• 제목/요약/키워드: skeleton model

검색결과 179건 처리시간 0.027초

Experimental hysteretic behavior of in-plane loaded reinforced grouted multi-ribbed aerated concrete blocks masonry walls

  • Li, Sheng-Cai;Dong, Jian-Xi;Li, Li-Feng
    • Structural Engineering and Mechanics
    • /
    • 제41권1호
    • /
    • pp.95-112
    • /
    • 2012
  • In order to analyze the experimental hysteretic behavior of the in-plane loaded reinforced grouted multi-ribbed aerated concrete blocks masonry walls (RGMACBMW), we have carried out the pseudo static testing on the six specimens of RGMACBMW. Based on the test results and shear failure characteristics, the shear force hysteretic curves and displacement envelope curves of the models were obtained and discussed. On the basis of the hysteretic curves a general skeleton curve of the shear force and displacement was formed. The restoring model was adopted to analyze the seismic behavior and earthquake response of RGMACBMW. The deformation capacity of the specimens was discussed, and the formulas for calculating the lateral stiffness of the walls at different loading stages were proposed as well. The average lateral displacement ductility factor of RGMACBMW calculated based on the test results was 3.16. This value illustrates that if the walls are appropriately designed, it can fully meet the seismic requirement of the structures. The quadri-linear restoring models of the walls degradation by the test results accurately reflect the hysteretic behaviors and skeleton curves of the masonry walls. The restoring model can be applied to the RGMACBMW structure in earthquake response analysis.

Triangulation Based Skeletonization and Trajectory Recovery for Handwritten Character Patterns

  • Phan, Dung;Na, In-Seop;Kim, Soo-Hyung;Lee, Guee-Sang;Yang, Hyung-Jeong
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • 제9권1호
    • /
    • pp.358-377
    • /
    • 2015
  • In this paper, we propose a novel approach for trajectory recovery. Our system uses a triangulation procedure for skeletonization and graph theory to extract the trajectory. Skeletonization extracts the polyline skeleton according to the polygonal contours of the handwritten characters, and as a result, the junction becomes clear and the characters that are touching each other are separated. The approach for the trajectory recovery is based on graph theory to find the optimal path in the graph that has the best representation of the trajectory. An undirected graph model consisting of one or more strokes is constructed from a polyline skeleton. By using the polyline skeleton, our approach accelerates the process to search for an optimal path. In order to evaluate the performance, we built our own dataset, which includes testing and ground-truth. The dataset consist of thousands of handwritten characters and word images, which are extracted from five handwritten documents. To show the relative advantage of our skeletonization method, we first compare the results against those from Zhang-Suen, a state-of-the-art skeletonization method. For the trajectory recovery, we conduct a comparison using the Root Means Square Error (RMSE) and Dynamic Time Warping (DTW) in order to measure the error between the ground truth and the real output. The comparison reveals that our approach has better performance for both the skeletonization stage and the trajectory recovery stage. Moreover, the processing time comparison proves that our system is faster than the existing systems.

스켈레톤 벡터 정보와 RNN 학습을 이용한 행동인식 알고리즘 (Using Skeleton Vector Information and RNN Learning Behavior Recognition Algorithm)

  • 김미경;차의영
    • 방송공학회논문지
    • /
    • 제23권5호
    • /
    • pp.598-605
    • /
    • 2018
  • 행동 인식은 데이터를 통해 인간의 행동을 인식하는 기술로서 비디오 감시 시스템을 통한 위험 행동과 같은 어플리케이션에 활용되어 질 수 있다. 기존의 행동 인식 알고리즘은 2차원 카메라를 통한 영상이나 다중모드 센서, 멀티 뷰와 같은 장비를 이용한 방법을 사용하거나 3D 장비를 이용하여 이루어져 왔다. 2차원 데이터를 사용한 경우 3차원 공간의 행위 인식에서는 가려짐과 같은 현상으로 낮은 인식율을 보였고 다른 방법은 복잡한 장비의 구성이나 고가의 추가적인 장비로 인한 어려움이 많았다. 본 논문은 RGB와 Depth 정보만을 이용하여 추가적인 장비 없이 CCTV 영상만으로 인간의 행동을 인식하는 방법을 제안한다. 먼저 RGB 영상에서 스켈레톤 추출 알고리즘을 적용하여 관절과 신체부위의 포인트를 추출한다. 이를 식을 적용하여 변위 벡터와 관계 벡터를 포함한 벡터로 변형한 후 RNN 모델을 통하여 연속된 벡터 데이터를 학습한다. 학습된 모델을 다양한 데이터 세트에 적용하여 행동 인식 정확도를 확인한 결과 2차원 정보만으로 3차원 정보를 이용한 기존의 알고리즘과 유사한 성능을 입증할 수 있었다.

장수명화와 시공성을 고려한 새로운 공동주택 모델의 초기 비용절감 가능성 연구 - 구조체와 외장전환 사례분석을 중심으로 - (A Study on the Possibility of Initial Cost Saving in the New Housing Model Considering Long-life and Constructability - Focused on the Case Analysis with Converting Skeleton and Cladding to New Systems -)

  • 김수암;신성은;정준수;손영진
    • 한국주거학회논문집
    • /
    • 제23권6호
    • /
    • pp.49-59
    • /
    • 2012
  • This study suggested a new model in consideration of long life and constructability of apartment house suggested in the former part. New model suggested the possibility of cost saving based on the idea that people trend to reject because of the recognition that the new model would cost a lot of expense which work as the barrier for the expansion and distribution at the local market so as to prepare the ground for its activation. The Study was aimed at verifying the possibility of cost saving through comparing it with the existing standard apartment house system centered on the skeleton and cladding system among the new structural design models suggested in the former part. Assuming that these existing standard both models should be changed structural design into new model system, the quantity volume, cost and construction period along with the alteration of finished materials between two models were compared altogether. Simultaneously BIM library was built for easy taking-off bill of quantity and consideration of working methodology for construction working cycle, which was translated into construction cost so as to derive the cost of the two subject systems to be counted. Through the analysis, it was concluded that new model would secure variability in the future and constructability along with shortening the construction period (29%) and achieve cost saving (13%) of construction against the those of existing model.

골격 특징 및 색상 유사도를 이용한 가축 도난 감지 시스템 (Livestock Theft Detection System Using Skeleton Feature and Color Similarity)

  • 김준형;주영훈
    • 전기학회논문지
    • /
    • 제67권4호
    • /
    • pp.586-594
    • /
    • 2018
  • In this paper, we propose a livestock theft detection system through moving object classification and tracking method. To do this, first, we extract moving objects using GMM(Gaussian Mixture Model) and RGB background modeling method. Second, it utilizes a morphology technique to remove shadows and noise, and recognizes moving objects through labeling. Third, the recognized moving objects are classified into human and livestock using skeletal features and color similarity judgment. Fourth, for the classified moving objects, CAM (Continuously Adaptive Meanshift) Shift and Kalman Filter are used to perform tracking and overlapping judgment, and risk is judged to generate a notification. Finally, several experiments demonstrate the feasibility and applicability of the proposed method.

지능형 로봇 시스템에서 하이브리드 실루엣 추출 방법을 이용한 인간의 몸 추출 (Extraction of Human Body Using Hybrid Silhouette Extraction Method in Intelligent Robot System)

  • 김문환;주영훈;박진배;조영조;지수영;김혜진
    • 한국지능시스템학회:학술대회논문집
    • /
    • 한국퍼지및지능시스템학회 2005년도 추계학술대회 학술발표 논문집 제15권 제2호
    • /
    • pp.257-260
    • /
    • 2005
  • This paper discusses a human body extraction method for mobile robot system. The skeleton features are used to analyze human motion and pose estimation. The intelligent robot system requires more robust silhouette extraction method because it has internal vibration and low resolution. The new hybrid silhouette extraction method is proposed to overcome this constrained environment. Finally, the experimental results show the superiority of the Proposed method.

  • PDF

Road Traffic Control Gesture Recognition using Depth Images

  • Le, Quoc Khanh;Pham, Chinh Huu;Le, Thanh Ha
    • IEIE Transactions on Smart Processing and Computing
    • /
    • 제1권1호
    • /
    • pp.1-7
    • /
    • 2012
  • This paper presents a system used to automatically recognize the road traffic control gestures of police officers. In this approach,the control gestures of traffic police officers are captured in the form of depth images.A human skeleton is then constructed using a kinematic model. The feature vector describing a traffic control gesture is built from the relative angles found amongst the joints of the constructed human skeleton. We utilize Support Vector Machines (SVMs) to perform the gesture recognition. Experiments show that our proposed method is robust and efficient and is suitable for real-time application. We also present a testbed system based on the SVMs trained data for real-time traffic gesture recognition.

  • PDF

3D 설계 프로세스 정립을 통한 복잡한 시스템 설계에서의 공용부품 사용 극대화 (Maximizing Use of Common Parts in Complex System Design through Organizing 3D Design Process)

  • 최영운;박강
    • 한국CDE학회논문집
    • /
    • 제12권3호
    • /
    • pp.209-219
    • /
    • 2007
  • Designing a complex system such as an LCD developing system becomes inefficient when many designers are involved and create their own parts even though they can be used repeatedly in other sections. Thus, this paper proposes a new design process that can maximize the number of common parts in complex system design by organizing the 3D design process. The proposed design process consists of 5 stages: analysis of design intention, definition of initial product structure, definition of skeleton model, sharing design intention with all assembles, control of correlation between components. The proposed design process can maximize common parts in design process, which results in shorter lead time, less production cost, and greater economic benefits.

횡하중을 받는 철골구조물에서 합성보의 강성과 강도 (Stiffness and Strength of Composite Beams in Steel Building Structures Under Lateral Loading)

  • 이승준
    • 전산구조공학
    • /
    • 제2권4호
    • /
    • pp.79-88
    • /
    • 1989
  • 철골 건축 구조물이 횡하중을 받을 때 합성보의 거동에 대한 연구가 수행되었다. 실험으로부터 얻어진 결과와 수치해석에 의한 결과를 이용하여 합성보의 강성과 연결부에서의 강도를 위한 수학적 모델이 연결부의 상세를 고려하여 개발되었다. 또한 캔티레버 합성보의 skeleton 곡선과 hysteresis 곡선을 위한 해석모델이 제시되었다. 탄성보와 부재내의 비탄성 변형이 응집된 양 단부스프링으로 구성된 단일요소모델에 의한 합성보 요소가 컴퓨터 프로그램, DRAIN-2D에 포함되었으며, 해석결과는 실험결과의 비교를 통해 검정되었다.

  • PDF

Use of infinite elements in simulating liquefaction phenomenon using coupled approach

  • Kumari, Sunita;Sawant, V.A.
    • Coupled systems mechanics
    • /
    • 제2권4호
    • /
    • pp.375-387
    • /
    • 2013
  • Soils consist of an assemblage of particles with different sizes and shapes which form a skeleton whose voids are filled with water and air. Hence, soil behaviour must be analyzed by incorporating the effects of the transient flow of the pore-fluid through the voids, and therefore requires a two-phase continuum formulation for saturated porous media. The present paper presents briefly the Biot's basic theory of dynamics of saturated porous media with u-P formulation to determine the responses of pore fluid and soil skeleton during cyclic loading. Kelvin elements are attached to transmitting boundary. The Pastor-Zienkiewicz-Chan model has been used to describe the inelastic behavior of soils under isotropic cyclic loadings. Newmark-Beta method is employed to discretize the time domain. The response of fluid-saturated porous media which are subjected to time dependent loads has been simulated numerically to predict the liquefaction potential of a semi-infinite saturated sandy layer using finite-infinite elements. A settlement of 17.1 cm is observed at top surface. It is also noticed that liquefaction occurs at shallow depth. The mathematical advantage of the coupled finite element analysis is that the excess pore pressure and displacement can be evaluated simultaneously without using any empirical relationship.