版权说明 帮助中心
首页 > 成果 > 详情

Cross-scale cost aggregation integrating intrascale smoothness constraint with weighted least squares in stereo matching

SCI-EEI
WOS被引频次:2
认领
导出
Link by DOI
反馈
分享
QQ微信 微博
成果类型:
期刊论文
作者:
Ma, Hao;Zheng, Shunyi;Li, Chang;Li, Yingsong;Gui, Li;Huang, Rongyong
通讯作者:
Zheng, SY
作者机构:
[Gui, Li] School of Electronic Information, Wuhan University, No. 129 Luoyu Road, Wuhan, 430079, China
[Ma, Hao; Li, Yingsong; Zheng, Shunyi; Gui, Li] School of Remote Sensing, Wuhan University, No. 129 Luoyu Road, Wuhan, 430079, China
[Huang, Rongyong] School of Marine Sciences, Guangxi University, Nanning, 530000, China
[Huang, Rongyong] Coral Reef Research Centre of China, Guangxi University, Nanning, 530000, China
[Zheng, Shunyi; Gui, Li] Collaborative Innovation Center of Geospatial Technology, No. 129 Luoyu Road, Wuhan, 430079, China
通讯机构:
[Zheng, Shunyi] Wuhan Univ, Sch Remote Sensing, 129 Luoyu Rd, Wuhan 430079, Peoples R China.
[Zheng, Shunyi] Collaborat Innovat Ctr Geospatial Technol, 129 Luoyu Rd, Wuhan 430079, Peoples R China.
语种:
英文
关键词:
Disparity estimations - Effectiveness and efficiencies - Experimental evidence - Multiscale interactions - Neighborhood systems - Quantitative evaluation - Smoothness constraints - Weighted least squares
期刊:
Journal of the Optical Society of America A: Optics and Image Science, and Vision
ISSN:
1084-7529
年:
2017
卷:
34
期:
4
页码:
648-656
文献类别:
WOS:Article;EI:Journal article (JA)
所属学科:
ESI学科类别:物理学;WOS学科类别:Optics
入藏号:
WOS:000399321700022;EI:20171503552725
基金类别:
Fundamental Research Funds for the Central Universities [2042016kf0012]; Key Technology Research and Development Program of Hubei Province [2015BCE080]; National Natural Science Foundation of China (NSFC) [41101407]
机构署名:
本校为其他机构
院系归属:
城市与环境科学学院
摘要:
Cross-scale cost aggregation (CSCA) allows pixel-wise multiscale interaction in the aggregated cost computation. This kind of multiscale constraint strengthens the consistency of interscale cost volume and behaves well in a textureless region, compared with single-scale cost aggregation. However, the relationship between neighbors' cost is ignored. Based on the prior knowledge that costs should vary smoothly, except at object boundaries, the smoothness constraint on cost in a neighborhood system is integrated into the CSCA model with weighted least squares for reliable matching in this paper. Our improved algorithm not only has the advantage of CSCA in computational efficiency, but also performs better than CSCA, especially on the KITTI data sets. Experimental evidence demonstrates that the proposed algorithm outperforms CSCA in textureless and discontinuous regions. Quantitative evaluations demonstrate the effectiveness and efficiency of the proposed method for improving disparity estimation accuracy. ©2017 Optical Society of America.
参考文献:
Brox T, 2011, IEEE T PATTERN ANAL, V33, P500, DOI 10.1109/TPAMI.2010.143
De-Maeztu L, 2011, IEEE I CONF COMP VIS, P1708, DOI 10.1109/ICCV.2011.6126434
Geiger A, 2012, PROC CVPR IEEE, P3354, DOI 10.1109/CVPR.2012.6248074
Hosni A, 2013, IEEE T PATTERN ANAL, V35, P504, DOI 10.1109/TPAMI.2012.156
Kohli P., 2007, IEEE C COMP VIS PATT, P1

反馈

验证码:
看不清楚,换一个
确定
取消

成果认领

标题:
用户 作者 通讯作者
请选择
请选择
确定
取消

提示

该栏目需要登录且有访问权限才可以访问

如果您有访问权限,请直接 登录访问

如果您没有访问权限,请联系管理员申请开通

管理员联系邮箱:yun@hnwdkj.com