• 제목/요약/키워드: object relation tracking

검색결과 15건 처리시간 0.023초

Augmented Reality of Robust Tracking with Realistic Illumination

  • Kim, Young-Baek;Lee, Hong-Chang;Rhee, Sang-Yong
    • International Journal of Fuzzy Logic and Intelligent Systems
    • /
    • 제10권3호
    • /
    • pp.178-183
    • /
    • 2010
  • In this study we augmented a virtual object to an image of a flexible surface such as a paper, which is acquired from a web camera. To get more presence feeling, we consider realistic illumination on augmenting. To get the geometric relation between the camera and the flexible surface, we use markers that are printed on the surface. Using marker information in prior, three dimensional coordinates of the surface can be calculated. After the marker is removed from the input image, we attach a two dimensional texture and shadow to the flexible surface by considering realistic illumination.

Anomalous Event Detection in Traffic Video Based on Sequential Temporal Patterns of Spatial Interval Events

  • Ashok Kumar, P.M.;Vaidehi, V.
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • 제9권1호
    • /
    • pp.169-189
    • /
    • 2015
  • Detection of anomalous events from video streams is a challenging problem in many video surveillance applications. One such application that has received significant attention from the computer vision community is traffic video surveillance. In this paper, a Lossy Count based Sequential Temporal Pattern mining approach (LC-STP) is proposed for detecting spatio-temporal abnormal events (such as a traffic violation at junction) from sequences of video streams. The proposed approach relies mainly on spatial abstractions of each object, mining frequent temporal patterns in a sequence of video frames to form a regular temporal pattern. In order to detect each object in every frame, the input video is first pre-processed by applying Gaussian Mixture Models. After the detection of foreground objects, the tracking is carried out using block motion estimation by the three-step search method. The primitive events of the object are represented by assigning spatial and temporal symbols corresponding to their location and time information. These primitive events are analyzed to form a temporal pattern in a sequence of video frames, representing temporal relation between various object's primitive events. This is repeated for each window of sequences, and the support for temporal sequence is obtained based on LC-STP to discover regular patterns of normal events. Events deviating from these patterns are identified as anomalies. Unlike the traditional frequent item set mining methods, the proposed method generates maximal frequent patterns without candidate generation. Furthermore, experimental results show that the proposed method performs well and can detect video anomalies in real traffic video data.

행동 탐지 기반의 효율적인 객체 선택 알고리듬 (Efficient Object Selection Algorithm by Detection of Human Activity)

  • 박왕배;서융호;두경수;최종수
    • 대한전자공학회논문지SP
    • /
    • 제47권3호
    • /
    • pp.61-69
    • /
    • 2010
  • 본 논문에서는 행동 탐지 기반으로 사람의 지시행위를 인식하여 지시방향의 객체를 선택하고 이를 추적하는 시스템을 제안한다. 일반적으로 사람은 무엇인가를 지시할 경우, 얼굴 방향을 목표물에 두게 된다. 따라서 얼굴과 손끝을 연결한 직선을 지시방향이라 간주하고, 지시된 객체를 선택한다. 제안된 알고리듬에서는 카메라를 통해 입력된 영상으로부터 움직임 영역을 검출하기 위해 배경 차분을 사용하여 실시간으로 관심 객체의 움직임을 추출한다. 보행 여부의 판단은 주성분(PCA) 분석과 객체의 움직임 변위로 결정되며, 이 때 사람이 정지 상태면, 머리를 기준으로 손에 이르는 벡터 관계를 계산하여 사용자의 지시방향을 최종적으로 결정한다. 실험결과를 통하여 다시점 카메라를 이용한 다각도의 영상에서 사람의 지시 방향을 정확하게 추정해 냄으로서 제안된 알고리즘의 유효성을 검증하였다.

영상기반 물체추적에 의한 소형 쿼드로터의 자세추정 성능향상 (Performance Enhancement of the Attitude Estimation using Small Quadrotor by Vision-based Marker Tracking)

  • 강석영;채종완;진태석
    • 한국지능시스템학회논문지
    • /
    • 제25권5호
    • /
    • pp.444-450
    • /
    • 2015
  • 소형 및 저가형 CCD 카메라의 성능은 소형 쿼드콥터의 정밀 추적기능을 구현하는데 있어서 충분한 성능을 갖추고 있지 못하는데 본 연구에서는 덜 정확한 GPS 보다 CCD 카메라를 이용한 보행자와 같은 대상물의 상공에서 강건한 호버링을 유지시키기 위한 방법을 제시하였다. 기존의 연구 대상이었던 고정된 물체가 아닌 보행자를 타깃으로 이용한 UAV의 절대 위치를 추정하는 방법을 제시하였다. 이는 UAV가 산악이나 사람들이 붐비는 공공지역에서 이동할 때 UAV의 절대위치를 인식할 수 있는 방법이 없을 경우 UAV 주변에서 움직이는 물체의 정보를 활용하여 UAV의 절대위치를 보정하는 방법으로 매우 유용하다. 연구를 위해서 보행자의 위치를 알고 있는 것으로 가정하나 실제적인 상황 속에서는 영상매칭을 통하여 그 정보를 수신하는 것으로 해석한다. 본 연구를 위하여 UAV의 위치 추정 불확실성을 정량적으로 나타내었으며, 좌표계 변환을 통한 영상기반의 기하학적 구속 식을 유도하여, 칼만 필터를 적용하여 로봇의 위치를 보정하여 위치 추정 불확실성을 줄일 수 있음을 보였다.

광픽업 미세구동부의 최적설계 (Optimal Design of a Fine Actuator for Optical Pick-up)

  • 이문구;권대갑
    • 대한기계학회논문집A
    • /
    • 제21권5호
    • /
    • pp.819-827
    • /
    • 1997
  • In this paper, a new modeling of a fine actuator for an optical pick-up has been proposed and multiobjective optimization of the actuator has been performed. The fine actuator is constituted of the bobbin which is supported by wire suspension, the coils which wind around the bobbin, and the magnets which cause the magnetic flux. If current flows in the coils, magnetic force is so produced as to be balanced with spring force of wire, so the bobbin is pisitioned. In this model the transfer function from input voltage to output displacementof bobbin has been obtained so that we can describe this integrated system with electromagnetic and mechanical parts. Wire suspension is regarded as a continuous Euler beam, damper as distributed viscous damping, and bobbin as a rigid body which can move up- and down- ward motion only. According to the model, the high frequency dynamic characteristics of the fine actuator can be known and the effect of damping can be investigated while the conventional second order model cannot. In multiobjective optimization, two objective functions have been chosen to maximize the fundamental frequency and the sensitivity with respect to the input voltage of the actuator so that Pareto's optimal solutions have been obtained using .epsilon.-constraint method. These objective functions will satisfy the trends which will enhance the access speed and reduce the tracking error in the optical pick-up technology of next generation. In the result of optimization, we obtain the designs of the optical pick-up fine actuator which has high speed, high sensitivity and low resonant peak. Furthermore, we offer the relation between two object functions so that the designer can make easy choice.