Block Partitioning and Merging for Processing Large-Scale Structure From Motion Problems in Distributed Manner

The processing time of incremental structure from motion increases exponentially with the number of images. As a result, a huge amount of time is needed for large datasets. In this paper, to improve time efficiency, a block partitioning and a merging strategy are proposed. We automatically split the image set into several overlapping subsets, and then each subset can be processed in parallel. Finally, the reconstruction results of each subset can be merged together according to the shared images and tie points. The image adjacency matrix obtained from the feature matching result is the input of our block partitioning algorithm. And by repeatedly using the matrix bandwidth reduction algorithm to reorder the images, the block can be partitioned into subsets. The partitioning result is satisfactory, namely, images assigned into a subset have a very strong connection, and the shape of each subset is compact. Most importantly, the algorithm is very simple and fast. We have successfully processed many large-scale aerial image datasets in a computer cluster system with 10 processing nodes. And, the time efficiency and the precision of the reconstruction are satisfactory.

[1]  Lei Zhou,et al.  Very Large-Scale Global SfM by Distributed Motion Averaging , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[2]  Frank Dellaert,et al.  Out-of-Core Bundle Adjustment for Large-Scale 3D Reconstruction , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[3]  Wilfried Philips,et al.  Speeding Up Structure from Motion on Large Scenes Using Parallelizable Partitions , 2010, ACIVS.

[4]  Andrea Fusiello,et al.  Hierarchical structure-and-motion recovery from uncalibrated images , 2015, Comput. Vis. Image Underst..

[5]  Andrea Fusiello,et al.  Improving the efficiency of hierarchical structure-and-motion , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[6]  Richard Szeliski,et al.  A Multi-stage Linear Approach to Structure from Motion , 2010, ECCV Workshops.

[7]  Ping Tan,et al.  A Global Linear Method for Camera Pose Registration , 2013, 2013 IEEE International Conference on Computer Vision.

[8]  Hristo Djidjev,et al.  Scalable and Accurate Graph Clustering and Community Structure Detection , 2013, IEEE Transactions on Parallel and Distributed Systems.

[9]  Inderjit S. Dhillon,et al.  Weighted Graph Cuts without Eigenvectors A Multilevel Approach , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Nanning Zheng,et al.  Large-Scale Bundle Adjustment by Parameter Vector Partition , 2012, ACCV.

[11]  Frank Dellaert,et al.  Spectral partitioning for structure from motion , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[12]  P. J. Narayanan,et al.  Multistage SFM: A Coarse-to-Fine Approach for 3D Reconstruction , 2015, ArXiv.

[13]  Long Quan,et al.  Parallel Structure from Motion from Local Increment to Global Averaging , 2017 .

[14]  Jan-Michael Frahm,et al.  Relative Bundle Adjustment Based on Trifocal Constraints , 2010, ECCV Workshops.

[15]  Richard Szeliski,et al.  Building Rome in a day , 2009, ICCV.

[16]  Ronen Basri,et al.  A Survey on Structure from Motion , 2017, ArXiv.

[17]  Inderjit S. Dhillon,et al.  Kernel k-means: spectral clustering and normalized cuts , 2004, KDD.

[18]  Pascal Monasse,et al.  Global Fusion of Relative Motions for Robust, Accurate and Scalable Structure from Motion , 2013, ICCV.

[19]  Vipin Kumar,et al.  A Fast and High Quality Multilevel Scheme for Partitioning Irregular Graphs , 1998, SIAM J. Sci. Comput..

[20]  Long Quan,et al.  Distributed Very Large Scale Bundle Adjustment by Global Camera Consensus , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[21]  Andrea Fusiello,et al.  Structure-and-motion pipeline on a hierarchical cluster tree , 2009, 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops.

[22]  Sanderson L. Gonzaga de Oliveira,et al.  A Systematic Review of Heuristics for Profile Reduction of Symmetric Matrices , 2015, ICCS.