• Proceedings of the Korean Information Science Society Conference
• /
• 2003.10b
• /
• pp.478-480
• /
• 2003

본 논문에서는 뉴스의 단위 구조화를 위해서 앵커 구간과 비앵커 구간으로 구분하는 효율적인 알고리즘을 제안한다. 이를 위하여 단순히 장면 전환 지점을 이용하기 보다는 화면에 존재하는 앵커의 얼굴을 찾은 후 앵커 장면의 객체 정보와 배경 컬러 정보를 이용한 클러스터링 기법을 이용하여 앵커 장면을 검출한다. 제안한 알고리즘을 다양한 뉴스 비디오에 적용한 결과, 그 성능이 우수함을 보였다.

• Annual Conference of KIPS
• /
• 2012.11a
• /
• pp.549-551
• /
• 2012

본 논문에서는 기존의 화소값 차영상 기법이 저속으로 움직이는 물체의 동작정보 감지에 취약한 점을 보완하기 위하여 실시간 영상 처리를 목적으로 연속된 프레임(Frame)에서 움직임이 있는 프레임을 찾아내고, 움직임 영역을 추출하는 움직임 검출에 관한 연구를 통해 웹캠 기반의 객체 감지시스템을 제안하였다. 제안 시스템은 단일 객체뿐 아니라 다중 객체의 움직임까지 파악할 수 있다는 장점을 가지고 있다.

• Journal of KIISE:Software and Applications
• /
• v.28 no.5
• /
• pp.389-401
• /
• 2001

This paper proposes an abstraction mechanism of the low-level digital video features for the automatic retrievals of the explosion scenes from the digital video library. In the proposed abstraction mechanism, the regional dominant colors of the key frame and the motion energy of the shot are defined as the primary abstractions of the shot for the explosion scene retrievals. It is because an explosion shot usually consists of the frames with a yellow-tone pixel and the objects in the shot are moved rapidly. The regional dominant colors of shot are selected by dividing its key frame image into several regions and extracting their regional dominant colors, and the motion energy of the shot is defined as the edge image differences between key frame and its neighboring frame. The edge image of the key frame makes the retrieval of the explosion scene more precisely, because the flames usually veils all other objects in the shot so that the edge image of the key frame comes to be simple enough in the explosion shot. The proposed automatic retrieval algorithm declares an explosion scene if it has a shot with a yellow regional dominant color and its motion energy is several times higher than the average motion energy of the shots in that scene. The edge image of the key frame is also used to filter out the false detection. Upon the extensive exporimental results, we could argue that the recall and precision of the proposed abstraction and detecting algorithm are about 0.8, and also found that they are not sensitive to the thresholds. This abstraction mechanism could be used to summarize the long action videos, and extract a high level semantic information from digital video archive.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.4
• /
• pp.62-70
• /
• 2015

Recently the demand for projected capacitance touch screens is sharply growing especially for large screens for medical devices, PC monitors and TVs. Large touch screens in general need a controller of higher complexity. They usually have a larger number of driving and sensing lines, and hence it takes longer to scan one frame for touch detection leading to a low frame scan rate. In this paper, a novel touch screen control technique is presented, which scans each frame in two steps of simultaneous multi-channel driving. The first step is to drive all driving lines simultaneously and determine which sensing lines have any touch. The second step is to sequentially rescan only the touched sensing lines, and determine exact positions of the touches. This technique can substantially increase the frame scan rate. This technique has been implemented using an FPGA and an AFE board, and tested using a commercial 23-inch touch screen panel. Experimental results show that the proposed technique improves the frame scan rate by 8.4 times for the 23-inch touch screen panel over conventional methods.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.05a
• /
• pp.139-140
• /
• 2012

This paper proposes a Video Browsing Service that provides both the video content retrieval and the video browsing by the real-time user interface on Web. For the scene segmentation and key frame extraction of video sequence, we proposes an efficient scene change detection method that combine the RGB color histogram with the ${\chi}2$ histogram.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.05a
• /
• pp.149-150
• /
• 2012

This paper presents a shot boundary detection method based on the global decision tree that allows for extraction of boundaries of high variations occurring due to camera breaks from frame difference values. For a start, difference values between frames are calculated through local X2-histogram and normalization. Next, the distances between difference values are calculated through normalization.

• The Plant Pathology Journal
• /
• v.27 no.4
• /
• pp.385-389
• /
• 2011

A new reverse transcription loop-mediated isothermal amplification (RT-LAMP) method for the Potato leafroll virus (PLRV) was developed and compared with conventional reverse transcription polymerase chain reaction (RT-PCR) to address its advantages over RTPCR. RT-LAMP primers were designed from the open reading frame 3 (ORF3) sequence of PLRV. The RT-LAMP reactions were conducted without or with a set of loop primers. By real-time monitoring using Turbimeter, the RT-LAMP (with loop primers) detects PLRV in less than 30 min, compared to 120 min of RT-PCR. By adding fluorescent reagent during the reaction, final products of the RT-LAMP were fluorescently visualized under UV light or could be differentiated by naked-eye inspection under normal light. The RT-LAMP was extremely sensitive, about 2000-fold more sensitive than RT-PCR. This study presents great potential of the RT-LAMP for diagnosis and PLRV epidemiology because RT-LAMP method is speedy, sensitive, inexpensive, and convenient.

• Journal of Korea Multimedia Society
• /
• v.8 no.1
• /
• pp.56-61
• /
• 2005

In this thesis, propose speech period and pitch detection for continuous speech recognition. This mathod is distinguishes between vowel and consonant to frame unit in continuous speech, for distinguishable voice. Powerful extraction of speech period could threshold energy make use of input signal to real noise environment. Also algorithm of this method distinguish between vowel and consonant at the same time in voice make use of zero crossing rate and short time energy to extractible speech period.

• Journal of Multimedia Information System
• /
• v.2 no.1
• /
• pp.163-170
• /
• 2015

Many overlay texts are artificially superimposed on the broadcasting videos by humans. These texts provide additional information to the audiovisual content. Especially, the overlay text in news videos contains concise and direct description of the content. Therefore, it is most reliable clue for constructing a news video indexing system. To make the automatic person indexing of interview video in the TV news program, this paper proposes the method to only detect the name text line among the whole overlay texts in one frame. The experimental results on Korean television news videos show that the proposed framework efficiently detects the overlaid name text line.

• Journal of Multimedia Information System
• /
• v.4 no.4
• /
• pp.239-242
• /
• 2017

This paper proposes a low-cost method for counting people based on blob detection and blob tracking. Here background subtraction is used to detected blob and then the blob is classified with its width and height to specify that the blob is a person. In this system we first define the area of entry and exit point in the video frame. The counting of people starts when midpoint of the people blob crosses the defined point. Finally, total number of people entry and exit from the place is displayed. Experiment result of this proposed system has high accuracy in real-time performance.