• 제목/요약/키워드: Object recognition system

검색결과 717건 처리시간 0.026초

2차원 물체 인식을 위한 입체 시각 포인트의 추출 (The Detection of the Stereo Viewing Points for 3D Object Recognition)

  • 서춘원;원영진
    • 대한전자공학회:학술대회논문집
    • /
    • 대한전자공학회 2007년도 하계종합학술대회 논문집
    • /
    • pp.451-452
    • /
    • 2007
  • It is need to find a new feature for the more statable recognition system. Now, we need more features like a human eyes. Therefore, this paper proposed a new feature with the stereo camera. In this paper, the each different features from the left and right input image will be extracted by stereo vision system, and will be good for the 3-D recognition.

  • PDF

긴급 상황 시나리오 해석을 위한 독립 객체의 규칙 기반 및 확률적 이벤트 인식 (Rule-based and Probabilistic Event Recognition of Independent Objects for Interpretation of Emergency Scenarios)

  • 이준철;최창규
    • 한국멀티미디어학회논문지
    • /
    • 제11권3호
    • /
    • pp.301-314
    • /
    • 2008
  • 기존의 이벤트 인식은 한정된 규칙 기반으로 이루어졌고, 시나리오 해석은 확률 자료의 크기로 많은 학습 시간이 필요했다. 본 논문에서는 객체로부터 특징 벡터를 추출하고 각 객체의 행동 양식을 분석하여 현재 객체의 이벤트를 인식하는 방법과 확률 모델을 기반으로 본 논문에서 정의한 긴급 상황 시나리오를 해석할 수 있는 방법을 제안한다. 독립 객체의 이벤트 규칙은 주-이벤트, 움직임-이벤트, 상호-이벤트, 그리고 'FALL DOWN' 이벤트로 구성되며, 객체의 특징 벡터와 베이지안 네트워크에 의해 학습된 분할 움직임 방향 벡터(SMOV)를 통해 정의된다. 긴급 상황 시나리오는 현재 이벤트의 상태와 사후 확률에 의해 분석된다. 본 논문에서는 기존 방법에 비해 다양한 이벤트를 정의하였고 이벤트 간의 독립성을 높여 확장성이 용이하도록 하였다. 그리고 객체 추적만을 통해 얻을 수 없는 의미론적 정보를 규칙과 확률을 기반으로 획득할 수 있었다.

  • PDF

스테레오 비전 기반의 이동객체용 실시간 환경 인식 시스템 (Investigation on the Real-Time Environment Recognition System Based on Stereo Vision for Moving Object)

  • 이충희;임영철;권순;이종훈
    • 대한임베디드공학회논문지
    • /
    • 제3권3호
    • /
    • pp.143-150
    • /
    • 2008
  • In this paper, we investigate a real-time environment recognition system based on stereo vision for moving object. This system consists of stereo matching, obstacle detection and distance estimation. In stereo matching part, depth maps can be obtained real road images captured adjustable baseline stereo vision system using belief propagation(BP) algorithm. In detection part, various obstacles are detected using only depth map in case of both v-disparity and column detection method under the real road environment. Finally in estimation part, asymmetric parabola fitting with NCC method improves estimation of obstacle detection. This stereo vision system can be applied to many applications such as unmanned vehicle and robot.

  • PDF

효율적인 인덱싱 기법을 이용한 3차원 물체 인식:Part I-Bayesian 인덱싱 (Three-dimensional object recognition using efficient indexing:Part I-bayesian indexing)

  • 이준호
    • 전자공학회논문지C
    • /
    • 제34C권10호
    • /
    • pp.67-75
    • /
    • 1997
  • A design for a system to perform rapid recognition of three dimensional objects is presented, focusing on efficient indexing. In order to retrieve the best matched models without exploring all possible object matches, we have employed a bayesian framework. A decision-theoretic measure of the discriminatory power of a feature for a model object is defined in terms of posterior probability. Detectability of a featrue defined as a function of the feature itselt, viewpoint, sensor charcteristics, nd the feature detection algorithm(s) is also considered in the computation of discribminatory power. In order to speed up the indexing or selection of correct objects, we generate and verify the object hypotheses for rfeatures detected in a scene in the order of the discriminatory power of these features for model objects.

  • PDF

The Development of real-time system for taking the dimensions of objects with arbitray shape

  • Chung, Yun-Su;Won, Jong-Un;Kim, Jin-Seok
    • 대한전자공학회:학술대회논문집
    • /
    • 대한전자공학회 2002년도 ITC-CSCC -3
    • /
    • pp.1523-1526
    • /
    • 2002
  • In this paper, we propose a method fur measuring the dimensions of an arbitrary object using geometric relationship between a perspective projection image and a rectangular parallelepiped model. For recognizing the vertexes of the rectangular parallelepiped surrounding an arbitrary object, the method adopts a strategy that derives the equations for vertex recognition from the geometrical relationships for image formation between 2D image and the rectangular parallelepiped model. extracts from 2D image with vertical view features (or junctions) of minimum quadrangle circumscribing an arbitrary shape object, and then recognizes vertexes from the features with the equations. Finally, the dimensions of the object are calculated from these results of vertex recognition. By the experimental results, it is demonstrated that this method is very effective to recognize the vertexes of the arbitrary objects.

  • PDF

화재방호 설비 설계 자동화를 위한 선행연구 및 기술 분석 (Literature Review and Current Trends of Automated Design for Fire Protection Facilities)

  • 홍성협;최두찬;이광호
    • 토지주택연구
    • /
    • 제11권4호
    • /
    • pp.99-104
    • /
    • 2020
  • This paper presents the recent research developments identified through a review of literature on the application of artificial intelligence in developing automated designs of fire protection facilities. The literature review covered research related to image recognition and applicable neural networks. Firstly, it was found that convolutional neural network (CNN) may be applied to the development of automating the design of fire protection facilities. It requires a high level of object detection accuracy necessitating the classification of each object making up the image. Secondly, to ensure accurate object detection and building information, the data need to be pulled from architectural drawings. Thirdly, by applying image recognition and classification, this can be done by extracting wall and surface information using dimension lines and pixels. All combined, the current review of literature strongly indicates that it is possible to develop automated designs for fire protection utilizing artificial intelligence.

이중카메라를 이용한 실시간 도난방지 시스템의 구현 (Implementation of Real-Time Security System by using Dual Camera)

  • 이광형;정용훈
    • 한국산학기술학회논문지
    • /
    • 제10권1호
    • /
    • pp.158-164
    • /
    • 2009
  • 웹 카메라를 이용한 실시간 도난 방지 시스템은 움직임 객체를 구분하고 행동에 대한 분석을 통해서 그에 상응한 대응을 실시간으로 하여야 한다. 카메라를 통한 실시간 영상에서 객체의 움직임 검출은 불필요한 잡음, 조명의 변화, 가려짐 현상 등에 따라 정확한 움직임을 검출하는 것이 어렵다. 본 논문에서는 이중카메라와 초음파 센서를 이용하여 특정객체의 정확한 움직임검출을 위한 향상된 검출방법인 실시간 도난방지 시스템을 제안하였다 즉, 초음파 센서를 위치변화 측정을 위한 요소로 사용하였고, 전면과 상단의 카메라의 정보를 통해 특정객체를 지속적으로 추적할 수 있음을 실험을 통해 검증하였다 실험결과 제안한 시스템은 97.4%의 객체 추출률을 얻을 수 있었으며, 객체의 가려짐 현상에서 지속적이고 정확한 추적을 할 수 있었다.

Recognition of partially occluded 3-D targets from computationally reconstructed integral images

  • Lee, Keong-Jin;Li, Gen;Lee, Guen-Sik;Hwang, Dong-Choon;Kim, Eun-Soo
    • 한국정보디스플레이학회:학술대회논문집
    • /
    • 한국정보디스플레이학회 2008년도 International Meeting on Information Display
    • /
    • pp.761-762
    • /
    • 2008
  • In this paper, a novel approach for robust recognition of partially occluded 3-D target objects from computationally reconstructed integral images is proposed. The occluding object noises are selectively removed from the picked-up elemental images and performance of the proposed integral imaging-based 3-D target recognition system can be improved.

  • PDF

Optical System Design for Thermal Target Recognition by Spiral Scanning [TRSS]

  • Kim, Jai-Soon;Yoon, Jin-Kyung;Lee, Ho-Chan;Lee, Jai-Hyung;Kim, Hye-Kyung;Lee, Seung-Churl;Ahn, Keun-Ok
    • Journal of the Optical Society of Korea
    • /
    • 제8권4호
    • /
    • pp.174-181
    • /
    • 2004
  • Various kinds of systems, that can do target recognition and position detection simultaneously by using infrared sensing detectors, have been developed. In this paper, the detection system TRSS (Thermal target Recognition by Spiral Scanning) adopts linear array shaped uncooled IR detector and uses spiral type fast scanning method for relative position detection of target objects, which radiate an IR region wavelength spectrum. It can detect thermal energy radiating from a 9 m-size target object as far as 200 m distance. And the maximum field of a detector is fully filled with the same size of target object at the minimum approaching distance 50 m. We investigate two types of lens systems. One is a singlet lens and the other is a doublet lens system. Every system includes one aspheric surface and free positioned aperture stop. Many designs of F/1.5 system with ${\pm}5.2^{\circ}$ field at the Efl=20, 30 mm conditions for single element and double elements lens system respectively are compared in their resolution performance [MTF] according to the aspheric surface and stop position changing on their optimization process. Optimum design is established including mechanical boundary conditions and manufacturing considerations.

무인헬기의 시선안정화를 위한 시각제어용 영상정보에 관한 연구 (A Study on Visual Servoing Image Information for Stabilization of Line-of-Sight of Unmanned Helicopter)

  • 신준영;이현정;이민철
    • 한국정밀공학회:학술대회논문집
    • /
    • 한국정밀공학회 2004년도 추계학술대회 논문집
    • /
    • pp.600-603
    • /
    • 2004
  • UAV (Unmanned Aerial Vehicle) is an aerial vehicle that can accomplish the mission without pilot. UAV was developed for a military purpose such as a reconnaissance in an early stage. Nowadays usage of UAV expands into a various field of civil industry such as a drawing a map, broadcasting, observation of environment. These UAV, need vision system to offer accurate information to person who manages on ground and to control the UAV itself. Especially LOS(Line-of-Sight) system wants to precisely control direction of system which wants to tracking object using vision sensor like an CCD camera, so it is very important in vision system. In this paper, we propose a method to recognize object from image which is acquired from camera mounted on gimbals and offer information of displacement between center of monitor and center of object.

  • PDF