by Yang, X and Klette, R
Abstract:
Motion analysis is of basic importance for vision-based driver assistance systems. Optical flow is a common image motion representation. This paper provides comparative evaluations of four different optical flow algorithms (called Horn-Schunck, CLG, BBPW, and TV-L 1 in the paper). The algorithms are tested for synthetic and recorded sequences on original image data, on edge maps, and on residual images after applying a smoothing operator. For testing robustness, the algorithms are also analyzed on synthetic sequences with artificial noises (Gaussian blur, Gaussian white noise, or constant brightness changes). A comparative discussion of the algorithms is provided at the end. © 2010 IEEE.
Reference:
Evaluation of motion analysis on synthetic and real-world image sequences (Yang, X and Klette, R), In International Conference Image and Vision Computing New Zealand, 2010.
Bibtex Entry:
@inproceedings{yang2010evaluationsequences,
author = "Yang, X and Klette, R",
booktitle = "International Conference Image and Vision Computing New Zealand",
title = "Evaluation of motion analysis on synthetic and real-world image sequences",
year = "2010",
abstract = "Motion analysis is of basic importance for vision-based driver assistance systems. Optical flow is a common image motion representation. This paper provides comparative evaluations of four different optical flow algorithms (called Horn-Schunck, CLG, BBPW, and TV-L 1 in the paper). The algorithms are tested for synthetic and recorded sequences on original image data, on edge maps, and on residual images after applying a smoothing operator. For testing robustness, the algorithms are also analyzed on synthetic sequences with artificial noises (Gaussian blur, Gaussian white noise, or constant brightness changes). A comparative discussion of the algorithms is provided at the end. © 2010 IEEE.",
doi = "10.1109/IVCNZ.2010.6148794",
isbn = "9781424496303",
issn = "2151-2191",
eissn = "2151-2205",
keyword = "BBPW",
keyword = "CLG",
keyword = "Horn-Schunck",
keyword = "Motion analysis",
keyword = "optical flow",
keyword = "performance evaluation",
keyword = "TV-L 1",
language = "eng",
}