• Title/Summary/Keyword: background information

Search Result 4,897, Processing Time 0.033 seconds

A Study on Tracking of Object in Image Sequence (동영상내의 물체 추적에 관한 연구)

  • Choi Ho-Jin;Park Seung-Kyu
    • Proceedings of the Korea Information Processing Society Conference
    • /
    • 2006.05a
    • /
    • pp.665-668
    • /
    • 2006
  • 이동 물체 검출 및 추적은 과중한 연산량에 의해 초당 처리할 수 있는 프레임의 수가 적게 되거나 정합 과정이 단순하여 추적을 실패하는 문제점들이 있다. 본 논문에서는 동영상내에서 이동 물체를 검출하고 추적하는 새로운 접근 방법을 제안한다. 입력된 영상으로부터 배경과 물체를 분리하기 위해 background subtraction을 이용하였고, 분리된 물체들은 이진 연결 요소 분석을 통하여 세그먼트 된다. 그리고 물체의 추적을 위하여 Kalman filter를 사용하였다. 본 논문의 실험에서는 야외에서 촬영한 비디오 시퀀스를 이용하였으며, 물체 검출 및 추적이 조명 변화, 그림자에도 잘 적응함을 증명하였다.

  • PDF

Feature Extraction Of Content-based image retrieval Using object Segmentation and HAQ algorithm (객체 분할과 HAQ 알고리즘을 이용한 내용 기반 영상 검색 특징 추출)

  • 김대일;홍종선;장혜경;김영호;강대성
    • Proceedings of the IEEK Conference
    • /
    • 2003.11a
    • /
    • pp.453-456
    • /
    • 2003
  • Compared with other features of the image, color features are less sensitive to noise and background complication. Besides, this adding to object segmentation has more accuracy of image retrieval. This paper presents object segmentation and HAQ(Histogram Analysis and Quantization) algorithm approach to extract features(the object information and the characteristic colors) of an image. The empirical results shows that this method presents exactly spatial and color information of an image as image retrieval's feature.

  • PDF

Dynamic Scene Segmentation Algorithm Using a Cross Mask and Edge Information (Cross Mask와 에지 정보를 사용한 동영상 분할)

  • 강정숙;박래홍;이상욱
    • Journal of the Korean Institute of Telematics and Electronics
    • /
    • v.26 no.8
    • /
    • pp.1247-1256
    • /
    • 1989
  • In this paper, we propose the dynamic scene segmentation algorithm using a cross mask and edge information. This method, a combination of the conventioanl feature-based and pixel-based approaches, uses edges as features and determines moving pixels, with a cross mask centered on each edge pixel, by computing similarity measure between two consecutive image frames. With simple calcualtion the proposed method works well for image consisting of complex background or several moving objects. Also this method works satisfactorily in case of rotaitional motion.

  • PDF

An Improved Voice Activity Detection Algorithm Employing Speech Enhancement Preprocessing

  • Lee, Yoon-Chang;Ahn, Sang-Sik
    • Proceedings of the IEEK Conference
    • /
    • 2000.07b
    • /
    • pp.865-868
    • /
    • 2000
  • In this paper we derive a new VAD algorithm, which combines the preprocessing algorithm and the optimum decision rule. To improve the performance of the VAD algorithm we employ the speech enhancement algorithm and then apply the maximal ratio combining technique in the preprocessing procedure, which leads to maximized output SNR. Moreover, we also perform extensive computer simulations to demonstrate the performance improvement of the proposed algorithm under various background noise environments.

  • PDF

A Study on the Operational Performance by the Investment Level of Companies Information Security in the Digital Transformation(DX) Era (디지털 전환(DX) 시대에 기업의 정보보안 투자 수준에 따른 운영성과에 관한 연구)

  • Jung Byoungho;Joo Hyungkun
    • Journal of Korea Society of Digital Industry and Information Management
    • /
    • v.20 no.1
    • /
    • pp.119-131
    • /
    • 2024
  • The purpose of this study is to examine the operational performances by the investment level of information security in companies. The theoretical background summarized the meaning of information security, management information security, and network security. The research process was carried out in four stages. As a result of the analysis, the level of information security was classified into four groups, and the difference in operational performance was confirmed. According to the categorical regression analysis of the three dependent variables, independent variables such as network threats, non-network threats, executive information security awareness, industry, organizational size, and information security education all affected information security regulations, in-house information security checks, and information security budget investments. The theoretical implications of this study have contributed to updating the latest information security theory. Practical implications are that rational investments should be made on the level of information security of companies.

Dynamic Textual Information Presenting Methods on Digital Displays (디지털 디스플레이에서의 동적 문자정보 제시 방법)

  • Lee, Kyong-Hee;Cheng, Hong-In
    • Archives of design research
    • /
    • v.18 no.4 s.62
    • /
    • pp.45-52
    • /
    • 2005
  • Displays, playing an essential role in HCI, have been developed to deliver more vivid and live pictures. LCD and PDP have the most common usage among various displays to present the dynamic textual information in restricted and open places. Important and unsolicited information is being provided by hundreds of displays while we don't even perceive the information. Watching context, effective color combinations of the text and background, speeds of presentation, contexts, and types of display for leading method, moving words cross the display from right to left, were investigated with readability, comprehensibility, and overall satisfaction were compared. LCD peformed better than PDP on all comparisons u4th typical text (black, white) and background (white, black) color better than other color combinations. Normal and fast text presentation was believed more preferred when only textual information was given while slower presentation was evaluated more efficient if multimedia contents were presented with textual information.

  • PDF

An Empirical Study on Local Businesses Strategies of Success in Knowledge Management (우리나라 기업의 지식경영 성공전략에 관한 실증적 연구)

  • Kwon Hyeok-Gi
    • Management & Information Systems Review
    • /
    • v.15
    • /
    • pp.19-35
    • /
    • 2004
  • Top management's will was considered most positive by all of the surveyed local businesses, followed by organizational culture, information technology, evaluation and reward, and organizational structure in order. When influences of educational background on factors of success in knowledge management were analyzed, it was found that such background was affecting organizational structure at the significance level of 0.01 and information technology and top management's will at that of 0.05. Those who were more educated responded that success in knowledge management were dependent more on top management's will. but less on organizational structure. Concerning effects of organizational position on factors of success in knowledge management, it was found that such position was influencing top management's will at the significance level of 0.01 and organizational structure at that of 0.05. Those who were higher in organizational position responded that success in knowledge management were dependent less on top management's will, but more on organizational culture, and evaluation and reward. It as generally agreed among the surveyed businesses that knowledge management is a key strategy for business survival in the 21st century. To utilize knowledge management as their strategy, Korea's businesses should change their recognition of such management, reform their organizational culture, have CEOs of strong conviction and will and firmly establish their own information technology. It is necessary to make recognized the importance of knowledge management and culture knowledge management culture. If a person has a strong conviction or will of achieving goals by using intellectual efforts, creative imagination and necessary information, such information can be regarded as a proper knowledge. In conclusion, knowledge enterprises should strengthen their ability of knowledge use by associating their competition strategies with knowledge management. They also need to positively invest in the capture and new development of knowledge and build up infrastructures for knowledge management.

  • PDF

An Improved ViBe Algorithm of Moving Target Extraction for Night Infrared Surveillance Video

  • Feng, Zhiqiang;Wang, Xiaogang;Yang, Zhongfan;Guo, Shaojie;Xiong, Xingzhong
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • v.15 no.12
    • /
    • pp.4292-4307
    • /
    • 2021
  • For the research field of night infrared surveillance video, the target imaging in the video is easily affected by the light due to the characteristics of the active infrared camera and the classical ViBe algorithm has some problems for moving target extraction because of background misjudgment, noise interference, ghost shadow and so on. Therefore, an improved ViBe algorithm (I-ViBe) for moving target extraction in night infrared surveillance video is proposed in this paper. Firstly, the video frames are sampled and judged by the degree of light influence, and the video frame is divided into three situations: no light change, small light change, and severe light change. Secondly, the ViBe algorithm is extracted the moving target when there is no light change. The segmentation factor of the ViBe algorithm is adaptively changed to reduce the impact of the light on the ViBe algorithm when the light change is small. The moving target is extracted using the region growing algorithm improved by the image entropy in the differential image of the current frame and the background model when the illumination changes drastically. Based on the results of the simulation, the I-ViBe algorithm proposed has better robustness to the influence of illumination. When extracting moving targets at night the I-ViBe algorithm can make target extraction more accurate and provide more effective data for further night behavior recognition and target tracking.

The Estimation of Hand Pose Based on Mean-Shift Tracking Using the Fusion of Color and Depth Information for Marker-less Augmented Reality (비마커 증강현실을 위한 색상 및 깊이 정보를 융합한 Mean-Shift 추적 기반 손 자세의 추정)

  • Lee, Sun-Hyoung;Hahn, Hern-Soo;Han, Young-Joon
    • Journal of the Korea Society of Computer and Information
    • /
    • v.17 no.7
    • /
    • pp.155-166
    • /
    • 2012
  • This paper proposes a new method of estimating the hand pose through the Mean-Shift tracking algorithm using the fusion of color and depth information for marker-less augmented reality. On marker-less augmented reality, the most of previous studies detect the hand region using the skin color from simple experimental background. Because finger features should be detected on the hand, the hand pose that can be measured from cameras is restricted considerably. However, the proposed method can easily detect the hand pose from complex background through the new Mean-Shift tracking method using the fusion of the color and depth information from 3D sensor. The proposed method of estimating the hand pose uses the gravity point and two random points on the hand without largely constraints. The proposed Mean-Shift tracking method has about 50 pixels error less than general tracking method just using color value. The augmented reality experiment of the proposed method shows results of its performance being as good as marker based one on the complex background.

A study on decision making system in library management with an analysis on the case study of university library in Seoul (도서관경영에 있어서 의사결정시스템에 관한 연구)

  • Lee Woo Bum
    • Journal of the Korean Society for Library and Information Science
    • /
    • v.20
    • /
    • pp.163-222
    • /
    • 1991
  • This dissertation are studying the conceptual structure of decision making situation in libraries, by analyzing the library function, decision makings of library and then seeking economic and efficient alternative decision making by programming the· decision making situations, and finally, introducing how to apply management information system or decision making support system. For this purpose, in order to analyzing necessary factors for the decision making system, the questionnaire used Lickert method were distributed to 400 librarians of 36 universities in Seoul by means of mail. 193 librarians, $48\%$ of the questionnaire, are returned are studied by using 'SYSTAT' statistical software to figure out the factors of the decision making system. This dissertation was put six hypotheses and tested with the returned questionnaire. The following five result can be asserted. First, to the higher degree of the librarians' participation in the important library decision makings, the quality of formal library services are improved regardless of seniority of the work. Secondly, the t-test results show that all of t-test scores of seniority of the work, educational background, and responsibilities of the work are exceeding significant level and perception of decision making was proved to be different depending on seniority of the work, educational background, and responsibilities of the work in libraries. Thirdly, as the results of factor af factor analysis, the encouragement on participation in the library academic activities, the extent to get useful information about performances of library and the improvements of library works were grouped by similar posibilities of distribution and therfore the academic activities, the collection of information and the improvement of library performances is proved to be interrelational each other. Fourthly, the fifth hypothesis of the close relationship between the decision making situation and types of advisor by it was more or less interrelational, but their relationship was not seen some significancies. Lastly, as the dynamic organization of library management forming a special commitee or a project team with librarian can improve the extent and quality of the librarian's participation in the decision making of library works, and thus library will become to performance more rational and effective library management.

  • PDF