Example based depth from fog

Research output: Contribution to journal › Conference article › Research › peer-review

Standard

Example based depth from fog. / Gibson, Kristofor B.; Belongie, Serge J.; Nguyen, Truong Q.

In: 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings, 2013, p. 728-732.

Research output: Contribution to journal › Conference article › Research › peer-review

Harvard

Gibson, KB, Belongie, SJ & Nguyen, TQ 2013, 'Example based depth from fog', 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings, pp. 728-732. https://doi.org/10.1109/ICIP.2013.6738150

APA

Gibson, K. B., Belongie, S. J., & Nguyen, T. Q. (2013). Example based depth from fog. 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings, 728-732. https://doi.org/10.1109/ICIP.2013.6738150

Vancouver

Gibson KB, Belongie SJ, Nguyen TQ. Example based depth from fog. 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings. 2013;728-732. https://doi.org/10.1109/ICIP.2013.6738150

Author

Gibson, Kristofor B. ; Belongie, Serge J. ; Nguyen, Truong Q. / Example based depth from fog. In: 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings. 2013 ; pp. 728-732.

Bibtex

@inproceedings{1b9eb5adaf514a45999fc717298d421c,
title = "Example based depth from fog",
abstract = "The presence of fog in an image reduces contrast which can be considered a nuisance in imaging applications, however, we consider this useful information for image enhancement and scene understanding. In this paper, we present a new method for estimating depth from fog in a single image and single image fog removal. We use an example based approach that is trained from data with known fog and depth. A data driven method and physics based model are used to develop the example based learning framework for single image fog removal. In addition, we account for various colors of fog by using a linear transformation of the RGB colorspace. This approach has the flexibility to learn from various scenes and relaxes the common constraint of fixed camera position. We present depth estimations and fog removal from a single image with good results.",
keywords = "Contrast Enhancement, Data Driven, Depth from Fog, Visibility",
author = "Gibson, {Kristofor B.} and Belongie, {Serge J.} and Nguyen, {Truong Q.}",
year = "2013",
doi = "10.1109/ICIP.2013.6738150",
language = "English",
pages = "728--732",
journal = "2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings",
note = "2013 20th IEEE International Conference on Image Processing, ICIP 2013 ; Conference date: 15-09-2013 Through 18-09-2013",

}

RIS

TY - GEN

T1 - Example based depth from fog

AU - Gibson, Kristofor B.

AU - Belongie, Serge J.

AU - Nguyen, Truong Q.

PY - 2013

Y1 - 2013

N2 - The presence of fog in an image reduces contrast which can be considered a nuisance in imaging applications, however, we consider this useful information for image enhancement and scene understanding. In this paper, we present a new method for estimating depth from fog in a single image and single image fog removal. We use an example based approach that is trained from data with known fog and depth. A data driven method and physics based model are used to develop the example based learning framework for single image fog removal. In addition, we account for various colors of fog by using a linear transformation of the RGB colorspace. This approach has the flexibility to learn from various scenes and relaxes the common constraint of fixed camera position. We present depth estimations and fog removal from a single image with good results.

AB - The presence of fog in an image reduces contrast which can be considered a nuisance in imaging applications, however, we consider this useful information for image enhancement and scene understanding. In this paper, we present a new method for estimating depth from fog in a single image and single image fog removal. We use an example based approach that is trained from data with known fog and depth. A data driven method and physics based model are used to develop the example based learning framework for single image fog removal. In addition, we account for various colors of fog by using a linear transformation of the RGB colorspace. This approach has the flexibility to learn from various scenes and relaxes the common constraint of fixed camera position. We present depth estimations and fog removal from a single image with good results.

KW - Contrast Enhancement

KW - Data Driven

KW - Depth from Fog

KW - Visibility

UR - http://www.scopus.com/inward/record.url?scp=84897749419&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2013.6738150

DO - 10.1109/ICIP.2013.6738150

M3 - Conference article

AN - SCOPUS:84897749419

SP - 728

EP - 732

JO - 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings

JF - 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings

T2 - 2013 20th IEEE International Conference on Image Processing, ICIP 2013

Y2 - 15 September 2013 through 18 September 2013

ER -

ID: 302046810