• DocumentCode
    2278241
  • Title

    Estimating cinematographic scene depth in movie shots

  • Author

    Benini, Sergio ; Canini, Luca ; Leonardi, Riccardo

  • Author_Institution
    Dept. of Inf. Eng., Univ. of Brescia, Brescia, Italy
  • fYear
    2010
  • fDate
    19-23 July 2010
  • Firstpage
    855
  • Lastpage
    860
  • Abstract
    In film-making, the distance from the camera to the subject greatly affects the narrative power of a shot. By the alternate use of Long shots, Medium and Close-ups the director is able to provide emphasis on key passages of the filmed scene. In this work we investigate four different inherent characteristics of single shots which contain indirect information about scene depth, without the need to recover the 3D structure of the scene as a prior step. Specifically, 2D scene geometric composition, frame colour properties, shot motion distribution and content are considered for classifying shots into three main categories. In the experimental phase, using SVM classifiers, we first test the ability of each single feature in distinguishing shot types; then we combine the whole feature set in order to improve the classification performance.
  • Keywords
    cinematography; image classification; image colour analysis; image motion analysis; support vector machines; 2D scene geometric composition; SVM classifier; cinematographic scene depth; film-making; filmed scene; frame colour property; long shot; movie shot; shot classification; shot motion distribution; single shot; Cameras; Face; Histograms; Image color analysis; Motion pictures; Pixel; Support vector machines; Feature extraction; Monocular vision; Scene depth; Shot type;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Multimedia and Expo (ICME), 2010 IEEE International Conference on
  • Conference_Location
    Suntec City
  • ISSN
    1945-7871
  • Print_ISBN
    978-1-4244-7491-2
  • Type

    conf

  • DOI
    10.1109/ICME.2010.5582611
  • Filename
    5582611