Cost aggregation is one of the most important steps in local stereo matching, while it is difficult to fulfill both accuracy and speed. In this letter, a novel cost aggregation, consisting of guidance image, fast aggregation function and simplified scan-line optimization, is developed. Experiments demonstrate that the proposed algorithm has competitive performance compared with the state-of-art aggregation methods on 32 Middlebury stereo datasets in both accuracy and speed.
Yunlong ZHAN
Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences
Yuzhang GU
Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences
Xiaolin ZHANG
Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences
Lei QU
Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences
Jiatian PI
Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences
Xiaoxia HUANG
Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences
Yingguan WANG
Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences
Jufeng LUO
Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences
Yunzhou QIU
Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Yunlong ZHAN, Yuzhang GU, Xiaolin ZHANG, Lei QU, Jiatian PI, Xiaoxia HUANG, Yingguan WANG, Jufeng LUO, Yunzhou QIU, "Stereo Matching Based on Efficient Image-Guided Cost Aggregation" in IEICE TRANSACTIONS on Information,
vol. E99-D, no. 3, pp. 781-784, March 2016, doi: 10.1587/transinf.2015EDL8223.
Abstract: Cost aggregation is one of the most important steps in local stereo matching, while it is difficult to fulfill both accuracy and speed. In this letter, a novel cost aggregation, consisting of guidance image, fast aggregation function and simplified scan-line optimization, is developed. Experiments demonstrate that the proposed algorithm has competitive performance compared with the state-of-art aggregation methods on 32 Middlebury stereo datasets in both accuracy and speed.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2015EDL8223/_p
Copy
@ARTICLE{e99-d_3_781,
author={Yunlong ZHAN, Yuzhang GU, Xiaolin ZHANG, Lei QU, Jiatian PI, Xiaoxia HUANG, Yingguan WANG, Jufeng LUO, Yunzhou QIU, },
journal={IEICE TRANSACTIONS on Information},
title={Stereo Matching Based on Efficient Image-Guided Cost Aggregation},
year={2016},
volume={E99-D},
number={3},
pages={781-784},
abstract={Cost aggregation is one of the most important steps in local stereo matching, while it is difficult to fulfill both accuracy and speed. In this letter, a novel cost aggregation, consisting of guidance image, fast aggregation function and simplified scan-line optimization, is developed. Experiments demonstrate that the proposed algorithm has competitive performance compared with the state-of-art aggregation methods on 32 Middlebury stereo datasets in both accuracy and speed.},
keywords={},
doi={10.1587/transinf.2015EDL8223},
ISSN={1745-1361},
month={March},}
Copy
TY - JOUR
TI - Stereo Matching Based on Efficient Image-Guided Cost Aggregation
T2 - IEICE TRANSACTIONS on Information
SP - 781
EP - 784
AU - Yunlong ZHAN
AU - Yuzhang GU
AU - Xiaolin ZHANG
AU - Lei QU
AU - Jiatian PI
AU - Xiaoxia HUANG
AU - Yingguan WANG
AU - Jufeng LUO
AU - Yunzhou QIU
PY - 2016
DO - 10.1587/transinf.2015EDL8223
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E99-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2016
AB - Cost aggregation is one of the most important steps in local stereo matching, while it is difficult to fulfill both accuracy and speed. In this letter, a novel cost aggregation, consisting of guidance image, fast aggregation function and simplified scan-line optimization, is developed. Experiments demonstrate that the proposed algorithm has competitive performance compared with the state-of-art aggregation methods on 32 Middlebury stereo datasets in both accuracy and speed.
ER -