• 한국멀티미디어학회논문지
• /
• 제25권4호
• /
• pp.575-582
• /
• 2022

In the manufacturing environment, research to minimize robot collisions with human beings have been widespread, but in order to interact with robots, it is important to precisely recognize and predict human actions. In this research, after enhancing performance by applying group normalization to the Hourglass model to detect the operator motion, the skeleton was estimated and data were created using this model. And then, three types of operator's movements were recognized using LSTM. As results of the experiment, the accuracy was enhanced by 1% using group normalization, and the recognition accuracy was 99.6%.

• 한국컴퓨터그래픽스학회논문지
• /
• 제23권5호
• /
• pp.29-38
• /
• 2017

본 논문은 나뭇가지 패턴을 의자의 골격에 임의로 합성하는(Tree-Inspired Chair) 모델링 기법을 제안한다. 여러 개의 입력모델을 합성하는 기존 기법과 다르게, 제안 기법은 하나의 메쉬만 사용하여, 사용자가 원하는 부분의 contour mesh로부터 나무 성장 시뮬레이션으로 생성된 패턴을 갖는 의자 모델링이 가능하다. 우리는 나뭇가지 패턴을 생성시킬 영역 contour mesh를 효율적으로 추출하기 위하여 새로운 기법을 제안한다. 우선, 입력된 모델의 face 면적에 기반한 contour mesh를 생성하고, 그 메쉬의 앞뒷면 정보를 이용하여 연결정보가 복원된 skeleton mesh를 생성한다. 또한, 입력 모델의 형상과 유사하게 나뭇가지 패턴을 생성하기 위해 형상 표면의 tangent vector를 고려하는 3-way 나무성장 시뮬레이션 기법을 제안한다. 제안기법은 기존의 가구 모델을 이용하여 간단한 파라미터의 조작만으로 나뭇가지 형상과 가구 모델의 골격을 결합하는 새로운 형태의 가구 모델링을 보여준다. 우리는 실험을 통하여 제안 기법의 성능과 유효성을 보여주었다.

• 제어로봇시스템학회논문지
• /
• 제14권2호
• /
• pp.178-183
• /
• 2008

Human motion analysis is researched as a new method for human-robot interaction (HRI) because it concerns with the key techniques of HRI such as motion tracking and pose recognition. To analysis human motion, extracting features of human body from sequential images plays an important role. After finding the silhouette of human body from the sequential images obtained by CCD color camera, the skeleton model is frequently used in order to represent the human motion. In this paper, using the silhouette of human body, we propose the feature extraction method based on hybrid skeleton for detecting human motion. Finally, we show the effectiveness and feasibility of the proposed method through some experiments.

• 한국정보전자통신기술학회논문지
• /
• 제14권4호
• /
• pp.314-322
• /
• 2021

Skeleton-based action recognition has attracted considerable attention in human action recognition. Recent methods for skeleton-based action recognition employ spatiotemporal graph convolutional networks (GCNs) and have remarkable performance. However, most of them have heavy computational complexity for robust action recognition. To solve this problem, we propose a shuffle graph convolutional network (SGCN) which is a lightweight graph convolutional network using pointwise group convolution rather than pointwise convolution to reduce computational cost. Our SGCN is composed of spatial and temporal GCN. The spatial shuffle GCN contains pointwise group convolution and part shuffle module which enhances local and global information between correlated joints. In addition, the temporal shuffle GCN contains depthwise convolution to maintain a large receptive field. Our model achieves comparable performance with lowest computational cost and exceeds the performance of baseline at 0.3% and 1.2% on NTU RGB+D and NTU RGB+D 120 datasets, respectively.

• International Journal of CAD/CAM
• /
• 제7권1호
• /
• pp.81-89
• /
• 2007

As the modular production is an important issue in globalized manufacturing industries, sub modules or parts of the final product are provided by many suppliers. Some part suppliers design their own products for themselves. In some cases, part supplier may provide the same type product to multiple 1-tier companies. Because all suppliers and 1-tier companies can not use the same CAD system in general case, the engineering change in the CAD model of one company could not propagate to related CAD models of other companies directly. Although they use the same CAD system, it is hard to share their CAD model with each other because of company security policy. In this paper, the neutral reference model, which consists of the neutral skeleton model and the external reference model, is proposed to apply a global top-down modeling approach to collaborating companies.

• 한국CDE학회논문집
• /
• 제13권4호
• /
• pp.243-254
• /
• 2008

As modular production becoming increasingly widespread in globalized manufacturing industries, sub modules or parts of the final product are being provided by many suppliers. Some part suppliers design their own products for themselves. In some cases, part suppliers provide the same type of product to multiple OEM companies. Because all part suppliers and OEM companies typically cannot use the same CAD system, engineering change in the CAD model of one company cannot be directly propagated to related CAD models of other companies. Even if two companies use the same CAD system, it may be difficult to share their CAD model owing to corporate security policy. In this paper, a neutral reference model that consists of a neutral skeleton model and an external reference data model is proposed as a new medium for the sharing and propagation of engineering change information among collaborating companies.

• International Journal of Internet, Broadcasting and Communication
• /
• 제16권2호
• /
• pp.267-277
• /
• 2024

This paper explores the use of machine learning in game production to create goal-oriented, realistic animations for skeleton monsters. The purpose of this research is to enhance realism by implementing intelligent movements in monsters within game development. To achieve this, we designed and implemented a learning model for skeleton monsters using reinforcement learning algorithms. During the machine learning process, various reward conditions were established, including the monster's speed, direction, leg movements, and goal contact. The use of configurable joints introduced physical constraints. The experimental method validated performance through seven statistical graphs generated using machine learning methods. The results demonstrated that the developed model allows skeleton monsters to move to their target points efficiently and with natural animation. This paper has implemented a method for creating game monster animations using machine learning, which can be applied in various gaming environments in the future. The year 2024 is expected to bring expanded innovation in the gaming industry. Currently, advancements in technology such as virtual reality, AI, and cloud computing are redefining the sector, providing new experiences and various opportunities. Innovative content optimized for this period is needed to offer new gaming experiences. A high level of interaction and realism, along with the immersion and fun it induces, must be established as the foundation for the environment in which these can be implemented. Recent advancements in AI technology are significantly impacting the gaming industry. By applying many elements necessary for game development, AI can efficiently optimize the game production environment. Through this research, We demonstrate that the application of machine learning to Unity and game engines in game development can contribute to creating more dynamic and realistic game environments. To ensure that VR gaming does not end as a mere craze, we propose new methods in this study to enhance realism and immersion, thereby increasing enjoyment for continuous user engagement.

• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 2008년도 추계 학술발표회
• /
• pp.1199-1203
• /
• 2008

It has been recognized that unsaturated soil behavior plays an importantrole in geomechanics. In the last decade several constitutive models have been proposed and used in the analysis. Many of them, however, are constructed in the frame work of rate independent model such as elasto-plastic one. Although rate dependency is an important characteristics of soil for both saturated and unsaturated soils, very few models have been developed taking account of rate dependency. In the present paper, we have developed an elasto-viscoplastic model considering an effect of suction based on the overstress-type viscoplasticity with soil structure degradation. In the model, we have adopted an averaged pore pressure composed of pore water pressure and air pressure to determine the effective stress.

• 스마트미디어저널
• /
• 제11권3호
• /
• pp.90-101
• /
• 2022

버스는 대중적으로 많이 이용되는 교통수단이다. 그만큼 승객의 안전관리를 위해 철저한 대비가 필요하다. 하지만 2018년 승차하기 위해 접근하는 노인을 인지하지 못하고 버스가 출발하면서 사망사고가 발생하는 등 안전 시스템이 미흡한 상황이다. 기존에 뒷문 계단 쪽 센서를 통해 끼임 사고를 방지하는 안전 시스템은 있지만, 이러한 시스템은 위 사고처럼 승하차하려는 과정에서 발생하는 사고를 예방하진 못한다. 버스 승객의 승하차 의도를 예측할 수 있다면, 위와 같은 사고를 예방하는 안전 시스템 개발에 도움이 될 것이다. 그러나 승객의 승하차 의도를 예측하는 연구는 부족한 상태이다. 따라서 본 논문에서는 버스에 부착된 카메라 영상에서 UDP-Pose를 통해 승객의 skeleton keypoints를 추출하고, 이를 활용한 1×1 CNN3D 기반의 버스 승객 승하차 의도를 예측하는 모델을 제안한다. 제안한 모델은 승객의 승하차 의도를 예측하는 부분에서 RNN, LSTM 모델보다 약 1~2% 높은 정확도를 보여준다.

• Steel and Composite Structures
• /
• 제49권6호
• /
• pp.615-631
• /
• 2023

To investigate the seismic behavior of steel slag self-stressing concrete-filled circular steel tubular (SSSCFCST) columns, 14 specimens were designed, namely, 10 SSSCFCST columns and four ordinary steel slag (SS) concrete (SSC)-filled circular steel tubular (SSCFCST) columns. Comparative tests were conducted under low reversed cyclic loading considering various parameters, such as the axial compression ratio, diameter-thickness ratio, shear-span ratio, and expansion ratio of SSC. The failure process of the specimens was observed, and hysteretic and skeleton curves were obtained. Next, the influence of these parameters on the hysteretic behavior of the SSSCFCST columns was analyzed. The self stress of SS considerably increased the bearing capacity and ductility of the specimens. Results indicated that specimens with a shear-span ratio of 1.83 exhibited compression bending failure, whereas those with shear-span ratios of 0.91 or 1.37 exhibited drum-shaped cracking failure. However, shear-bond failure occurred in the nonloading direction. The stiffness of the falling section of the specimens decreased with increasing shear-span ratio. The hysteretic curves exhibited a weak pinch phenomenon, and their shapes evolved from a full shuttle shape to a bow shape during loading. The skeleton curves of the specimens were nearly complete, progressing through elastic, elastoplastic, and plastic stages. Based on the experimental study and considering the effects of the SSC expansion rate, shear-span ratio, diameter-thickness ratio, and axial compression ratio on the seismic behavior, a peak displacement coefficient of 0.91 was introduced through regression analysis. A simplified method for calculating load-displacement skeleton curves was proposed and loading and unloading rules for SSSCFCST columns were provided. The load-displacement restorative force model of the specimens was established. These findings can serve as a guide for further research and practical application of SSSCFCST columns.