DocumentCode :
1833506
Title :
Skin-Aware Stylization of Video Portraits
Author :
O´Regan, D. ; Kokaram, A.C.
Author_Institution :
Trinity Coll. Dublin, Dublin, Ireland
fYear :
2009
fDate :
12-13 Nov. 2009
Firstpage :
35
Lastpage :
44
Abstract :
This paper presents a new non-photorealistic/stroke-based rendering (NPR/SBR) framework for the stylization of videos featuring head shots of people, such as home videos, movies, and camera mobile phone clips. Spatiotemporal skin and edge detection are used to locate and emphasize the semantic content in the stylization process. The SBR portion of the algorithm features novel techniques for motion expression with elliptical brush strokes, brush stroke anchor point distribution, spatio-temporal color-sampling, and brush stroke animation with regard to state-of-the-art issues such as object occlusion and uncovering in the source video. A wide user-accessible parameter space and finishing touches such as cartoon-like edge decoration and other quirky effects empowers a variety of artistic outputs. The resulting stylized sequences are fun and interesting with regard to compression, summarization, motion visualization, story-boarding and art. Both the semantic content, and underlying video motion is highlighted and summarized on every frame of the stylized output sequence.
Keywords :
feature extraction; gesture recognition; hidden feature removal; image colour analysis; image motion analysis; rendering (computer graphics); skin; video signal processing; brush stroke anchor point distribution; brush stroke animation; cartoon like edge decoration; edge detection; elliptical brush strokes; motion expression; nonphotorealistic based rendering; object occlusion; quirky effects; skin aware stylization; spatio temporal color sampling; spatiotemporal skin; stroke based rendering; video motion; video portraits; videos featuring; Animation; Cameras; Finishing; Image edge detection; Mobile handsets; Motion pictures; Skin; Spatiotemporal phenomena; Video compression; Visualization; Animation; Motion Analysis; Probability; Rendering; Video Signal Processing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Visual Media Production, 2009. CVMP '09. Conference for
Conference_Location :
London
Print_ISBN :
978-1-4244-5257-6
Electronic_ISBN :
978-0-7695-3893-8
Type :
conf
DOI :
10.1109/CVMP.2009.15
Filename :
5430081
Link To Document :
بازگشت