Efficient Large-Scale Structure From Motion by Fusing Auxiliary Imaging Information

被引:47
作者
Cui, Hainan [1 ]
Shen, Shuhan [1 ]
Gao, Wei [1 ]
Hu, Zhanyi [2 ,3 ]
机构
[1] Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
[2] Chinese Acad Sci, Beijing 100190, Peoples R China
[3] Univ Chinese Acad Sci, Beijing 100049, Peoples R China
基金
国家高技术研究发展计划(863计划);
关键词
Structure from motion; auxiliary imaging information; potential inlier; 3D reconstruction; RECONSTRUCTION;
D O I
10.1109/TIP.2015.2449557
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
One of the potentially effective means for large-scale 3D scene reconstruction is to reconstruct the scene in a global manner, rather than incrementally, by fully exploiting available auxiliary information on the imaging condition, such as camera location by Global Positioning System (GPS), orientation by inertial measurement unit (or compass), focal length from EXIF, and so on. However, such auxiliary information, though informative and valuable, is usually too noisy to be directly usable. In this paper, we present an approach by taking advantage of such noisy auxiliary information to improve structure from motion solving. More specifically, we introduce two effective iterative global optimization algorithms initiated with such noisy auxiliary information. One is a robust rotation averaging algorithm to deal with contaminated epipolar graph, the other is a robust scene reconstruction algorithm to deal with noisy GPS data for camera centers initialization. We found that by exclusively focusing on the estimated inliers at the current iteration, the optimization process initialized by such noisy auxiliary information could converge well and efficiently. Our proposed method is evaluated on real images captured by unmanned aerial vehicle, StreetView car, and conventional digital cameras. Extensive experimental results show that our method performs similarly or better than many of the state-of-art reconstruction approaches, in terms of reconstruction accuracy and completeness, but is more efficient and scalable for large-scale image data sets.
引用
收藏
页码:3561 / 3573
页数:13
相关论文
共 41 条
[1]   Building Rome in a Day [J].
Agarwal, Sameer ;
Furukawa, Yasutaka ;
Snavely, Noah ;
Simon, Ian ;
Curless, Brian ;
Seitz, Steven M. ;
Szeliski, Richard .
COMMUNICATIONS OF THE ACM, 2011, 54 (10) :105-112
[2]  
[Anonymous], 2006, IEEE COMPUT SOC C CO
[3]  
[Anonymous], 2006, 2006 IEEE COMP SOC C
[4]  
[Anonymous], 2007, P IEEE C COMP VIS PA, DOI DOI 10.1109/CVPR.2007.383115
[5]   Global Motion Estimation from Point Matches [J].
Arie-Nachimson, Mica ;
Kovalsky, Shahar Z. ;
Kemelmacher-Shlizerman, Ira ;
Singer, Amit ;
Basri, Ronen .
SECOND JOINT 3DIM/3DPVT CONFERENCE: 3D IMAGING, MODELING, PROCESSING, VISUALIZATION & TRANSMISSION (3DIMPVT 2012), 2012, :81-88
[6]  
Arth Clemens, 2013, Computer Vision - ACCV 2012. 11th Asian Conference on Computer Vision. Revised Selected Papers, P705, DOI 10.1007/978-3-642-37431-9_54
[7]   Content-based image retrieval using high-dimensional information geometry [J].
Cao WenMing ;
Liu Ning ;
Kong QiCong ;
Feng Hao .
SCIENCE CHINA-INFORMATION SCIENCES, 2014, 57 (07) :1-11
[8]  
Carceroni Rodrigo., 2006, Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1, V1, P477, DOI DOI 10.1109/CVPR.2006.296
[9]  
Changchang Wu, 2011, 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), P3057, DOI 10.1109/CVPR.2011.5995552
[10]   Efficient and Robust Large-Scale Rotation Averaging [J].
Chatterjee, Avishek ;
Govindu, Venu Madhav .
2013 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2013, :521-528