Shot boundary detection from videos using entropy and local descriptor

Baber, Junaid; Afzulpurkar, Nitin; Dailey, Matthew N.; Bakhtyar, Maheen

doi:10.1109/icdsp.2011.6004918

Cited by 46 publications

(26 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Lu [23] proposes a refinement method that uses color histogram based features from every frame in each of the already detected shots and applies later post-refining to eliminate both false positives and negatives. Baber [24] on the other hand uses a more simple approach by means of entropic comparisons in the first pass and false positives in the second pass by comparing similitude between SURF descriptors extracted from the candidate boundaries.…”

Section: Shot Detection Techniquesmentioning

confidence: 99%

“…As done by [24], both the abrupt and dissolved transitions can be located by comparing the entropy 1 between consecutive frames. For the abrupt changes the difference in entropy between frames will be high, while the fade-out 2 or fade-in 3 transitions will show either a continuous decrease or increase in the entropy respectively.…”

Section: Shot Detection − Cases Of Study Entropic and Surf-based Detementioning

confidence: 99%

“…To recognize such gradual transitions, the concept of a fade signature is introduced to characterize the entropic changes typical of fades that are recognized by employing Run Length Encoding (RLE). Since some sudden changes in illumination, extreme motion, or gradual disappearance of an object within a scene can also trigger a big change in the entropy, Baber [24] uses a pair of thresholds to decide. If the entropic change is not big enough to be considered a shot boundary straight away, a point matching correspondence is done using SURF descriptor.…”

Section: Shot Detection − Cases Of Study Entropic and Surf-based Detementioning

confidence: 99%

See 2 more Smart Citations

Adult Video Content Detection Using Machine Learning Techniques

Ochoa

Yayilgan

Cheikh

2012

2012 Eighth International Conference on Signal Image Technology and Internet Based Systems

View full text Add to dashboard Cite

Automatic adult video detection is a problem of interest for many organizations around the globe aiming to restrict the availability of potentially harmful material for young audiences. Being most of the existing techniques a mere extension of the image categorization problem. In the present work we employ video genre classification techniques applied specifically for adult content detection by considering cinematic principles. Shot structure and camera motion in the temporal domain are used as the main features while skin detection and color histograms representation in the spatial domain are utilized as complementary features. Using a data set of more than 7 hours of video, our experiments comparing two different SVM algorithms achieve a high accuracy of 94.44%.

show abstract

Section: Shot Detection Techniquesmentioning

confidence: 99%

Section: Shot Detection − Cases Of Study Entropic and Surf-based Detementioning

confidence: 99%

Section: Shot Detection − Cases Of Study Entropic and Surf-based Detementioning

confidence: 99%

See 1 more Smart Citation

Adult Video Content Detection Using Machine Learning Techniques

Ochoa

Yayilgan

Cheikh

2012

2012 Eighth International Conference on Signal Image Technology and Internet Based Systems

View full text Add to dashboard Cite

show abstract

“…Color [5] is very effective and important feature of an image for retrieval system as it gives maximum information of intensity and brightness of an image. System generates color histogram for each RGB distribution (red, blue & green) of an image which is further use for HSV plane.…”

Section: Colormentioning

confidence: 99%

Video Retrieval System using Shot detection and Analysis of Frame Dissimilarities using Different Parameters

Harishbhai¹,

Deodeshmukh²

2017

CAE

View full text Add to dashboard Cite

Today, nearly above 400million of population uses internet. Internet is mostly used for search engines like google, where an individual search for information. Roughly 100million hours of videos are uploaded over internet daily (Viz. YouTube, Netflix, Dailymotion, Vimeo, Veoh, Metacafe, etc.) due to this tremendous amount of data is generated. Semantic/context based search is use which matches fast but only with correct tags. Each and every video is assigned with tags, the desired video is retrieved if and only if correct tags are used. Due to involvement of large number of frames in videos, it is difficult to extract desired video using context based matching. The proposed system is developed to extract desired video from huge data base. Algorithm consists of content based shot detection method and features are extracted for each data set of videos. Further, the frames dissimilarities are analyzed by different parameters like entropy, probability, color, etc. User can search desired video by using image as an input to the system. Proposed system successfully achieved 100% accuracy in content based search. This algorithm also reduces the search time than the existing one that is roughly 0.3ms/video, which is much faster and reliable. Expectation oof system is algorithm fits for content based video search and also gives alternative to context based search (e.g. Netflix, YouTube). General TermsVideo Retrieval, Shot detection, Different parameters for matching, SVM, Image as query, Content based video retrieval system

show abstract

“…Entre as abordagens encontradas na literatura para realizar a segmentação vídeo em tomadas, encontram-se a utilização de características (Thakar e Hadia, 2013;Baber et al, 2011), diferenças entre quadros (Chiu et al, 2008) e busca binária adaptativa (Jiang et al, 2012).…”

Section: Estrutura De Vídeounclassified

Detecção de cenas em segmentos semanticamente complexos

Lopes¹

View full text Add to dashboard Cite

Dedico esse trabalho a meus pais e à minha noiva, que sempre me apoiaram e ajudaram em todos os momentos. AgradecimentosAgradeço em primeiro lugar a Deus, por ter me iluminado durante todo o desenvolvimento do trabalho, dando a paciência e a inspiração necessária para sua realização.Agradeço também, a meu orientador, pelos infindáveis conselhos e por sua orientação sempre tão pertinente.Agradeço aos professores das matérias realizadas no mestrado, que certamente contribuíram beneficamente para a realização dessa pesquisa.Agradeço aos colegas e amigos do laboratório de pesquisa, que sempre me apoiaram e me deram forças nos momentos de desânimo.Agradeço ao CNPq pelo auxílio financeiro, processo n°134245/2011-3. Agradeço à FAPESP pelo auxílio financeiro, processo n°2011/05238-0, Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP). "As opiniões, hipóteses e conclusões ou recomendações expressas neste material são de responsabilidade do(s) autor(es) e não necessariamente refletem a visão da FAPESP". Resumo Diversas áreas da Computação (Personalização e Adaptação de Conteúdo, Recuperação de Informação, entre outras) se beneficiam da segmentação de vídeo em unidades menores de informação. A literatura apresenta diversos métodos e técnicas cujo objetivo é identificar essas unidades. Uma limitação é que tais técnicas não tratam o problema da detecção de cenas em segmentos semanticamente complexos, definidos como trechos de vídeo que apresentam mais de um assunto ou tema, e cuja semân-tica latente dificilmente pode ser determinada utilizando-se somente uma única mídia. Esses segmentos são muito relevantes, pois estão presentes em diversos domínios de vídeo, tais como filmes, noticiários e mesmo comerciais.A presente Dissertação de Mestrado propõe uma técnica de segmentação de vídeo capaz de identificar cenas em segmentos semanticamente complexos. Para isso utiliza a semântica latente alcançada com o uso de Bag of Visual Words para agrupar os segmentos de um vídeo. O agrupamento é baseado em multimodalidade, analisando-se características visuais e sonoras de cada vídeo e combinando-se os resultados por meio da estratégia fusão tardia. O presente trabalho demonstra a viabilidade técnica em reconhecer cenas em segmentos semanticamente complexos. The literature reports lots of techniques and methods, whose goal is to identify these units. One of these techniques' limitations is that they don't handle scene detection in semantically complex segments, which are defined as video snippets that present more than one subject or theme, whose latent semantics can hardly be determined using only one media. Those segments are very relevant, since they are present in multiple video domains as movies, news and even television commercials. This Master's dissertation proposes a video scene segmentation technique able to detect scenes in semantically complex segments. In order to achieve this goal it uses latent semantics extracted by the Bag of Visual Words to group a video segments. This grouping process is based on multimodalit...

show abstract

Shot boundary detection from videos using entropy and local descriptor

Cited by 46 publications

References 5 publications

Adult Video Content Detection Using Machine Learning Techniques

Adult Video Content Detection Using Machine Learning Techniques

Video Retrieval System using Shot detection and Analysis of Frame Dissimilarities using Different Parameters

Detecção de cenas em segmentos semanticamente complexos

Contact Info

Product

Resources

About