by Vaudrey, T, Wedel, A, Chen, C-Y and Klette, R
Abstract:
Optical flow is a highly researched area in low-level computer vision. It is a complex problem which tries to solve a 2D search in continuous space, while the input data is 2D discrete data. Furthermore, the latest representations of optical flow use Hue-Saturation-Value (HSV) colour circles, to effectively convey direction and magnitude of vectors. The major assumption in most optical flow applications is the intensity consistency assumption, introduced by Horn and Schunck. This constraint is often violated in practice. This paper proposes and generalises one such approach; using residual images (high-frequencies) of images, to remove the illumination differences between corresponding images. © 2010 Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering.
Reference:
Improving optical flow using residual and Sobel edge images (Vaudrey, T, Wedel, A, Chen, C-Y and Klette, R), In Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, volume 30 LNICST, 2010.
Bibtex Entry:
@inproceedings{vaudrey2010improvingimages,
author = "Vaudrey, T and Wedel, A and Chen, C-Y and Klette, R",
booktitle = "Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering",
pages = "215--222",
title = "Improving optical flow using residual and Sobel edge images",
volume = "30 LNICST",
year = "2010",
abstract = "Optical flow is a highly researched area in low-level computer vision. It is a complex problem which tries to solve a 2D search in continuous space, while the input data is 2D discrete data. Furthermore, the latest representations of optical flow use Hue-Saturation-Value (HSV) colour circles, to effectively convey direction and magnitude of vectors. The major assumption in most optical flow applications is the intensity consistency assumption, introduced by Horn and Schunck. This constraint is often violated in practice. This paper proposes and generalises one such approach; using residual images (high-frequencies) of images, to remove the illumination differences between corresponding images. © 2010 Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering.",
doi = "10.1007/978-3-642-11577-6_27",
isbn = "3642115764",
isbn = "9783642115769",
issn = "1867-8211",
language = "eng",
}