• Proceedings of the IEEK Conference
• /
• 2000.09a
• /
• pp.729-732
• /
• 2000

대용량 비디오 데이터의 이용에 있어 효과적인 비디오 검색을 위해서는 비디오 데이터의 색인 과정이 필요하다. 효과적인 비디오 데이터의 색인을 위해서는 의미적 단위인 씬(Scene)으로 이루어진 비디오 데이터를 물리적인 경계면인 컷(장면전환점)으로 검출하는 기법이 필수적이며 각 샷에서의 키 프레임 추출 또한 필수적이다. 본 논문에서는 뉴스 비디오데이터의 키 프레임인 앵커 프레임의 효과적인 검색을 위해 DC 성분 추출과 이진 검색기법, 그리고 컬러 클러스터링을 이용하고 있다. 본 논문에서 제하고 있는 방법을 검증하기 위해서 47분 10초 분량의 MPEG-2 로 압축된 뉴스 비디오 데이터에 적용한 결과 91.3%의 정확도와 84.0%의 재현율을 보여 제안한 방법의 우수성을 증명하고 있다.

• Speech Sciences
• /
• v.11 no.3
• /
• pp.157-164
• /
• 2004

Human has average pitch-level when speak naturally. That is 'Habitual pitch level'. However, if noise added at speech, the pitch-wave is changed irregularly. We can estimate noise level of speech by using this point. This paper calculates energy level of the input speech, pitch period from of above limited energy level by NAMDF (Normalized Average Magnitude Difference Function) method, after cut each frame by pitch period unit, and propose a method that estimate noise level through closed pitch of input speech.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.11
• /
• pp.2754-2768
• /
• 2013

Video fingerprints generated from global features are usually vulnerable against general geometric transformations. In this paper, a novel video fingerprinting algorithm is proposed, in which a new spatio-temporal gradient is designed to represent the spatial and temporal information for each frame, and a new partition scheme, based on concentric circle and rings, is developed to resist the attacks efficiently. The centroids of spatio-temporal gradient orientations (CSTGO) within the circle and rings are then calculated to generate a robust fingerprint. Our experiments with different attacks have demonstrated that the proposed approach outperforms the state-of-the-art methods in terms of robustness and discrimination.

• Journal of Biosystems Engineering
• /
• v.26 no.2
• /
• pp.169-176
• /
• 2001

Defect of apple was depreciated the product value and causes storage disease seriously. To detect the defect of ‘Fuji’apple with machine vision system, the optical characteristics of defect should be investigated. In this research, absorbance spectra of defect were acquired by spectrophotometer in the range of visible and NIR region(400∼1,100nm) and L*a*b* color values were also acquired by colorimeter. NIR machine vision system was constructed with B&W camera, frame grabber, 16 tungsten-halogen lamps, variable focal length lens and NIR bandpass filter which was mounted to lens outward. Average gray values of defect at 15 NIR wavelength were acquired and the significant NIR wavelength was selected by comparing Mahalanobis distance between sound and defective apple. As the result of Mahalanobis distance analysis, the significant wavelength to discriminate the defectives in ‘Fuji’apple were found to be 720nm for scab and 970nm for bruise and cuts and 920nm was also effective regardless of defective types.

• MALSORI
• /
• no.66
• /
• pp.61-72
• /
• 2008

This paper proposes a method to improve pathological and normal voice classification performance by combining multiple features such as auditory-based and higher-order features. Their performances are measured by Gaussian mixture models (GMMs) and linear discriminant analysis (LDA). The combination of multiple features proposed by the frame-based LDA method is shown to be an effective method for pathological and normal voice classification, with a 87.0% classification rate. This is a noticeable improvement of 17.72% compared to the MFCC-based GMM algorithm in terms of error reduction.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2010.07a
• /
• pp.185-187
• /
• 2010

최근 3D HDTV에 대한 연구가 활발히 이루어지고 있다. 우리나라에서도 3D HDTV 표준을 제정하기 위한 준비가 이루어지고 있으며, 이와 같은 흐름에 맞추어 기존의 ATSC 전송 방식을 확장한 전송 방식이 연구되고 있다. 확장된 ATSC 전송 방식은 지상파 3D HDTV 방송을 목표로 하고, 프레임 구조를 중국의 지상파 방송 표준인 DMB-T와 유사하게 PN 시퀀스와 데이터로 이루어진 방식으로 이용하고자 한다. 연구되고 있는 확장된 전송방식은 기존의 ATSC 시스템의 VSB 변조방식을 기반으로 한다. 프레임 구조는 PN 시퀀스와 데이터 심볼의 구조를 가지며 이 PN을 이용하여 심볼 타이밍 오차를 복구한다. PN을 이용하기 위해 수신 단에서는 가장먼저 프레임 동기를 이루어야 하므로, 본 논문에서는 확장된 ATSC 전송 시스템 방식에 적용 가능한 프레임 동기와 심볼 타이밍 복구에 관한 방식을 제안하였다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2015.07a
• /
• pp.211-214
• /
• 2015

본 논문은 적응적 휘도 성분 부호화(Adaptive Luminance Coding)알고리듬을 이용한 블록의 움직임을 고려한 장면전환 감지 성능을 개선시키는 알고리듬을 제안하고자 한다. 기존의 장면전환 기법에서는 단순 물체의 움직임도 장면전환으로 인식하는 문제가 발생하는 점을 착안하여 본 논문에서는 적응적 휘도 성분 부호화와 블록 매칭 오류를 활용하여 보다 정확한 장면전환 기법을 제안하고자 한다. 실험결과를 통해 제안하는 방법이 기존 방법보다 높은 Precision과 Recall을 보이는 것을 확인할 수 있다.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2011.11a
• /
• pp.131-132
• /
• 2011

Image-based survey can be performed for a floating structure using the hydraulic model tests and empirical methods. I extracted the frame images from a digital camcoder movies and found the corner points for image matching. In the future, we will try the movie acquisition in the improved lab environment for a precise result.

• Proceedings of the KIEE Conference
• /
• 1987.07b
• /
• pp.1383-1386
• /
• 1987

This paper concerns, the method for velocity of dynamic Image on two dimensional sequence Image which can be obtained from two sample lines on the street. The velocity of a single moving object Is measured by the number of total frame which Is required when an automobile passes over the second sample line through the first sample line. The measured results show that the velocity error Is less than 5% comparing with the value measured by X-band speed gun.

• Proceedings of the KIEE Conference
• /
• 2006.10c
• /
• pp.300-302
• /
• 2006

The structured lighting technique is a very accurate depth measurement method. One problem in this technique is that the laser light is invisible very often partly or as a whole caused from occlusion, light absorbtion, and reflection on the surface. If there is no laser light detected on a row of the image frame, the depth could not be computed at the point on the row. In this paper, a Dynamic Programing-based efficient laser line tracking algorithm is proposed to find the most likely line of the laser light utilizing all the possible information of the laser light trace. The performance of the algorithm is shown.