• 제목/요약/키워드: fast-tracking

검색결과 545건 처리시간 0.026초

ASIC을 이용한 자동영상 추적기 구현 (Realization of automatic video tracker using ASIC)

  • 강재열;윤상로
    • 한국통신학회논문지
    • /
    • 제21권8호
    • /
    • pp.1885-1896
    • /
    • 1996
  • This paper describes the implementation of the AVT(Automatic video Tracker) using ASIC. The basic tracking algorithm is based on the spatio-temporal gradient method, and adaptive window sizing, track state decision algorithm were also realized. Newly developed ASIC performs recursive image filtering, extraction of spatio-temporal gradient/gradient functions of image in field rate. Using the FPGA/ASIC, the tracker was simply realized in one board type which can be easily applied to various image system. We conformed ASIC operation by computer simulation and tested the system in real tracking situations. From the result, the system can track the moving target which has a velocity of 2-3 pixel/field and a size of varying from 2 to 128 pixes. Also fast refresh rateof motion estimation(60Hz) improves the characteristics of servoing system which forms feedback loop with the tracker.

  • PDF

고속 열차용 대형 알루미늄 부품의 GAP 대응 로봇 자동화 용접 기술 (Technologies for Robotized Welding of Big Aluminium Structures with Tolerances for High Speed Trains)

  • 이상철
    • Journal of Welding and Joining
    • /
    • 제31권1호
    • /
    • pp.33-37
    • /
    • 2013
  • Robotized MIG welding of large aluminium components for high speed trains is state-of-the-art. The implementation of online laser cameras enables seam tracking and adoptive modification of welding parameters. A constant fill is achieved regardless of the gap tolerances. Friction Stir Welding has been introduced to the market as a reliable and fast joining technology. The advantages of high welding speeds and the elimination of arc light, fumes and liquefaction in the welding spot lead to economical realisation of heavy-duty gantry systems. FSW robots offer a high flexibility with regard to welding of curved parts, and can be equipped with laser cameras for exact joint tracking.

Object Detection by Gaussian Mixture Model and Shape Adaptive Bidirectional Block Matching Algorithm

  • 박구만
    • 방송공학회논문지
    • /
    • 제13권5호
    • /
    • pp.681-684
    • /
    • 2008
  • We proposed a method to improve moving object detection capability of Gaussian Mixture Model by suggesting shape adaptive bidirectional block matching algorithm. This method achieves more accurate detection and tracking performance at various motion types such as slow, fast, and bimodal motions than that of Gaussian Mixture Model. Experimental results showed that the proposed method outperformed the conventional methods.

관상동맥 영상에서의 혈관 경계 검출 (Detection of Vessel Contours in Coronary Arteriograms)

  • 엄경식;정재호
    • 대한의용생체공학회:의공학회지
    • /
    • 제16권4호
    • /
    • pp.439-446
    • /
    • 1995
  • 본 논문은 관상동맥 영상에서 혈관 경계 검출에 대한 알고리듬을 제안한다. 제안된 알고리듬은 정합필터링과 적응추적에 기반한 방법이다. 제안된 알고리듬은 분기부분 문제와 직경이 작은 혈관 부분의 문제점을 해결하였다. 또한 빠른 처리기간과 잡음에 강인한 성능을 가지고 있다.

  • PDF

Adaptive Tracking Control of Two-Wheeled Welding Mobile Robot - Dynamic Model Approach -

  • ;;서진호;김상봉
    • 대한전기학회:학술대회논문집
    • /
    • 대한전기학회 2002년도 하계학술대회 논문집 D
    • /
    • pp.2424-2426
    • /
    • 2002
  • This paper proposes an adaptive control method of partially known system and shows its application result to control for two-wheeled WMR. The controlled system is stable in the sense of Lyapunov stability. To design a tracking controller for welding path reference, an error configuration is defined and the controller is designed to drive the error to zero as fast as desired. Moments of inertia of system are considered to be unknown system parameters. Their values are estimated using update laws in adaptive control scheme. The effectiveness of the proposed controller is shown through simulation results.

  • PDF

Facial Feature Tracking and Head Orientation-based Gaze Tracking

  • Ko, Jong-Gook;Kim, Kyungnam;Park, Seung-Ho;Kim, Jin-Young;Kim, Ki-Jung;Kim, Jung-Nyo
    • 대한전자공학회:학술대회논문집
    • /
    • 대한전자공학회 2000년도 ITC-CSCC -1
    • /
    • pp.11-14
    • /
    • 2000
  • In this paper, we propose a fast and practical head pose estimation scheme fur eye-head controlled human computer interface with non-constrained background. The method we propose uses complete graph matching from thresholded images and the two blocks showing the greatest similarity are selected as eyes, we also locate mouth and nostrils in turn using the eye location information and size information. The average computing time of the image(360*240) is within 0.2(sec) and we employ template matching method using angles between facial features for head pose estimation. It has been tested on several sequential facial images with different illuminating conditions and varied head poses, It returned quite a satisfactory performance in both speed and accuracy.

  • PDF

An Optimal Maximum Power Point Tracking Algorithm for Wind Energy System in Microgrid

  • Nguyen, Thanh-Van;Kim, Kyeong-Hwa
    • 전력전자학회:학술대회논문집
    • /
    • 전력전자학회 2018년도 전력전자학술대회
    • /
    • pp.382-383
    • /
    • 2018
  • To increase the efficiency of a wind energy conversion system (WECS), the maximum power point tracking (MPPT) algorithm is usually employed. This paper proposes an optimal MPPT algorithm which tracks a sudden wind speed change condition fast. The proposed method can be implemented without the prior information on the wind turbine parameters, generator parameters, air density or wind speed. By investigating the directions of changes of the mechanical output power in wind turbine and rotor speed of the generator, the proposed MPPT algorithm is able to determine an optimal speed to achieve the maximum power point. Then, this optimal speed is set to the reference of the speed control loop. As a result, the proposed MPPT algorithm forces the system to operate at the maximum power point by using a three-phase converter. The simulation results based on the PSIM are given to prove the effectiveness of the proposed method.

  • PDF

학습을 이용한 로봇 머니퓰레이터용 지능제어 (Intelligent Control of Robot Manipulators by Learning)

  • 이동훈;국태웅;정재욱
    • 제어로봇시스템학회논문지
    • /
    • 제11권4호
    • /
    • pp.330-336
    • /
    • 2005
  • An intelligent control method is proposed for control of rigid robot manipulators which achieves exponential tracking of repetitive robot trajectory under uncertain operating conditions such as parameter uncertainty and unknown deterministic disturbance. In the learning controller, exponentially stable learning algorithms are combined with stabilizing computed error feedforward and feedback inputs. It is shown that all the error signals in the learning system are bounded and the repetitive robot motion converges to the desired one exponentially fast with guaranteed convergence rate. An engineering workstation based control system is built to verify the effectiveness of the proposed control scheme.

환자 감시장치를 위한 눈의 개폐(開閉) 상태 인식에 관한 연구 (A Study on the Recognition of the State of Eye for the Patient Monitoring System)

  • 김성환;한영환;박승환;장영건;홍승홍
    • 전자공학회논문지B
    • /
    • 제32B권11호
    • /
    • pp.1455-1463
    • /
    • 1995
  • A new automatic tracking & recognition algorithm which decides the opening & the closing states of subject's eye and isn't affected by the subject's background is proposed. And it was tested in circumstances in which subject's background was not restricted using the developed system, ATRS(Automatic Tracking & Recognition System). The significant characteristic of the ATRS is new movement detection of object that is a body in motion with accelated velocity and it doesn't need any extra hardware except a formal CCD camera and an image grabber but it works so well and so fast. The ATRS would be particularly well suited to a way of communications of patients in a hospital, who can not communicate otherwise.

  • PDF

지능기법을 이용한 영상분활 및 물체추적에 관한 연구 (A Study on Image Segmentation and Tracking based on Intelligent Method)

  • 이민중;황기현;김종윤;진태석
    • 대한전자공학회:학술대회논문집
    • /
    • 대한전자공학회 2007년도 하계종합학술대회 논문집
    • /
    • pp.311-312
    • /
    • 2007
  • This dissertation proposes a global search and a local search method to track the object in real-time. The global search recognizes a target object among the candidate objects through the entire image search, and the local search recognizes and track only the target object through the block search. This dissertation uses the object color and feature information to achieve fast object recognition. Finally we conducted an experiment for the object tracking system based on a pan/tilt structure.

  • PDF