• Title, Summary, Keyword: exact model matching

Search Result 27, Processing Time 0.032 seconds

3D Object Recognition and Accurate Pose Calculation Using a Neural Network (인공신경망을 이용한 삼차원 물체의 인식과 정확한 자세계산)

  • Park, Gang
    • Transactions of the Korean Society of Mechanical Engineers A
    • /
    • v.23 no.11
    • /
    • pp.1929-1939
    • /
    • 1999
  • This paper presents a neural network approach, which was named PRONET, to 3D object recognition and pose calculation. 3D objects are represented using a set of centroidal profile patterns that describe the boundary of the 2D views taken from evenly distributed view points. PRONET consists of the training stage and the execution stage. In the training stage, a three-layer feed-forward neural network is trained with the centroidal profile patterns using an error back-propagation method. In the execution stage, by matching a centroidal profile pattern of the given image with the best fitting centroidal profile pattern using the neural network, the identity and approximate orientation of the real object, such as a workpiece in arbitrary pose, are obtained. In the matching procedure, line-to-line correspondence between image features and 3D CAD features are also obtained. An iterative model posing method then calculates the more exact pose of the object based on initial orientation and correspondence.

Strip Adjustment of Airborne Laser Scanner Data Using Area-based Surface Matching

  • Lee, Dae Geon;Yoo, Eun Jin;Yom, Jae-Hong;Lee, Dong-Cheon
    • Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
    • /
    • v.32 no.6
    • /
    • pp.625-635
    • /
    • 2014
  • Multiple strips are required for large area mapping using ALS (Airborne Laser Scanner) system. LiDAR (Light Detection And Ranging) data collected from the ALS system has discrepancies between strips due to systematic errors of on-board laser scanner and GPS/INS, inaccurate processing of the system calibration as well as boresight misalignments. Such discrepancies deteriorate the overall geometric quality of the end products such as DEM (Digital Elevation Model), building models, and digital maps. Therefore, strip adjustment for minimizing discrepancies between overlapping strips is one of the most essential tasks to create seamless point cloud data. This study implemented area-based matching (ABM) to determine conjugate features for computing 3D transformation parameters. ABM is a well-known method and easily implemented for this purpose. It is obvious that the exact same LiDAR points do not exist in the overlapping strips. Therefore, the term "conjugate point" means that the location of occurring maximum similarity within the overlapping strips. Coordinates of the conjugate locations were determined with sub-pixel accuracy. The major drawbacks of the ABM are sensitive to scale change and rotation. However, there is almost no scale change and the rotation angles are quite small between adjacent strips to apply AMB. Experimental results from this study using both simulated and real datasets demonstrate validity of the proposed scheme.

Slewing maneuver control of flexible space structure using adaptive CGT

  • Shimada, Yuzo
    • 제어로봇시스템학회:학술대회논문집
    • /
    • /
    • pp.47-50
    • /
    • 1995
  • This paper concerns an adaptive control scheme which is an extension of the simplified adaptive control. Originally, the SAC approach was developed based on the command generator tracker (CGT) theory for perfect model tracking. An attractive point of the SAC is that a control input can be synthesized without any prior knowledge about plant structure. However, a feedforward dynamic compensator of the CGT is removed from the basic structure of the SAC. This deletion of the compensator makes perfect model tracking difficult against even a step input. In this paper, an adaptive control system is redesigned to achieve perfect model tracking for as long as possible by reviving the dynamic compensator of the CGT. The proposed method is applied to slewing control of a flexible space structure and compared to the SAC responses.

  • PDF

A Boundary Curve Extraction Method using Triangular Elements of a Lightweight Model (경량 모델의 삼각 요소망으로부터 경계 곡선 추출 방법)

  • Kwon, Ki-Youn
    • Korean Journal of Computational Design and Engineering
    • /
    • v.22 no.1
    • /
    • pp.28-36
    • /
    • 2017
  • Sharing of CAD data plays a key role in the PLM and a lightweight model is widely used for visualizing and sharing a large data. The lightweight model is mainly composed of triangular elements to minimize file size. There is no problem at all to visually confirm the shape based on these triangular elements but there is a limit to numerically calculate the exact position on the curve or surface. In this paper, a boundary curve generation method using triangular elements is proposed to increase the utilization of lightweight models. After matching connectivity of triangular elements, boundary element edges are extracted. Boundary curves are generated by connecting of these boundary element edges. This proposed method has been tested on several models to demonstrate the feasibility.

A Study on the Characteristics Improvement of Fluid Power Actuator Using Adaptive Control (적응제어를 이용한 유압 액츄에이터의 특성개선에 관한 연구)

  • 염만오;윤일로
    • Journal of the Korean Society for Precision Engineering
    • /
    • v.21 no.1
    • /
    • pp.124-132
    • /
    • 2004
  • A hydraulic system is difficult to keep the performance due to non-linearity, load pressure which changes according to working condition and system parameter variation, the requirement of control algorithm has been risen in order to satisfy them. An adaptive control is a control method which is suggested to achieve a control object though plant characteristics change. In spite of the case that plant characteristics and the degree of variation are difficult to grasp, adaptive control can keep the characteristics of closed-loop system regularly. In this study GMVAC(generalized minimum variance adaptive control) combined with output error feedback is proposed in order to solve problems of non-minimum phase, vibration and overshoot in initial response of the plant. The control performance according to the variation of characteristics of the plant is evaluated by changing the supply pressure only.

State Feedback Control for Model Matching Inclusion of Asynchronous Sequential Machines with Model Uncertainty (모델 불확실성을 가진 비동기 순차 머신의 모델 정합 포함을 위한 상태 피드백 제어)

  • Yang, Jung-Min;Park, Yong-Kuk
    • Journal of the Institute of Electronics Engineers of Korea SC
    • /
    • v.47 no.4
    • /
    • pp.7-14
    • /
    • 2010
  • Stable-state behaviors of asynchronous sequential machines represented as finite state machines can be corrected by feedback control schemes. In this paper, we propose a state feedback control scheme for input/state asynchronous machines with uncertain transitions. The considered asynchronous machine is deterministic, but its state transition function is partially known due to model uncertainty or inner logic errors. The control objective is to compensate the behavior of the closed-loop system so that it matches a sub-behavior of a prescribed model despite uncertain transitions. Furthermore, during the execution of corrective action, the controller reflects the exact knowledge of transitions into the next step, i.e., the range of the behavior of the closed-loop system can be enlarged through learning. The design procedure for the proposed controller is described in a case study.

VRML image overlay method for Robot's Self-Localization (VRML 영상오버레이기법을 이용한 로봇의 Self-Localization)

  • Sohn, Eun-Ho;Kwon, Bang-Hyun;Kim, Young-Chul;Chong, Kil-To
    • Proceedings of the KIEE Conference
    • /
    • /
    • pp.318-320
    • /
    • 2006
  • Inaccurate localization exposes a robot to many dangerous conditions. It could make a robot be moved to wrong direction or damaged by collision with surrounding obstacles. There are numerous approaches to self-localization, and there are different modalities as well (vision, laser range finders, ultrasonic sonars). Since sensor information is generally uncertain and contains noise, there are many researches to reduce the noise. But, the correctness is limited because most researches are based on statistical approach. The goal of our research is to measure more exact robot location by matching between built VRML 3D model and real vision image. To determine the position of mobile robot, landmark-localitzation technique has been applied. Landmarks are any detectable structure in the physical environment. Some use vertical lines, others use specially designed markers, In this paper, specially designed markers are used as landmarks. Given known focal length and a single image of three landmarks it is possible to compute the angular separation between the lines of sight of the landmarks. The image-processing and neural network pattern matching techniques are employed to recognize landmarks placed in a robot working environment. After self-localization, the 2D scene of the vision is overlaid with the VRML scene.

  • PDF

Self-localization of a Mobile Robot for Decreasing the Error and VRML Image Overlay (오차 감소를 위한 이동로봇 Self-Localization과 VRML 영상오버레이 기법)

  • Kwon Bang-Hyun;Shon Eun-Ho;Kim Young-Chul;Chong Kil-To
    • Journal of Institute of Control, Robotics and Systems
    • /
    • v.12 no.4
    • /
    • pp.389-394
    • /
    • 2006
  • Inaccurate localization exposes a robot to many dangerous conditions. It could make a robot be moved to wrong direction or damaged by collision with surrounding obstacles. There are numerous approaches to self-localization, and there are different modalities as well (vision, laser range finders, ultrasonic sonars). Since sensor information is generally uncertain and contains noise, there are many researches to reduce the noise. But, the correctness is limited because most researches are based on statistical approach. The goal of our research is to measure more exact robot location by matching between built VRML 3D model and real vision image. To determine the position of mobile robot, landmark-localization technique has been applied. Landmarks are any detectable structure in the physical environment. Some use vertical lines, others use specially designed markers, In this paper, specially designed markers are used as landmarks. Given known focal length and a single image of three landmarks it is possible to compute the angular separation between the lines of sight of the landmarks. The image-processing and neural network pattern matching techniques are employed to recognize landmarks placed in a robot working environment. After self-localization, the 2D scene of the vision is overlaid with the VRML scene.

A Self-Consistent Semi-Analytical Model for AlGaAs/InGaAs PMHEMTs

  • Abdel Aziz, M.;El-Banna, M.;El-Sayed, M.
    • JSTS:Journal of Semiconductor Technology and Science
    • /
    • v.2 no.1
    • /
    • pp.59-69
    • /
    • 2002
  • A semi-analytical model based on exact numerical analysis of the 2DEG channel in pseudo-morphic HEMT (PMHEMT) is presented. The exactness of the model stems from solving both Schrodinger's wave equation and Poisson's equation simultaneously and self-consistently. The analytical modeling of the device terminal characteristics in relation to the charge control model has allowed a best fit with the geometrical and structural parameters of the device. The numerically obtained data for the charge control of the channel are best fitted to analytical expressions which render the problem analytical. The obtained good agreement between experimental and modeled current/voltage characteristics and small signal parameters has confirmed the validity of the model over a wide range of biasing voltages. The model has been used to compare both the performance and characteristics of a PMHEMT with a competetive HEMT. The comparison between the two devices has been made in terms of 2DEG density, transfer characteristics, transconductance, gate capacitance and unity current gain cut-off frequency. The results show that PMHEMT outperforms the conventional HEMT in all considered parameters.

VS3-NET: Neural variational inference model for machine-reading comprehension

  • Park, Cheoneum;Lee, Changki;Song, Heejun
    • ETRI Journal
    • /
    • v.41 no.6
    • /
    • pp.771-781
    • /
    • 2019
  • We propose the VS3-NET model to solve the task of question answering questions with machine-reading comprehension that searches for an appropriate answer in a given context. VS3-NET is a model that trains latent variables for each question using variational inferences based on a model of a simple recurrent unit-based sentences and self-matching networks. The types of questions vary, and the answers depend on the type of question. To perform efficient inference and learning, we introduce neural question-type models to approximate the prior and posterior distributions of the latent variables, and we use these approximated distributions to optimize a reparameterized variational lower bound. The context given in machine-reading comprehension usually comprises several sentences, leading to performance degradation caused by context length. Therefore, we model a hierarchical structure using sentence encoding, in which as the context becomes longer, the performance degrades. Experimental results show that the proposed VS3-NET model has an exact-match score of 76.8% and an F1 score of 84.5% on the SQuAD test set.