Keyframe-based tracking for rotoscoping and animation
- 1 August 2004
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 23 (3), 584-591
- https://doi.org/10.1145/1015706.1015764
Abstract
We describe a new approach to rotoscoping --- the process of tracking contours in a video sequence --- that combines computer vision with user interaction. In order to track contours in video, the user specifies curves in two or more frames; these curves are used as keyframes by a computer-vision-based tracking algorithm. The user may interactively refine the curves and then restart the tracking algorithm. Combining computer vision with user interaction allows our system to track any sequence with significantly less effort than interpolation-based systems --- and with better reliability than "pure" computer vision systems. Our tracking algorithm is cast as a spacetime optimization problem that solves for time-varying curve shapes based on an input video sequence and user-specified constraints. We demonstrate our system with several rotoscoped examples. Additionally, we show how these rotoscoped contours can be used to help create cartoon animation by attaching user-drawn strokes to the tracked contours.This publication has 26 references indexed in Scilit:
- WYSIWYG NPRACM Transactions on Graphics, 2002
- Computer aided inbetweeningPublished by Association for Computing Machinery (ACM) ,2002
- Vision-assisted image editingACM SIGGRAPH Computer Graphics, 1999
- A semi-automatic system for edge tracking with snakesThe Visual Computer, 1996
- The Robust Estimation of Multiple Motions: Parametric and Piecewise-Smooth Flow FieldsComputer Vision and Image Understanding, 1996
- Dynamic programming for detecting, tracking, and matching deformable contoursIEEE Transactions on Pattern Analysis and Machine Intelligence, 1995
- Fast surface interpolation using hierarchical basis functionsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1990
- Snakes: Active contour modelsInternational Journal of Computer Vision, 1988
- The Conjugate Gradient Method and Trust Regions in Large Scale OptimizationSIAM Journal on Numerical Analysis, 1983
- Interactive skeleton techniques for enhancing motion dynamics in key frame animationCommunications of the ACM, 1976