Disparity refinement based on segment-tree and fast weighted median filter

Wenxuan Wu; Li Li; Weiqi Jin

doi:10.1109/ICIP.2016.7533000

Disparity refinement based on segment-tree and fast weighted median filter

Wenxuan Wu, Li Li, Weiqi Jin

School of Optics and Photonics

Beijing Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

13 Citations (Scopus)

Abstract

The depth of a scene is very important in computer vision. One way to get the depth map is by stereo vision. But because of the noise, textureless area of the scene and the occlusion area, stereo matching becomes rather challenging. Some very good algorithms have been proposed. In this paper, the mainstream semi-global stereo matching algorithm (SGM) is studied, and a disparity refinement algorithm is proposed. By using SGM, an initial disparity map is computed. Then a better disparity map can be obtained by applying the disparity refinement algorithm. The proposed refinement algorithm is based on a segment-tree and a fast weighted median filter (WMF). Some experiments are done based on the well-known Middlebury dataset. The results show that the proposed algorithm can improve the quality of the disparity map effectively in most cases.

Original language	English
Title of host publication	2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings
Publisher	IEEE Computer Society
Pages	3449-3453
Number of pages	5
ISBN (Electronic)	9781467399616
DOIs	https://doi.org/10.1109/ICIP.2016.7533000
Publication status	Published - 3 Aug 2016
Event	23rd IEEE International Conference on Image Processing, ICIP 2016 - Phoenix, United States Duration: 25 Sept 2016 → 28 Sept 2016

Publication series

Name	Proceedings - International Conference on Image Processing, ICIP
Volume	2016-August
ISSN (Print)	1522-4880

Conference

Conference	23rd IEEE International Conference on Image Processing, ICIP 2016
Country/Territory	United States
City	Phoenix
Period	25/09/16 → 28/09/16

Keywords

Disparity Refinement
Fast Weighted Median Filter
Segment Tree
Stereo Matching

Access to Document

10.1109/ICIP.2016.7533000

Cite this

Wu, W., Li, L., & Jin, W. (2016). Disparity refinement based on segment-tree and fast weighted median filter. In 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings (pp. 3449-3453). Article 7533000 (Proceedings - International Conference on Image Processing, ICIP; Vol. 2016-August). IEEE Computer Society. https://doi.org/10.1109/ICIP.2016.7533000

@inproceedings{35dfc0048e864ecb9ec0ed46a8670857,

title = "Disparity refinement based on segment-tree and fast weighted median filter",

abstract = "The depth of a scene is very important in computer vision. One way to get the depth map is by stereo vision. But because of the noise, textureless area of the scene and the occlusion area, stereo matching becomes rather challenging. Some very good algorithms have been proposed. In this paper, the mainstream semi-global stereo matching algorithm (SGM) is studied, and a disparity refinement algorithm is proposed. By using SGM, an initial disparity map is computed. Then a better disparity map can be obtained by applying the disparity refinement algorithm. The proposed refinement algorithm is based on a segment-tree and a fast weighted median filter (WMF). Some experiments are done based on the well-known Middlebury dataset. The results show that the proposed algorithm can improve the quality of the disparity map effectively in most cases.",

keywords = "Disparity Refinement, Fast Weighted Median Filter, Segment Tree, Stereo Matching",

author = "Wenxuan Wu and Li Li and Weiqi Jin",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 23rd IEEE International Conference on Image Processing, ICIP 2016 ; Conference date: 25-09-2016 Through 28-09-2016",

year = "2016",

month = aug,

day = "3",

doi = "10.1109/ICIP.2016.7533000",

language = "English",

series = "Proceedings - International Conference on Image Processing, ICIP",

publisher = "IEEE Computer Society",

pages = "3449--3453",

booktitle = "2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings",

address = "United States",

}

Wu, W, Li, L & Jin, W 2016, Disparity refinement based on segment-tree and fast weighted median filter. in 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings., 7533000, Proceedings - International Conference on Image Processing, ICIP, vol. 2016-August, IEEE Computer Society, pp. 3449-3453, 23rd IEEE International Conference on Image Processing, ICIP 2016, Phoenix, United States, 25/09/16. https://doi.org/10.1109/ICIP.2016.7533000

Disparity refinement based on segment-tree and fast weighted median filter. / Wu, Wenxuan; Li, Li ; Jin, Weiqi.
2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings. IEEE Computer Society, 2016. p. 3449-3453 7533000 (Proceedings - International Conference on Image Processing, ICIP; Vol. 2016-August).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Disparity refinement based on segment-tree and fast weighted median filter

AU - Wu, Wenxuan

AU - Li, Li

AU - Jin, Weiqi

PY - 2016/8/3

Y1 - 2016/8/3

N2 - The depth of a scene is very important in computer vision. One way to get the depth map is by stereo vision. But because of the noise, textureless area of the scene and the occlusion area, stereo matching becomes rather challenging. Some very good algorithms have been proposed. In this paper, the mainstream semi-global stereo matching algorithm (SGM) is studied, and a disparity refinement algorithm is proposed. By using SGM, an initial disparity map is computed. Then a better disparity map can be obtained by applying the disparity refinement algorithm. The proposed refinement algorithm is based on a segment-tree and a fast weighted median filter (WMF). Some experiments are done based on the well-known Middlebury dataset. The results show that the proposed algorithm can improve the quality of the disparity map effectively in most cases.

AB - The depth of a scene is very important in computer vision. One way to get the depth map is by stereo vision. But because of the noise, textureless area of the scene and the occlusion area, stereo matching becomes rather challenging. Some very good algorithms have been proposed. In this paper, the mainstream semi-global stereo matching algorithm (SGM) is studied, and a disparity refinement algorithm is proposed. By using SGM, an initial disparity map is computed. Then a better disparity map can be obtained by applying the disparity refinement algorithm. The proposed refinement algorithm is based on a segment-tree and a fast weighted median filter (WMF). Some experiments are done based on the well-known Middlebury dataset. The results show that the proposed algorithm can improve the quality of the disparity map effectively in most cases.

KW - Disparity Refinement

KW - Fast Weighted Median Filter

KW - Segment Tree

KW - Stereo Matching

UR - http://www.scopus.com/inward/record.url?scp=85006822919&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2016.7533000

DO - 10.1109/ICIP.2016.7533000

M3 - Conference contribution

AN - SCOPUS:85006822919

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 3449

EP - 3453

BT - 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings

PB - IEEE Computer Society

T2 - 23rd IEEE International Conference on Image Processing, ICIP 2016

Y2 - 25 September 2016 through 28 September 2016

ER -

Disparity refinement based on segment-tree and fast weighted median filter

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this