As studies on robot-aided education are still in a starting phase, attempts need to be made to use robots for educational purposes and to investigate the effects of the use. It was showed that robot-aided learning was friendlier than other media assisted learning, and especially effective for motivating children. We developed the prototype robot Jenny that can help teachers as a educational media in class(i.e. as a T.A. robot, it can present robot contents on its chest to screen and explain about it when teacher asks). is a schoolmate for 5th or 6th grade children or an elder schoolmate for the rest. We performed the field trial at an elementary school. We carried out 9 classes for three subjects(english, korean, music) with -students in $4th{\sim}5th$ grade. They thought Jenny who was 13 years old as an elder schoolmate in 6th grade. Also, a significant difference was found in the interest and concentration of experimental groups from controlled groups.