• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.773-775
• /
• 2022

영상처리 기술의 발달로 영상처리 기술을 이용한 다양한 어플리케이션이 출시되고 있다. 영상처리 기술로 영상의 정보를 디지털화 할 수 있는 점에 착안해 춤 실력을 평가하는 시스템을 고안했다. 본 작품에서는 Human Pose Estimation 기술로 사람의 관절 위치 정보를 파악하고, 춤 전문가의 관절 위치와 사용자의 관절 위치를 동작 비교 알고리즘을 통해 비교해 사용자가 춤을 얼마나 정확하게 추는지 수치적으로 점수화해 제공한다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.10
• /
• pp.1398-1401
• /
• 2020

We present the concept of a Medical Digital Twin (MDT) that can predict and analyze medical diseases using computer simulations and introduce a dynamic virtual body capture system to create it. The MDT is a technology that creates a 3D digital virtual human body by reflecting individual medical and biometric information. The virtual human body is composed of a static virtual human body that reflects an individual's internal and external information and a dynamic virtual human body that reflects his motion. Especially we describe an early version of the dynamic virtual body capture system that enables continuous simulation of musculoskeletal diseases.

• Journal of KIISE:Software and Applications
• /
• v.36 no.11
• /
• pp.960-966
• /
• 2009

A manifold is used to represent a relationship between high-dimensional data samples in low-dimensional space. In human pose estimation, it is created in low-dimensional space for processing image and 3D body configuration data. Manifold learning is to build a manifold. But it is vulnerable to silhouette variations. Such silhouette variations are occurred due to view-change, person-change, distance-change, and noises. Representing silhouette variations in a single manifold is impossible. In this paper, we focus a silhouette variation problem occurred by view-change. In previous view invariant pose estimation methods based on manifold learning, there were two ways. One is modeling manifolds for all view points. The other is to extract view factors from mapping functions. But these methods do not support one by one mapping for silhouettes and corresponding body configurations because of unsupervised learning. Modeling manifold and extracting view factors are very complex. So we propose a method based on triple manifolds. These are view manifold, pose manifold, and body configuration manifold. In order to build manifolds, we employ biased manifold learning. After building manifolds, we learn mapping functions among spaces (2D image space, pose manifold space, view manifold space, body configuration manifold space, 3D body configuration space). In our experiments, we could estimate various body poses from 24 view points.

• Journal of Information Processing Systems
• /
• v.15 no.1
• /
• pp.67-90
• /
• 2019

Accurate detection, tracking and analysis of human movement using robots and other visual surveillance systems is still a challenge. Efforts are on to make the system robust against constraints such as variation in shape, size, pose and occlusion. Traditional methods of detection used the sliding window approach which involved scanning of various sizes of windows across an image. This paper concentrates on employing a state-of-the-art, hierarchical graph based method for segmentation. It has two stages: part level segmentation for color-consistent segments and object level segmentation for category-consistent regions. The tracking phase is achieved by employing SIFT keypoint descriptor based technique in a combined matching and tracking scheme with validation phase. Localization of human region in each frame is performed by keypoints by casting votes for the center of the human detected region. As it is difficult to avoid incorrect keypoints, a consensus-based framework is used to detect voting behavior. The designed methodology is tested on the video sequences having 3 to 4 persons.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.634-636
• /
• 2023

Surveillance systems play a pivotal role in ensuring the safety and security of various environments, including public spaces, critical infrastructure, and private properties. However, detecting abnormal human behavior in lowlight conditions is a critical yet challenging task due to the inherent limitations of visual data acquisition in such scenarios. This paper introduces a spatiotemporal framework designed to address the unique challenges posed by low-light environments, enhancing the accuracy and efficiency of human abnormality detection in surveillance camera systems. We proposed the pre-processing using lightweight exposure correction, patched frames pose estimation, and optical flow to extract the human behavior flow through t-seconds of frames. After that, we train the estimated-action-flow into autoencoder for abnormal behavior classification to get normal loss as metrics decision for normal/abnormal behavior.

• Journal of Korean Institute of Industrial Engineers
• /
• v.37 no.2
• /
• pp.96-104
• /
• 2011

Modeling and simulation of human-involved complex systems pose challenges to representing human decision makings into logical systems because of the nondeterministic and dynamic nature of human behaviors. In modeling perspectives, human's activities in systems can increase uncertainty and complexity, because he or she can potentially access all other resources within the system and change the system states. To address all of these human involvements in the system, this research suggests applying the Finite State Automata (FSA)-based formal modeling of human-involved systems that incorporates the ecological concept of affordances to an evacuation simulation, so that human behavioral patterns under urgent and dynamic emergency situations can be considered in the real-time simulation. The proposed simulation methodologies were interpreted using the warehouse fire evacuation simulation to clarify the applicability of the proposed methodology. This research is expected to merge system engineering technologies and human factors, and come out to the new predictive modeling methodology for disaster simulations. This research can be applied to a variety of applications such as building layout designs and building access control systems for emergency situations.

• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.8
• /
• pp.738-744
• /
• 2013

According to the cognitive science research, the interaction intent of humans can be estimated through an analysis of the representing behaviors. This paper proposes a novel methodology for reliable intention analysis of humans by applying this approach. To identify the intention, 8 behavioral features are extracted from the 4 characteristics in human-human interaction and we outline a set of core components for nonverbal behavior of humans. These nonverbal behaviors are associated with various recognition modules including multimodal sensors which have each modality with localizing sound source of the speaker in the audition part, recognizing frontal face and facial expression in the vision part, and estimating human trajectories, body pose and leaning, and hand gesture in the spatial part. As a post-processing step, temporal confidential reasoning is utilized to improve the recognition performance and integrated human model is utilized to quantitatively classify the intention from multi-dimensional cues by applying the weight factor. Thus, interactive robots can make informed engagement decision to effectively interact with multiple persons. Experimental results show that the proposed scheme works successfully between human users and a robot in human-robot interaction.

• Toxicological Research
• /
• v.12 no.2
• /
• pp.271-275
• /
• 1996

Carcinogenic potential of HPV-16 DNA and NNK in a human keratinocyte cell line was assessed to study effects of viral-chemical interaction. Human cells were transfected with HPV-16 DNA and 6 clonal cell lines were subsequently obtained. Clonal line-3 and 6 at passage 7 showed characteristics of tumor cells such as increases of saturation density, soft-agar colony formation, cell aggregation and foci appearance. Among cells treated with 1$\mu M$, 10$\mu M$, 100$\mu M$ or 1 mM of NNK for 4 weeks, 100$\mu M$ treatment showed most tumorigenic characteristics at passage 7. These results indicate that either HPV-16 or NNK alone is tumorigenic in this in human in vitro model. When cells transfected with HPV-16 were subsequently exposed by 100 uM NNK for 4 weeks, all the clonal cells except clone-1 showed higher levels of tumor cell characteristics than HPV-16 DNA or NNK exposure alone. Clonal line-6, the most tumorigenic cells, showed higher transcriptional level of fibronectin and lower level of TGF-$\beta_1$, as compared to control cells, suggesting that alteration of growth factor or extracellular matrix may play a role in carcinogenesis process induced by HPV-16 and NNK. Taken together, the present study indicates that viral-chemical interactions between HPV-16 DNA and NNK enhance carcinogenic potentials of human cells and implies that smoking among people infected with human papillomavirus may pose an additional risk of causing cancer.

• Journal of Broadcast Engineering
• /
• v.26 no.3
• /
• pp.247-257
• /
• 2021

This paper proposes a new technique for calibrating a multi-view RGB-D camera using a 3D (dimensional) skeleton. In order to calibrate a multi-view camera, consistent feature points are required. In addition, it is necessary to acquire accurate feature points in order to obtain a high-accuracy calibration result. We use the human skeleton as a feature point to calibrate a multi-view camera. The human skeleton can be easily obtained using state-of-the-art pose estimation algorithms. We propose an RGB-D-based calibration algorithm that uses the joint coordinates of the 3D skeleton obtained through the posture estimation algorithm as a feature point. Since the human body information captured by the multi-view camera may be incomplete, the skeleton predicted based on the image information acquired through it may be incomplete. After efficiently integrating a large number of incomplete skeletons into one skeleton, multi-view cameras can be calibrated by using the integrated skeleton to obtain a camera transformation matrix. In order to increase the accuracy of the calibration, multiple skeletons are used for optimization through temporal iterations. We demonstrate through experiments that a multi-view camera can be calibrated using a large number of incomplete skeletons.

• International Journal of Aeronautical and Space Sciences
• /
• v.14 no.1
• /
• pp.11-18
• /
• 2013

Human spaceflight experience in extra-vehicular activity (EVA) is limited to two regimes: the micro-gravity environment of Earth orbit, and the lunar surface environment at one-sixth of Earth's gravity. Future human missions to low-gravity bodies, including asteroids, comets, and the moons of Mars, will require EVA techniques that are beyond the current experience base. In order to develop robust approaches for exploring these small bodies, the dynamics associated with human exploration on low-gravity surface must be characterized. This paper examines the translational and rotational motion of an astronaut on the surface of a small body, and it is shown that the low-gravity environment will pose challenges to the surface mobility of an astronaut, unless new tools and EVA techniques are developed. Possibilities for addressing these challenges are explored, and utilization of the International Space Station to test operational concepts and hardware in preparation for a low-gravity surface EVA is discussed.