• 제목/요약/키워드: Vision data

검색결과 1,800건 처리시간 0.029초

A study on correspondence problem of stereo vision system using self-organized neural network

  • 조영빈;권대갑
    • 한국정밀공학회지
    • /
    • 제10권4호
    • /
    • pp.170-179
    • /
    • 1993
  • In this study, self-organized neural network is used to solve the vorrespondence problem of the axial stereo image. Edge points are extracted from a pair of stereo images and then the edge points of rear image are assined to the output nodes of neural network. In the matching process, the two input nodes of neural networks are supplied with the coordi- nates of the edge point selected randomly from the front image. This input data activate optimal output node and its neighbor nodes whose coordinates are thought to be correspondence point for the present input data, and then their weights are allowed to updated. After several iterations of updating, the weights whose coordinates represent rear edge point are converged to the coordinates of the correspondence points in the front image. Because of the feature map properties of self-organized neural network, noise-free and smoothed depth data can be achieved.

  • PDF

중년기 안구건조증 환자의 안구건조 증상정도와 안구피로가 시력관련 삶의 질에 미치는 영향 (Effects of dry eye syndrome symptoms and asthenopia on vision-related quality of life in middle-aged patients with dry eye syndrome)

  • 윤혜숙;김현경
    • 가정∙방문간호학회지
    • /
    • 제29권3호
    • /
    • pp.310-318
    • /
    • 2022
  • Purpose: This is a cross-sectional study aimed to investigate the effects of dry eye syndrome symptoms and eye fatigue on the vision-related quality of life (QOL) of middle-aged patients with dry eye syndrome. Methods: The participants of this study were 94 ophthalmology clinic outpatients aged 40-59 years who were diagnosed with dry eye syndrome at A and S Ophthalmology Clinics in D City, South Korea, and were exhibiting dry eye syndrome symptoms. Data were collected from July 5, 2021 to July 22, 2021, and analyzed using independent t-test, analysis of variance, Scheffe test, Pearson's correlation coefficient, and multiple regression analysis using the SPSS/WIN 25.0 program. Results: The severity of dry eye syndrome symptoms and asthenopia (r=.73, p<.001) in the participants were positively correlated, whereas the severity of dry eye syndrome symptoms and vision-related quality of life (r=-.76, p<.001) were negatively correlated. Additionally, there was a negative relationship between eye fatigue and vision-related QOL (r=-.55, p<.001). It was found that the final factors affecting the vision-related QOL of middle-aged patients with dry eye syndrome were the severity of dry eye syndrome symptoms (β=-0.76, p<.001) and dry eye stress (β=-0.14, p=.048). The explanatory power of vision-related QOL in the participants was 56.0%. Conclusion: To develop indices that can objectively measure patients' subjective symptoms for improving their vision-related QOL is necessary.

비마커 영상기반 변위계측 시스템을 이용한 구조물의 동특성 측정 (Measurement of Dynamic Characteristics on Structure using Non-marker Vision-based Displacement Measurement System)

  • 최인섭;김준희
    • 한국전산구조공학회논문집
    • /
    • 제29권4호
    • /
    • pp.301-308
    • /
    • 2016
  • 본 연구에서는 마커없이 구조물의 변위를 측정할 수 있는 영상기반 변위계측 시스템(NVDMS)을 제안한다. 기존의 방식과 제안하는 NVDMS는 크게 두 가지의 차이점이 있다. 첫째, NVDMS는 마커를 사용하지 않고 구조물의 특징점의 픽셀좌표 변화를 추출한다. 둘째, 특징점의 픽셀좌표를 물리좌표로 변환하는 scaling factor는 기존 방식에선 마커의 크기로부터 계산되는 반면, NVDMS에서는 카메라와 구조물사이의 거리, 각도, 초점거리로 계산된다. 3층 축소모형의 자유진동 실험에서 제안한 NVDMS로부터 얻은 변위데이터의 신뢰도를 분석하기 위해 LDS로부터 얻은 변위데이터의 비교를 하였으며, 얻어진 변위데이터를 이용하여 동특성을 분석하였다. 분석결과 NVDMS는 마커없이 구조물의 동적변위를 정밀하게 측정가능할 뿐만 아니라 얻어진 변위데이터로부터 추출한 동특성의 신뢰도 또한 높았다.

영상보안 구조 기반의 지능형 독거노인 모니터링 시스템 (Intelligent Monitoring System for Solitary Senior Citizens with Vision-Based Security Architecture)

  • 김수희;정영우;정유리;이승은
    • 한국정보통신학회:학술대회논문집
    • /
    • 한국정보통신학회 2022년도 춘계학술대회
    • /
    • pp.639-641
    • /
    • 2022
  • 사회적으로 고령화 문제가 심화되면서, 독거노인 모니터링 시스템에 관한 연구가 활발히 진행되고 있다. 일반적으로 모니터링 시스템은 영상, 센서, 계측값 등의 정보를 바탕으로 서버에서 연산을 수행하여, 사용자에게 모니터링 서비스를 제공한다. 서버를 이용하는 시스템의 구조상 데이터 유출의 위험이 존재하며, 데이터 보안을 고려한 설계가 필수적이다. 본 논문에서는 영상보안 구조 기반의 지능형 독거노인 모니터링 시스템을 제안한다. 제안하는 시스템은 Edge AI 모듈을 사용하여 카메라 모듈과 서버 간의 통신을 차단하는 구조를 통해 높은 보안성을 보장한다. Edge AI 모듈은 Verilog HDL로 설계되었으며, Field Programmable Gate Array (FPGA)를 통해 기능을 구현하였다. 본 시스템을 검증하기 위해 5,144개의 프레임 데이터에 대해 실험하였으며, 사람의 움직임이 일정 시간 감지되지 않았을 때 위험 감지 신호가 올바르게 발생하는 것을 확인하였다.

  • PDF

Review for vision-based structural damage evaluation in disasters focusing on nonlinearity

  • Sifan Wang;Mayuko Nishio
    • Smart Structures and Systems
    • /
    • 제33권4호
    • /
    • pp.263-279
    • /
    • 2024
  • With the increasing diversity of internet media, available video data have become more convenient and abundant. Related video data-based research has advanced rapidly in recent years owing to advantages such as noncontact, low-cost data acquisition, high spatial resolution, and simultaneity. Additionally, structural nonlinearity extraction has attracted increasing attention as a tool for damage evaluation. This review paper aims to summarize the research experience with the recent developments and applications of video data-based technology for structural nonlinearity extraction and damage evaluation. The most regularly used object detection images and video databases are first summarized, followed by suggestions for obtaining video data on structural nonlinear damage events. Technologies for linear and nonlinear system identification based on video data are then discussed. In addition, common nonlinear damage types in disaster events and prevalent processing algorithms are reviewed in the section on structural damage evaluation using video data uploaded on online platform. Finally, a discussion regarding some potential research directions is proposed to address the weaknesses of the current nonlinear extraction technology based on video data, such as the use of uni-dimensional time-series data as leverage to further achieve nonlinear extraction and the difficulty of real-time detection, including the fields of nonlinear extraction for spatial data, real-time detection, and visualization.

목표달성가능성에 영향을 미치는 개인의 특성과 목표달성기제에 관한 연구 (The Relationship of Individual Trait Factors and Goal Mechanisms with Goal Attainability)

  • 박종철;최지은
    • 유통과학연구
    • /
    • 제12권11호
    • /
    • pp.45-53
    • /
    • 2014
  • Purpose - Goal setting is effective in any domain in which an individual or group has some control over the outcomes. It applies not only to work tasks but also to sports and health, and in various other settings. Its success depends on considering the mediators and moderators determining its efficacy and applicability. This study investigates the individual factors influencing academic goal attainability. Unlike previous studies, we focused on the effect of the relationships between individual traits (passion, tenacity, self-control) and specific motivation (vision, self-efficacy, implementation intentions) with academic goal attainability, rather than the effects of the relationship between commitment and the goal shielding mechanism with goal attainability. Research design, data, and methodology - Data collected through questionnaires were analyzed by the SPSS program. A total of 293 school students, who participated in the TOEIC program, participated in the survey. Slightly more than half were female (male: n=145 vs. female: n=148). We verified nine hypotheses through various statistical methods (reliability analysis, exploratory factor analysis, confirmatory factor analysis, structural equation model for the hypothesis test, bootstrapping test for the mediation test). Results - Data was analyzed in three phases. The first phase involved measurement analysis (i.e., item purification and factor structure confirmation), involving the scales of the three variables of individual traits, three mechanism variables, and goal attainability. The second phase involved estimating the proposed structural relationships among the key constructs (see Figure 1), using the results to test H1 to H9. The final phase involved examining the mediating effects of the three variables (vision, implementation intention, and self-efficacy). The research model shows that the independent variable passion has a significant result with both the mediators-vision and self-efficacy. Further, vision and self-efficacy significantly affect goal attainability. The second variable, self-control, shows a significant effect when mediated by implementation intentions, but the direct relationship between implementation intension and goal attainability shows an insignificant result. However, when further mediated by self-efficacy, it showed a significant effect between self-efficacy and goal attainability. Similarly, the third variable, tenacity, shows an insignificant result when mediated by vision. In contrast, the mediator self-efficacy shows a positive effect between tenacity and goal attainability. Conclusions - This study shows how these individual traits, when mediated with the appropriate motivational factors, resulted significantly in the attainability of academic goals. We may identify several theoretical and practical contributions. Theoretically, we developed a step further in the research into consumer goals and related studies. Future research could examine the effects of different learning goal types and their combinations with performance goals (e.g., learning goals first, then performance goals), different types of goal framing (approach success vs. avoid failure), the relation between goals and cognition (which, by implication, entails all of cognitive psychology), goal hierarchies, and macro goal studies with organizations of different sizes. More studies on the relationship between conscious and subconscious goals would also be valuable.

인공지능 기반 멀티태스크를 위한 비디오 코덱의 성능평가 방법 (Evaluation of Video Codec AI-based Multiple tasks)

  • 김신;이예지;윤경로;추현곤;임한신;서정일
    • 방송공학회논문지
    • /
    • 제27권3호
    • /
    • pp.273-282
    • /
    • 2022
  • MPEG 내 VCM 그룹은 머신을 위한 비디오 코덱을 표준화하는 것으로 목표로 하고 있다. VCM 그룹은 객체 탐지, 객체 분할, 객체 추적 등 3가지의 머신비전 태스크를 포함한 데이터 세트와 데이터 세트 별 기준 데이터인 Anchor를 제공하고 있으며, 평가 템플릿을 이용하여 후보 기술군과 Anchor의 압축 대비 머신비전 성능을 비교할 수 있다. 하지만 성능 비교는 머신비전 태스크 별로 분리하여 수행되고 있으며, 다수의 머신비전 태스크에 대한 성능 평가를 수행할 수 있는 비트스트림을 생성할 수 있는 데이터는 별도로 제공하고 있지 않다. 본 논문에서는 인공 지능 기반 멀티 태스크를 위한 비디오 코덱의 성능 평가 방안에 대해 제안한다. 하나의 비트스트림의 크기 척도인 픽셀 당 비트수(BPP, Bits Per Pixel) 와 각 태스크의 정확도 결과인 Mean Average Precision(mAP)를 기반으로 산술 평균, 가중 평균, 조화 평균 등 총 3가지의 멀티 태스크 성능 평가 지표를 제안하며 mAP 결과를 기반으로 성능 결과를 비교하고자 한다. 멀티 태스크에서 태스크 별 mAP 결과 값의 범위의 차이가 있을 수 있으며 차이로 인해 생길 수 있는 성능 평가와 관련된 문제를 방지하고자 정규화한 mAP 기반 멀티 태스크 성능 결과를 산출하고 평가하고자 한다.

스테레오 비전 센서의 깊이 및 색상 정보를 이용한 환경 모델링 기반의 이동로봇 주행기술 (Direct Depth and Color-based Environment Modeling and Mobile Robot Navigation)

  • 박순용;박민용;박성기
    • 로봇학회논문지
    • /
    • 제3권3호
    • /
    • pp.194-202
    • /
    • 2008
  • This paper describes a new method for indoor environment mapping and localization with stereo camera. For environmental modeling, we directly use the depth and color information in image pixels as visual features. Furthermore, only the depth and color information at horizontal centerline in image is used, where optical axis passes through. The usefulness of this method is that we can easily build a measure between modeling and sensing data only on the horizontal centerline. That is because vertical working volume between model and sensing data can be changed according to robot motion. Therefore, we can build a map about indoor environment as compact and efficient representation. Also, based on such nodes and sensing data, we suggest a method for estimating mobile robot positioning with random sampling stochastic algorithm. With basic real experiments, we show that the proposed method can be an effective visual navigation algorithm.

  • PDF

역공학(Reverse Engineering)을 위한 자유곡면 형상의 NURBS Approximation (Reverse Engineering for Sculptured Surfaces by Using NURBS Approximation)

  • 조재형;조명우
    • 한국정밀공학회지
    • /
    • 제19권8호
    • /
    • pp.108-115
    • /
    • 2002
  • In measuring step for reverse engineering of sculptured surfaces, computer vision system is used to simplify the complicated surface by boundary edge detection method that minimizes the measuring error. The measured data by Coordinate measuring machine is clouded data points of surfaces which is segmented surface using image process. In this research, the measured data is approximated as NURBS surfaces by new suggested algorithm. The position and number of control points, selection of parametric values and compensation of weight factors are proposed. Finally, surface model is simulated and improved resulting performance is obtained.

Structural performance monitoring of an urban footbridge

  • Xi, P.S.;Ye, X.W.;Jin, T.;Chen, B.
    • Structural Monitoring and Maintenance
    • /
    • 제5권1호
    • /
    • pp.129-150
    • /
    • 2018
  • This paper presents the structural performance monitoring of an urban footbridge located in Hangzhou, China. The structural health monitoring (SHM) system is designed and implemented for the footbridge to monitor the structural responses of the footbridge and to ensure the structural safety during the period of operation. The monitoring data of stress and displacement measured by the fiber Bragg grating (FBG)-based sensors installed at the critical locations are used to analyze and assess the operation performance of the footbridge. A linear regression method is applied to separate the temperature effect from the stress monitoring data measured by the FBG-based strain sensors. In addition, the static vertical displacement of the footbridge measured by the FBG-based hydrostatic level gauges are presented and compared with the dynamic displacement remotely measured by a machine vision-based measurement system. Based on the examination of the monitored stress and displacement data, the structural safety evaluation is executed in combination with the defined condition index.