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
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;
Conference_Titel :
Multimedia and Expo (ICME), 2010 IEEE International Conference on
Conference_Location :
Suntec City
Print_ISBN :
978-1-4244-7491-2
DOI :
10.1109/ICME.2010.5582611