• Journal of Institute of Control, Robotics and Systems
• /
• 제11권12호
• /
• pp.1062-1067
• /
• 2005

This paper discusses a skeleton feature extraction method for ubiquitous robot system. The skeleton features are used to analyze human motion and pose estimation. In different conventional feature extraction environment, the ubiquitous robot system requires more robust feature extraction method because it has internal vibration and low image quality. The new hybrid silhouette extraction method and adaptive skeleton model are proposed to overcome this constrained environment. The skin color is used to extract more sophisticated feature points. Finally, the experimental results show the superiority of the proposed method.

• International Journal of Aeronautical and Space Sciences
• /
• 제17권1호
• /
• pp.45-53
• /
• 2016

This work is mainly done by too many manual operations in the aircraft structure design process resulting in heavy workload, low efficiency and quality, non-standardized processes and procedures. A top-down associated design method employing the template parametric technology is proposed here in order to improve the quality of design and efficiency of aircraft wing structure at the preliminary design stage. The appropriate parametric tool is chosen and the rapid design system of knowledge-driven aircraft wing structure is developed. First, a skeleton model of aircraft wing structure is rapidly built up through the template encapsulated design knowledge. Associated design is then introduced to realize the association between the typical structural part and skeleton model. Finally, the related elements are referenced from skeleton model, and a typical structural part reflecting an automatic response for design changes of the upstream skeleton model is quickly constructed within the template. The rapid design system proposed and developed in this paper is able to formalize the design standardization of aircraft wing structure and thus the rapid generation of different aircraft wing structure programs and achieve the structural design knowledge reuse as well.

• Structural Engineering and Mechanics
• /
• 제77권2호
• /
• pp.179-196
• /
• 2021

Experimental investigations on the seismic behaviors of the PVC-FRP Confined Reinforced Concrete (PFCRC) columns under low cyclic loading are carried out and two variable parameters including CFRP strips spacing and axial compression ratio are considered. The PFCRC column finally fails by bending and is characterized by the crushing of concrete and yielding of the longitudinal reinforcement, and the column with a high axial compression ratio is also accompanied by the cracking of the PVC tube and the fracture of CFRP strips. The hysteretic curves and skeleton curves of the columns are obtained from the experimental data. With the increase of axial compression ratio, the stiffness degradation rate accelerates and the ductility decreases. With the decrease of CFRP strips spacing, the unloading sections of the skeleton curves become steep and the ductility reduces significantly. On the basis of fiber model method, a numerical analysis approach for predicting the skeleton curves of the PFCRC columns is developed. Additionally, a simplified skeleton curve including the elastic stage, strengthening stage and unloading stage is suggested depending on the geometric drawing method. Moreover, the loading and unloading rules of the PFCRC columns are revealed by analyzing the features of the skeleton curves. The quantitative expressions that are used to predict the unloading stiffness of the specimens in each stage are proposed. Eventually, an analytical model for the PFCRC columns under low cyclic loading is established and it agrees well with test data.

• Steel and Composite Structures
• /
• 제21권3호
• /
• pp.661-677
• /
• 2016

The quasi static test of the steel reinforced concrete (SRC) bridge piers and rigid frame arch bridge structure with SRC piers was conducted in the laboratory, and the seismic performance of SRC piers was compared with that of reinforced concrete (RC) bridge piers. In the test, the failure process, the failure mechanism, hysteretic curves, skeleton curves, ductility coefficient, stiffness degradation curves and the energy dissipation curves were analyzed. According to the $M-{\Phi}$ relationship of fiber section, the three-wire type theoretical skeleton curve of the lateral force and the pier top displacement was proposed, and the theoretical skeleton curves are well consistent with the experimental curves. Based on the theoretical model, the effects of the concrete strength, axial compression ratio, slenderness ratio, reinforcement ratio, and the stiffness ratio of arch to pier on the skeleton curve were analyzed.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 한국소성가공학회 1997년도 고액공존금속의 성형기술 심포지엄
• /
• pp.5-15
• /
• 1997

It is the objective of this study that by conducting the serni-solid extrusion using A12024, the effect of various process variables on the quality of extruded product and extrusion force is understood. The results of experiment are compared with those of finite element simulation in order to verify the effectiveness of the developed FE-simulation code. In order to simulate densification in the deformation of serni-solid material, the semi-solid material is assumed to be composed of solid region as porous skeleton following compressible visco-plastic model and liquid region following Darcy's equation for the liquid flow saturated in the interstitial space. Then the flow and deformation of the semi-solid alloy are analyzed by coupling the deformation of the porous skeleton and the flow of the eutectic liquid. It is assumed that initial solid fraction is homogeneous. Yield and plastic potential function presented by Kuhn and constitutive model developed by Gunasekera are used for solid skeleton.

• KIPS Transactions on Software and Data Engineering
• /
• 제10권11호
• /
• pp.491-500
• /
• 2021

In this study, we propose a method for detecting fall behavior using MS Kinect v2 RGBD Camera-based Human-Skeleton Keypoints and a 2-Stacked Bi-LSTM model. In previous studies, skeletal information was extracted from RGB images using a deep learning model such as OpenPose, and then recognition was performed using a recurrent neural network model such as LSTM and GRU. The proposed method receives skeletal information directly from the camera, extracts 2 time-series features of acceleration and distance, and then recognizes the fall behavior using the 2-Stacked Bi-LSTM model. The central joint was obtained for the major skeletons such as the shoulder, spine, and pelvis, and the movement acceleration and distance from the floor were proposed as features of the central joint. The extracted features were compared with models such as Stacked LSTM and Bi-LSTM, and improved detection performance compared to existing studies such as GRU and LSTM was demonstrated through experiments.

• Bulletin of the Korean Chemical Society
• /
• 제31권7호
• /
• pp.2039-2042
• /
• 2010

• Bulletin of the Korean Chemical Society
• /
• 제31권11호
• /
• pp.3441-3444
• /
• 2010

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권9호
• /
• pp.3924-3940
• /
• 2020

Dynamic hand gesture recognition(d-HGR) plays an important role in human-computer interaction(HCI) system. With the growth of hand-pose estimation as well as 3D depth sensors, depth, and the hand-skeleton dataset is proposed to bring much research in depth and 3D hand skeleton approaches. However, it is still a challenging problem due to the low resolution, higher complexity, and self-occlusion. In this paper, we propose a hand-shape feature extraction(HSFE) network to produce robust hand-shapes. We build a hand-shape model, and hand-skeleton based on LSTM to exploit the temporal information from hand-shape and motion changes. Fusion between two models brings the best accuracy in dynamic hand gesture (DHG) dataset.

• Proceedings of the KIEE Conference
• /
• 대한전기학회 2007년도 제38회 하계학술대회
• /
• pp.321-322
• /
• 2007

본 논문에서는 로봇과 인간의 인터액션을 위해 인간 몸의 실루엣 및 액티브 스켈레톤 추출 기법을 제안한다. 연속된 이미지 정보로 부터 얻어진 옷영역등의 정보에서 background subtraction를 이용한 adaptive fusion을 통해 추출된 인간 몸의 실루엣을 바탕으로 active contour와 가상 신체 모델인 skeleton model을 응용하여 작은 움직임에 보다 강한 active skeleton model을 이용하여 인간 몸의 특징 점 위치를 추출하는 방법을 한다.