• Annual Conference of KIPS
• /
• 2010.11a
• /
• pp.565-567
• /
• 2010

일반적으로 얼굴 인식 방법에는 템플릿 기반 통계적 기법들이 사용되고 있다. 이 방법들은 2차원 영상을 고차원 벡터로 표현하여 특징을 추출한다. 그러나 많은 이미지와 비디오 데이터는 본래 텐서로 표현된다. 따라서, 본 논문에서는 벡터 표현보다는 직접적인 텐서 표현으로 특징들을 추출하기 위해 텐서 얼굴의 다선형 주성분 분석(MPCA: Multilinear Principal Component Analysis) 기법을 이용한 동영상 기반 얼굴인식에 대해 다룬다. 마지막으로, u-로봇 테스트베드 환경에서 구축된 얼굴 인식 데이터 베이스를 이용하여 제안된 방법과 기존 방법들의 인식처리시간과 성능을 비교한다.

• Annual Conference of KIPS
• /
• 2011.11a
• /
• pp.295-297
• /
• 2011

본 논문에서는 동적얼굴영상으로부터 감정인식을 위해 벡터 표현 보다는 직접적인 텐서 표현으로 특징들을 추출하는 텐서 기반 다선형 주성분분석(MPCA: Multilinear Principal Component Analysis) 기법을 사용한다. 사람 6가지의 얼굴 표정을 사용하는데 한 사람의 각 표정마다 5프레임으로 묶어서 텐서 형태로 취하여 특징을 추출하고 인식한다. 시스템의 성능 평가는 CNU 얼굴 감정인식 데이터베이스를 이용하여 특징점 개수와 성능척도에 따른 실험을 수행하여 제시된 방법의 유용성에 관해 살펴본다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.177-179
• /
• 2021

This paper proposes a method of estimating location of a target point at which an interactive robot gazes in an indoor space. RGB images are extracted from low-cost web-cams, user head pose is obtained from the face detection (Openface) module, and geometric configurations are applied to estimate the user's gaze direction in the 3D space. The coordinates of the target point at which the user stares are finally measured through the correlation between the estimated gaze direction and the plane on the table plane.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.27 no.4
• /
• pp.474-484
• /
• 2024

Reinforcement learning, which are also studied in the field of defense, face the problem of sample efficiency, which requires a large amount of data to train. Transfer learning has been introduced to address this problem, but its effectiveness is sometimes marginal because the model does not effectively leverage prior knowledge. In this study, we propose a stochastic initial state randomization(SISR) method to enable robust knowledge transfer that promote generalized and sufficient knowledge transfer. We developed a simulation environment involving a cooperative robot transportation task. Experimental results show that successful tasks are achieved when SISR is applied, while tasks fail when SISR is not applied. We also analyzed how the amount of state information collected by the agents changes with the application of SISR.

• International conference on construction engineering and project management
• /
• 2024.07a
• /
• pp.501-508
• /
• 2024

Building Information Model (BIM) is increasingly being used in the research of construction. The demand for low-cost and efficient access to architectural models is also on the rise. However, generating a parametric model from a point cloud will face interference from other facilities and will be affected by the quality of the measured point cloud. This paper describes a method for generating parametric models from laser-scanned point clouds. With slice voxel selection and line segment detection, the structural framework of the walls can be quickly extracted. By reducing the impact of missing furniture and data on the room, the new approach is applicable to most raw point clouds. This method has potential in multiple directions such as rapid BIM modeling, large-scale room reconstruction, and robot spatial perception.

• The Journal of the Convergence on Culture Technology
• /
• v.6 no.1
• /
• pp.489-494
• /
• 2020

We propose to designs and to implements a robot analyzing the risk of occurrence of mental disorder of single-person households' workers through the facial expression-detecting system. Due to complex social factors, the number and proportion of single-person households continues to increase. In addition, contrast to the household of many family members, the prevalence of mental disorder among single-person household varies greatly. Since most patients with mental can not detect the disease on their own, counseling and treatment with doctors are often ignored. In this study, we design and implement a robot analyzing the risk of mental disorder of single-person households workers by constructing a system with Q.bo One, a social robot created by Thecorpora. Q.bo One is consisted of Arduino, ar raspberry pie, and other sensors designed to detect and respond to sensors in the direction users want to implement. Based on the DSM-5 provided by the American Psychiatric Association, the risk of mental disorder occurrence was specified based on mental disorder. Q.bo One analyzed the facial expressions of the subjects for a week or two to evaluate depressive disorder, anxiety disorder. If the mental disorder occurrence risk is high, Q.bo One is designd to inform the subject to counsel and have medical treatment with a specialist.

• Knowledge Management Research
• /
• v.22 no.3
• /
• pp.235-252
• /
• 2021

The development of information and communication technology and COVID-19 have caused an unusual change in the hotel industry, and the demand for the contactless services such as service robots from hotel customers has surged. Therefore, this study investigates the perception of hotel customers on contactless services by applying a mixed-method analysis. Specifically, this study identified the causal correlations between variables through the structural equation model, and further applied the fuzzy set qualitative comparison analysis to derive patterns of variables that form the intention to use the non-face-to-face services. As a result of the analysis, it was shown that service experience co-creation, palyfulness, personalization, and trust had a significant effect on intention to use through the contactless service use desire. On the other hand, in the results of fuzzy-set qualitative comparison analysis, playfulness was derived as a core factor in all patterns. Based on these analysis results, this study provides academic basis for in-depth understanding of hotel customers' perception of contactless service and specific guidelines for hotel managers on the contactless service strategies in the era of COVID-19 pandemic.

• Journal of Institute of Control, Robotics and Systems
• /
• v.22 no.3
• /
• pp.241-246
• /
• 2016

Nowadays many people have an interest in facial expression and the behavior of people. These are human-robot interaction (HRI) researchers utilize digital image processing, pattern recognition and machine learning for their studies. Facial feature point detector algorithms are very important for face recognition, gaze tracking, expression, and emotion recognition. In this paper, a cascade facial feature point detector is used for finding facial feature points such as the eyes, nose and mouth. However, the detector has difficulty extracting the feature points from several images, because images have different conditions such as size, color, brightness, etc. Therefore, in this paper, we propose an algorithm using a modified cascade facial feature point detector using a convolutional neural network. The structure of the convolution neural network is based on LeNet-5 of Yann LeCun. For input data of the convolutional neural network, outputs from a cascade facial feature point detector that have color and gray images were used. The images were resized to $32{\times}32$. In addition, the gray images were made into the YUV format. The gray and color images are the basis for the convolution neural network. Then, we classified about 1,200 testing images that show subjects. This research found that the proposed method is more accurate than a cascade facial feature point detector, because the algorithm provides modified results from the cascade facial feature point detector.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.35 no.7
• /
• pp.737-743
• /
• 2011

Service robots are equipped with various sensors such as vision camera, sonar sensor, laser scanner, and microphones. Although these sensors have their own functions, some of them can be made to work together and perform more complicated functions. AudioFvisual fusion is a typical and powerful combination of audio and video sensors, because audio information is complementary to visual information and vice versa. Human beings also mainly depend on visual and auditory information in their daily life. In this paper, we conduct two studies using audioFvision fusion: one is on enhancing the performance of sound localization, and the other is on improving robot attention through sound localization and face detection.

• Journal of Digital Convergence
• /
• v.19 no.2
• /
• pp.509-514
• /
• 2021

The pandemic of COVID-19 is driving the demand for non-face-to-face diagnosis, observation, and treatment in the healthcare environment, which has led to increased interest in helathcare robots. The authors intend to predict the direction in which the quarantine healthcare robots should be utilized in the post-corona era through analysis of national agency reports, on-offline press reports, and domestic and foreign robot company press releases. The COVID-19 pandemic has raised interest in medical robots. And there is a need to apply healthcare robots that can perform tasks such as disinfection, logistics transfer, screening tests, monitoring of patients, remote medical treatment support for isolated patients, and video calls with family members. Therefore, it is considered that future correct development and application of healthcare robots and empirical research to verify them should be continued based on sufficient consideration for various problems associated with the practical application of robots.