• 방송공학회논문지
• /
• 제26권3호
• /
• pp.247-257
• /
• 2021

본 논문에서는 3D(dimensional) 스켈레톤을 이용하여 다시점 RGB-D 카메라를 캘리브레이션 하는 새로운 기법을 제안하고자 한다. 다시점 카메라를 캘리브레이션 하기 위해서는 일관성 있는 특징점이 필요하다. 또한 높은 정확도의 캘리브레이션 결과를 얻기 위해서는 정확한 특징점의 획득이 필요하다. 우리는 다시점 카메라를 캘리브레이션 하기 위한 특징점으로 사람의 스켈레톤을 사용한다. 사람의 스켈레톤은 최신의 자세 추정(pose estimation) 알고리즘들을 이용하여 쉽게 구할 수 있게 되었다. 우리는 자세 추정 알고리즘을 통해서 획득된 3D 스켈레톤의 관절 좌표를 특징점으로 사용하는 RGB-D 기반의 캘리브레이션 알고리즘을 제안한다. 다시점 카메라에 촬영된 인체 정보는 불완전할 수 있기 때문에, 이를 통해 획득된 영상 정보를 바탕으로 예측된 스켈레톤은 불완전할 수 있다. 불완전한 다수의 스켈레톤을 효율적으로 하나의 스켈레톤으로 통합한 후에, 통합된 스켈레톤을 이용하여 카메라 변환 행렬을 구함으로써 다시점 카메라들을 캘리브레이션 할 수 있다. 캘리브레이션의 정확도를 높이기 위해서 시간적인 반복을 통해서 다수의 스켈레톤을 최적화에 이용한다. 우리는 실험을 통해서 불완전한 다수의 스켈레톤을 이용하여 다시점 카메라를 캘리브레이션 할 수 있음을 증명한다.

• 대기
• /
• 제17권1호
• /
• pp.45-53
• /
• 2007

In order to investigate the impacts of heat wave on human health, cluster analysis of meteorological elements (e.g., temperature, dewpoint, sea level pressure, visibility, cloud amount, and wind components) for identifying offensive synoptic air masses is employed. Meteorological data at Seoul during the past 30 years are used. The daily death data at Seoul are also employed. Occurrence frequency of heat waves which is defined by daily maximum temperature greater than the threshold temperature (i.e., $31.2^{\circ}C$) was analyzed. The result shows that the frequency and duration of heat waves at Seoul are increasing during the past 30 years. In addition, the increasing trend of the frequency and duration clearly appears in late spring and early autumn as well as summer. Factor analysis shows that 65.1% of the total variance can be explained by 4 components which are linearly independent. Eight clusters (or synoptic air masses) were classified and found to be optimal for representing the summertime air masses at Seoul, Korea. The results exhibit that cluster-mean values of meteorological variables of an offensive air mass (or cluster) are closely correlated with the observed and standardized deaths.

• Asian Journal of Atmospheric Environment
• /
• 제4권3호
• /
• pp.115-140
• /
• 2010

Great concerns about atmospheric aerosols are attributed to their multiple roles to atmospheric processes. For example, atmospheric aerosols influence global climate, directly by scattering or absorbing solar radiations and indirectly by serving as cloud condensation nuclei. They also have a significant impact on human health and visibility. Many of these effects depend on the size and composition of atmospheric aerosols, and thus detailed information on the physicochemical properties and the distribution of airborne particles is critical to accurately predict their impact on the Earth's climate as well as human health. A single particle analysis technique, named low-Z particle electron probe X-ray microanalysis (low-Z particle EPMA) that can determine the concentration of low-Z elements such as carbon, nitrogen and oxygen in a microscopic volume has been developed. The capability of quantitative analysis of low-Z elements in individual particle allows the characterization of especially important atmospheric particles such as sulfates, nitrates, ammonium, and carbonaceous particles. Furthermore, the diversity and the complicated heterogeneity of atmospheric particles in chemical compositions can be investigated in detail. In this review, the development and methodology of low-Z particle EPMA for the analysis of atmospheric aerosols are introduced. Also, its typical applications for the characterization of various atmospheric particles, i.e., on the chemical compositions, morphologies, the size segregated distributions, and the origins of Asian dust, urban aerosols, indoor aerosols in underground subway station, and Arctic aerosols, are illustrated.

• 한국환경복원기술학회지
• /
• 제21권3호
• /
• pp.67-81
• /
• 2018

We tried to analyze qualitatively a total of 110 the research papers which were related domestic ecological restoration technologies about 15 years through semantic network analysis in social network analysis. In order to understand the research trends of ecological restoration technologies, we analyzed the degree centrality and betweenness centrality of the Stream/Wetland, Slope, Soil/Others fields selected as Word Cloud. As a result, ecological restoration technologies have been changed. They were focused on the restoration of species or their habitats in the past. However, they have been evolved into the detailed systems to respond in unpredictable natural disasters and climate change, high-resolution image implementation technology to accurately grasp the practical environment and methods related to environmental restoration for human in urban ecosystem. In the future, investment and technology for the ecosystem restoration field will be continuously demanded for the symbiosis of human beings and species in the damaged ecosystem. Therefore, the research trend of ecological restoration technologies should be provided as reliable guidelines when decision makers establish the policy direction or when researchers select their subjects.

• 영어영문학
• /
• 제57권1호
• /
• pp.3-25
• /
• 2011

As extremes of climate such as heavy storms, rainfalls, and droughts tend to be routine in recent years, global climate change becomes a serious concern not only for natural scientists but also for scholars of the human sciences. Efforts to tackle the anthropogenic climate change certainly require not only scientific knowledge about it but also a new sociocultural paradigm for valorizing and respecting nature in its own right. The huge casualties and mass destruction caused by recent climate disasters also remind us that nature has been an important factor to bring about changes in human history-a fact largely ignored in traditional history. This again validates the ecocritical request to prioritize place, physical setting, or the relationship characters hold with the natural world in understanding literary works. In this context this paper aims to demonstrate the importance of the meteorological vision in creating as well as understanding literary and cultural texts by examining such works as Shelley's "The Cloud," Byron's "Darkness," Keats's "To Autumn," all produced during the period of dramatic climate change including "the year without summer." It also briefly discusses Roland Emmerich's 2004 movie The Day after Tomorrow as a way of understanding recent cultural responses to the crisis of global warming.

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 2020년도 제32회 한글 및 한국어 정보처리 학술대회
• /
• pp.145-150
• /
• 2020

최근 음성인식 분야에서 신경망 기반의 종단간 모델이 제안되고 있다. 해당 모델들은 음성을 직접 입력받아 전사된 문장을 생성한다. 음성을 직접 입력받는 모델의 특성상 데이터의 품질이 모델의 성능에 많은 영향을 준다. 본 논문에서는 이러한 종단간 모델의 문제점을 해결하고자 음성인식 결과를 후처리하기 위한 멀티모달 기반 모델을 제안한다. 제안 모델은 음성과 전사된 문장을 입력 받는다. 입력된 각각의 데이터는 Encoder를 통해 자질을 추출하고 주의집중 메커니즘을 통해 Decoder로 추출된 정보를 전달한다. Decoder에서는 전달받은 주의집중 메커니즘의 결과를 바탕으로 후처리된 토큰을 생성한다. 본 논문에서는 후처리 모델의 성능을 평가하기 위해 word error rate를 사용했으며, 실험결과 Google cloud speech to text모델에 비해 word error rate가 8% 감소한 것을 확인했다.

• 한국정보통신학회논문지
• /
• 제23권12호
• /
• pp.1528-1534
• /
• 2019

최근 들어, 3차원의 깊이 카메라의 대중화로 인해서 RGB 영상에서 수행되던 연구에 새로운 관심과 기회가 생겼지만 사람의 손 자세의 추정은 여전히 어려운 주제 중의 하나로 분류되고 있다. 본 논문에서는 다양하게 입력되는 3차원의 깊이 영상으로부터 사람의 손의 자세를 학습 알고리즘을 이용하여 강인하게 추정하는 방법을 제안한다. 제안된 접근 방법에서는 먼저 뼈대 기반의 손 모델을 생성한 다음, 생성된 손 모델을 3차원의 포인트 클라우드 데이터에 정렬한다. 그런 다음, 랜덤 포레스트 기반의 학습 알고리즘을 이용하여 정렬된 손 모델로부터 손의 자세를 강인하게 추정한다. 본 논문의 실험 결과에서는 제안된 접근 방법이 다양한 실내외의 환경에서 촬영된 입력 영상으로부터 사람의 손의 자세를 강인하고 빠르게 추정한다는 것을 보여준다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권2호
• /
• pp.763-774
• /
• 2015

Hand posture recognition has been a wide region of applications in Human Computer Interaction and Computer Vision for many years. The problem arises mainly due to the high dexterity of hand and self-occlusions created in the limited view of the camera or illumination variations. To remedy these problems, a hand posture recognition method using 3-D point cloud is proposed to explicitly utilize 3-D information from depth maps in this paper. Firstly, hand region is segmented by a set of depth threshold. Next, hand image normalization will be performed to ensure that the extracted feature descriptors are scale and rotation invariant. By robustly coding and pooling 3-D facets, the proposed descriptor can effectively represent the various hand postures. After that, SVM with Gaussian kernel function is used to address the issue of posture recognition. Experimental results based on posture dataset captured by Kinect sensor (from 1 to 10) demonstrate the effectiveness of the proposed approach and the average recognition rate of our method is over 96%.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제5권5호
• /
• pp.938-958
• /
• 2011

Ubiquitous web services have been expanding in various business areas with the evolution of wireless Internet technologies, accessible and usable with a variety of mobile Internet devices such as smart phones. Ubiquitous mobile-web information services can be evaluated for accessibility and usability with the mobile Internet devices interacting with mobile-web information servers. In human mobile-web activity, a web server could be a unified center for mobile-web interaction services as well as for real-time estimation and analysis of mobile-web interaction sessions. We present a real-time estimation and analysis scheme for time-based accessibility and usability in ubiquitous mobile-web services. With real-time estimation/analysis of sessions in a mobile-web server, we estimated the time-based accessibility and usability for comparison between different web services as well as for applications in mobile cloud computing services. We present empirical results based on the implementation of the real-time estimation/analysis scheme.

• 전자통신동향분석
• /
• 제34권1호
• /
• pp.23-35
• /
• 2019

In the upcoming post-app era, real-time, intelligent and immersive services such as autonomous vehicles, virtual secretaries, virtual reality, and augmented reality are expected to dominate. However, there is a growing demand for new networking and computing infrastructure capabilities because existing physical connection-oriented networks and centralized cloud-based service environments have inherent limitations to effectively accommodate these services. To this end, research on intelligent edge network computing technology is underway to analyze the contextual situation of human and things and to configure the service environment on the network edge so that the application services can be performed optimally. In this article, we describe the technology issues for edge network intelligence and introduce related research trends.