• Journal of the Korea Society of Computer and Information
• /
• v.11 no.2 s.40
• /
• pp.111-119
• /
• 2006

Video viewers can not understand enough entire video contents because most video is long length data of large capacity. This paper propose efficient scene change detection and video abstracting using new shot clustering to solve this problem. Scene change detection is extracted by method that was merged color histogram with $\chi2$ histogram. Clustering is performed by similarity measure using difference of local histogram and new shot merge algorithm. Furthermore, experimental result is represented by using Real TV broadcast program.

• KSCI Review
• /
• v.14 no.1
• /
• pp.255-264
• /
• 2006

Video viewers can not understand enough entire video contents because most video is long length data of large capacity. This paper propose efficient scene change detection and video abstracting using new shot clustering to solve this problem. Scene change detection is extracted by method that was merged color histogram with ${\chi}^2$ histogram. Clustering is performed by similarity measure using difference of local histogram and new shot merge algorithm. Furthermore, experimental result is represented by using Real TV broadcast program.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.2
• /
• pp.282-291
• /
• 1999

In order to construct the News Video Database System, cut detection technique is very important. In general, the color histogram, $\chi$2 histogram or Bin-to-Bin difference(B2B) techniques are mainly using for the scene partitioning. In this paper, we propose the efficient algorithm that is applied the weight in terms of NTSC standard to cut detection. This algorithm is able to reduce the time of acquiring and comparing histogram using by separate calculation of R, G, and B for the color histogram technique. And it also provide the efficient selection method fo threshold value by and use the news videos of KBS, MBC, SBS, CNN and NHK as experimental domains. By the result of experiment, we present the proposed algorithm is more efficient for cut detection than the previous methods, and that the basis for the automatic selection of threshold values.

• The KIPS Transactions:PartB
• /
• v.8B no.4
• /
• pp.411-418
• /
• 2001

비디오 하이라이트(highlights)는 원래의 비디오 보다 짧고 많은 양의 의미를 갖는다. 기존의 파노라마 형태의 추상화 기법은 여러 프레임을 하나의 프레임으로 모자이크하는 형태이었고, TV 드라마 하이라이트 방법은 카메라의 이동이나 특수효과에 의존하기 때문에 스포츠 비디오에 적용은 부적합하다. 이 논문에서는 축구 비디오를 대상으로 시각정보와 자막을 이용하는 새로운 비디오 하이라이트 생성 방법과 이벤트 기반 비디오 인덱싱 방법을 제안한다. 하이라이트 생성은 하이라이트 생성 규칙에 따라 자막에 의해 추출된 TIT을 중심으로 시각정보에 의해 추출된 샷을 합성하여 생성하였고, 인덱싱은 자막으로 추출된 샷은 주요소로, 시각정보에 의해 추출된 샷은 부가적 요소로 구성하였다. 실험에서는 샷 추출기법 중 대표적인 컬러히스토그램과 $\chi$$^2$히스토그램과의 성능을 비교하여 제안한 하이라이트 기법이 다른 방식보다 우수함을 증명하였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.05a
• /
• pp.119-121
• /
• 2013

The fact of smoking is prohibited in elevators. Smoking in elevators that contrary to business ethics, and it can be fatal to our children and women. In this paper, people who smoke in elevators is submitted to forensic evidence. Method is to extract the white bar at the mouth, biting people that smoke. ${\chi}^2$ histogram of scene change detection method is extracted.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.05a
• /
• pp.104-106
• /
• 2013

In crime, sexual harassment is acts arouse sexual shame to the other man by the physical body contact in order to obtain sexual gratification. One of sexual abuse, molestation, means indecent assault. The different point of indecent assault and sexual harassment is 'Harassment' as means of 'assault or intimidation'. In this paper, these incidents of sexual harassment to women in elevators extract by ${\chi}^2$ histogram.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.05a
• /
• pp.86-88
• /
• 2013

Theft is secretly steal things of others. And theft tell the person who secretly stealing, bandits, stealing one's things. In modern society, theft is one of the crimes that occur frequently in the elevator. In this paper, theft crime is extracted using a ${\chi}^2$ histogram of scene change detection method. Extracted images are submitted as evidence for the action on the merits the court.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.05a
• /
• pp.101-103
• /
• 2013

Most pickpockets occurs at a place where a lot of people. However, the current occurs more commonly in a secluded place and unfrequented place. In this paper, we classified to the scene for submitting to image forensics evidence target for pickpockets of theft. Using the ${\chi}^2$ histogram to detect the scene change detection. We wish to submit evidence by classifying as a pickpocket scene video.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.05a
• /
• pp.109-111
• /
• 2013

The attack refers to the act deliberately to stimulate an abomination to the people. Of violence, such as physical aggression, direct physical forcing. Assault said to contact the opponent's body with the power to superior opponent. In other words, it is the act of hitting an opponent with the fist. In this paper, the violence and assaults that occur in elevators extracted using a color histogram of scene change detection technique.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2001.11a
• /
• pp.286-289
• /
• 2001

뉴스 비디오에서 앵커가 등장하는 첫 번째 프레임은 하나의 뉴스를 샷으로 설정하는데 기준이 되는 키 프레임이라고 볼 수 있다. 본 논문에서는 뉴스 비디오의 장면 전환을 검출을 위하여 컬러 히스토그램과 $\chi$$^2$ 히스토그램을 합성한 방법을 이용하여 키 프레임을 추출하며, 추출된 키 프레임을 대상으로 앵커 프레임의 공간적 구성과 얼굴의 특징 정보에 대한 사전 지식을 바탕으로 한 유사성 측정을 통하여 앵커를 인식하도록 한다. 앵커로 인식된 프레임은 하나의 뉴스 신에 대한 키 프레임이 되며 뉴스 비디오를 색인화 하는데 중요한 역할을 수행한다.