• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.778-782
• /
• 2003

This paper presents how it is effective to use many features for improving the speed and the accuracy of the visual servo systems. Some rank conditions which relate the image Jacobian and the control performance are derived. It is also proven that the accuracy is improved by increasing the number of features. Effectiveness of the redundant features is evaluated by the smallest singular value of the image Jacobian which is closely related to the accuracy with respect to the world coordinate system. Usefulness of the redundant features is verified by the real time experiments on a Dual-Arm Robot manipulator made in Samsung Electronic Co. Ltd.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제31권10호
• /
• pp.1386-1399
• /
• 2004

본 논문에서는 상호 관계에 기반한 자동 이미지 주석 생성 방법을 보인다 새로운 실험 이미지를 위한 자동 주석의 생성은 훈련 데이타 내의 주석과 함께 주어진 이미지들을 이용하여 이미지의 시각적 속성과 텍스트 속성의 상호 관계를 발견해 냄으로 수행된다. 본 논문에서 제시하는 상호 관계 기반 자동주석 생성 모델은 1) 시각적 속성의 적절한 군집화, 2) 시각적 속성과 텍스트 속성의 가중치 부여, 3) 노이즈 제거를 위한 차원 축소 등의 요소를 고려하여 설계된다. 실험은 680 MB의 Corel 이미지 데이터를 이용하여 각 10개의 데이타 집합에 대해 수행되었으며, 실험 결과, 시각적 속성과 텍스트 속성에 대한 가중치 부여와 시각적 속성의 적절한 군집화가 모델의 성능을 향상시키며, 본 논문에서 제시한 상호 관계기반 모델이 기존의 EM을 이용한 자동 주석 생성 모델에 비해 45%의 상대적 성능 향상을 보인다.

• 한국콘텐츠학회논문지
• /
• 제6권1호
• /
• pp.41-53
• /
• 2006

본 논문에서는 동영상에서 시간과 공간특징을 선택적으로 사용한 ROI(Region of Interest) 탐지 시스템을 소개한다. 동영상에서 명암도, 색상 등과 같은 공간특징을 사용한 공간상의 현저도 뿐만 아니라 시간상의 현저도도 얻기 위하여 모션이라는 시간특징을 사용하였다. 본 시스템에서는 동영상이 입력되면 공간특징 및 시간특징을 탐지하고, 이 특징과 관련된 기존의 심리학적 연구결과를 바탕으로 이들을 분석한다. 이렇게 분석된 결과는 하나로 통합되어 이를 기반으로 ROI 영역을 탐지한다. 일반적으로 비디오 영상에서 움직이는 개체나 영역은 같은 영상 안의 다른 개체나 영역보다 먼저 주의가 가게 되므로, 본 시스템에서는 분석된 결과를 통합하는 데 있어 시간특징인 모션을 공간특징보다 우선하여 통합한다. 시스템의 성능 분석을 위하여 동일한 실험영상을 가지고 인간을 대상으로 한 심리학적 실험을 우선 수행하였으며, 이 결과를 기준으로 본 시스템에서 얻어진 결과를 비교하여 모형의 성능을 분석하였다. 실험결과 공간특징만을 사용했을 때 보다 시간특징을 같이 사용함으로써 시스템의 성능을 보다 향상시킬 수 있었다.

• 로봇학회논문지
• /
• 제3권4호
• /
• pp.263-269
• /
• 2008

Visual odometry is a popular approach to estimating robot motion using a monocular or stereo camera. This paper proposes a novel visual odometry scheme using a stereo camera for robust estimation of a 6 DOF motion in the dynamic environment. The false results of feature matching and the uncertainty of depth information provided by the camera can generate the outliers which deteriorate the estimation. The outliers are removed by analyzing the magnitude histogram of the motion vector of the corresponding features and the RANSAC algorithm. The features extracted from a dynamic object such as a human also makes the motion estimation inaccurate. To eliminate the effect of a dynamic object, several candidates of dynamic objects are generated by clustering the 3D position of features and each candidate is checked based on the standard deviation of features on whether it is a real dynamic object or not. The accuracy and practicality of the proposed scheme are verified by several experiments and comparisons with both IMU and wheel-based odometry. It is shown that the proposed scheme works well when wheel slip occurs or dynamic objects exist.

• International Journal of Contents
• /
• 제2권1호
• /
• pp.5-8
• /
• 2006

This paper describes a new mechanism of detecting object of interest from a noisy image, without using any a-priori knowledge about the target. It employs a parallel set of filters inspired upon biological findings of mammalian vision. In our proposed system, several basic features are extracted directly from original input visual stimuli, and these features are integrated based on their local competitive relations and statistical information. Through integration process, unnecessary features for detecting the target are spontaneously decreased, while useful features are enhanced. Experiments have been performed on a set of computer generated and real images corrupted with noise.

• Journal of Information Processing Systems
• /
• 제16권6호
• /
• pp.1250-1260
• /
• 2020

This study proposes a novel deep neural network model that can accurately detect objects and their relationships in an image and represent them as a scene graph. The proposed model utilizes several multimodal features, including linguistic features and visual context features, to accurately detect objects and relationships. In addition, in the proposed model, context features are embedded using graph neural networks to depict the dependencies between two related objects in the context feature vector. This study demonstrates the effectiveness of the proposed model through comparative experiments using the Visual Genome benchmark dataset.

• 한국콘텐츠학회논문지
• /
• 제6권5호
• /
• pp.20-28
• /
• 2006

본 논문은 공간주파수 특징들과 다중 해상도 특징들을 가진 웨이블렛 영역에서 추출된 각 대역의 시각 특징 추출과 이들의 퍼지 적분 조합에 대하여 제안하였다. 칼라 양자화 이후에 똑같은 칼라의 빈도를 취함으로써 기존의 칼라 히스토그램 인터섹션 방법의 단점인 양자화 에러를 줄일 수 있게 칼라 특징을 표현한다. 또한 유사도는 서로 독립적인 특성을 갖는 호모그램, 칼라, 에너지 특징을 퍼지 측도와 퍼지 적분을 사용하여 조합한다. 1,000개의 칼라 영상에 대하여 실험을 하였고, 제안된 방법이 기존 방법들보다 객관적이고 주관적인 성능에서 우수함을 보였다.

• Journal of Biosystems Engineering
• /
• 제19권2호
• /
• pp.124-137
• /
• 1994

Visual features of a mushroom(Lentinus Edodes, L.) are critical in grading and sorting as most agricultural products are. Because of its complex and various visual features, grading and sorting of mushrooms have been done manually by the human expert. To realize the automatic handling and grading of mushrooms in real time, the computer vision system should be utilized and the efficient and robust processing of the camera captured visual information be provided. Since visual features of a mushroom are distributed over the front and back sides, recognizing sides and states of the stalk including the stalk orientation from the captured image is a prime process in the automatic task processing. In this paper, the efficient and robust recognition process identifying the front and back side and the state of the stalk was developed and its performance was compared with other recognition trials. First, recognition was tried based on the rule set up with some experimental heuristics using the quantitative features such as geometry and texture extracted from the segmented mushroom image. And the neural net based learning recognition was done without extracting quantitative features. For network inputs the segmented binary image obtained from the combined type automatic thresholding was tested first. And then the gray valued raw camera image was directly utilized. The state of the stalk seriously affects the measured size of the mushroom cap. When its effect is serious, the stalk should be excluded in mushroom cap sizing. In this paper, the stalk removal process followed by the boundary regeneration of the cap image was also presented. The neural net based gray valued raw image processing showed the successful results for our recognition task. The developed technology through this research may open the new way of the quality inspection and sorting especially for the agricultural products whose visual features are fuzzy and not uniquely defined.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.1944-1948
• /
• 2005

This paper presents how it is effective to use many features for improving the speed and the accuracy of the visual servo systems. Some rank conditions which relate the image Jacobian and the control performance are derived. It is also proven that the accuracy is improved by increasing the number of features. Effectiveness of the redundant features is evaluated by the smallest singular value of the image Jacobian which is closely related to the accuracy with respect to the world coordinate system. Usefulness of the redundant features is verified by the real time experiments on a Dual-Arm Robot manipulator made in Samsung Electronic Co. Ltd

• 한국멀티미디어학회논문지
• /
• 제18권3호
• /
• pp.359-367
• /
• 2015

In this paper, we propose intelligent fire learning and detection system using hybrid visual attention mechanism of human. Proposed fire learning system generates leaned data by learning process of fire and smoke images. The features used as learning feature are selected among many features which are extracted based on bottom-up visual attention mechanism of human, and these features are modified as learned data by calculating average and standard variation of them. Proposed fire detection system uses learned data which is generated in fire learning system and features of input image to detect fire.