Abstract
Large-scale 3D image localization requires computationally expensive matching between 2D feature points in the query image and a 3D point cloud. In this chapter, we present a method to accelerate the matching process and reduce the memory footprint by analyzing the view statistics of points in a training corpus. Given a training image set that is representative of common views of a scene, our approach identifies a compact subset of the 3D point cloud for efficient localization, while achieving comparable localization performance to using the full 3D point cloud. We demonstrate that the problem can be precisely formulated as a mixed-integer quadratic program and present a point-wise descriptor calibration process to improve matching. We show that our algorithm outperforms the state-of-the-art greedy algorithm on standard datasets, on measures of both point-cloud compression and localization accuracy.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
http://www.gurobi.com.
References
Agarwal S, Snavely N, Simon I, Seitz S, Szeliski R (2009) Building Rome in a Day. In: ICCV
Baatz G, Saurer O, Köser K, Pollefeys M (2012) Large scale visual geo-localization of images in mountainous terrain. In: ECCV
Baatz G, Köser K, Chen D, Grzeszczuk R, Pollefeys M (2012) Handling urban location recognition as a 2D homothetic problem. In: ECCV
Chen D, Baatz G, Köser K, Tsai SS, Vedantham R, Pylvänäinen T, Roimela K, Chen X, Bach J, Pollefeys M, Girod B, Grzeszczuk R (2011) City-scale landmark identification on mobile devices. In: CVPR
Cozman F, Krotkov E (1995) Robot localization using a computer vision sextant. In: ICRA
Cummins M, Newman P (2008) FAB-MAP: probabilistic localization and mapping in the space of appearance. In: IJRR
Fischler MA, Bolles RC (1981) FAB-MAP: random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. In: Communications of the ACM
Frahm J-M, Georgel P, Gallup D, Johnson T, Raguram R, Wu C, Jen Y-H, Dunn E, Clipp B, Lazebnik S, Pollefeys M (2010) Building Rome on a cloudless day. In: ECCV
Havlena M, Torii A, Pajdla T (2010) Efficient structure from motion by graph optimization. In: ECCV
Hays J, Efros AA (2008) IM2GPS: estimating geographic information from a single image. In: CVPR
Irschara A, Zach C, Frahm J-M, Bischof H (2009) From structure-from-motion point clouds to fast location recognition. In: CVPR
Jacobs N, Satkin S, Roman N, Speyer R, Pless R (2007) Geolocating static cameras. In: ICCV
Kalogerakis E, Vesselova O, Hays J, Efros AA, Hertzmann A (2009) Image sequence geolocation with human travel priors. In: ICCV
Karp RM (1972) Reducibility among combinatorial problems. In: Complexity of computer computations
Sattler T, Leibe B, Kobbelt L (2011) Fast image-based localization using direct 2D-to-3D matching. In: ICCV
Choudhary S, Narayanan PJ (2012) Visibility probability structure from SfM datasets and applications. In: ECCV
Sattler T, Leibe B, Kobbelt L (2012) Improving image-based localization by active correspondence search. In: ECCV
Donoser M, Schmalstieg D (2014) Discriminative feature-to-point matching in image-based localization. In: CVPR
Cao S, Snavely N (2013) Graph-based discriminative learning for location recognition. In: CVPR
Lepetit V, Moreno-Noguer F, Fua P (2009) EPnP: an accurate O(n) solution to the PnP problem. In: IJCV
Li F, Kosecka J (2006) Probabilistic location recognition using reduced feature set. In: ICRA
Li X, Wu C, Zach C, Lazebnik S, Frahm J-M (2008) Probabilistic location recognition using reduced feature set. In: ECCV
Li Y, Snavely N, Huttenlocher D, Fua P (2012) Worldwide pose estimation using 3D point clouds. In: ECCV
Li Y, Snavely N, Huttenlocher D (2010) Location recognition using priotized feature matching. In: ECCV
Lowe DG (2004) Distinctive image features from scale-invariant keypoints. In: IJCV
Ni K, Kannan A, Criminisi A, Winn J (2009) Epitomic location recognition. In: TPAMI
Nistér D, Stewénius H (2006) Scalable recognition with a vocabulary tree. In: CVPR
Olsson C, Eriksson AP, Kahl F (2007) Solving large scale binary quadratic problems: spectral methods vs. semidefinite programming. In: CVPR
Duncan R, Roberto C (2004) An image-based system for urban navigation. In: BMVC
Schindler G, Brown M, Szeliski R (2007) City-scale location recognition. In: ICCV
Se S, Lowe D, Little J (2002) Global localization using distinctive visual features. In: IROS
Simon I, Snavely N, Seitz SM (2007) Scene summarization for online image collections. In: ICCV
Snavely N, Seitz SM, Szeliski R (2006) Photo tourism: exploring photo collections in 3D. In: TOG(SIGGRAPH)
Snavely N, Seitz SM, Szeliski R (2008) Skeletal graphs for efficient structure from motion. In: CVPR
Torralba A, Murphy KP, Freeman WT, Rubin MA (2008) Context-based vision system for place and object recognition. In: ICCV
Zamir AR, Shah M (2010) Accurate image localization based on Google Maps street view. In: ECCV
Zhang W, Kosecka J (2006) Image based localization in urban environments. In: 3DPVT
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Park, H.S., Wang, Y., Nurvitadhi, E., Hoe, J.C., Sheikh, Y., Chen, M. (2016). 3D Point Cloud Reduction Using Mixed-Integer Quadratic Programming. In: Zamir, A., Hakeem, A., Van Gool, L., Shah, M., Szeliski, R. (eds) Large-Scale Visual Geo-Localization. Advances in Computer Vision and Pattern Recognition. Springer, Cham. https://doi.org/10.1007/978-3-319-25781-5_10
Download citation
DOI: https://doi.org/10.1007/978-3-319-25781-5_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-25779-2
Online ISBN: 978-3-319-25781-5
eBook Packages: Computer ScienceComputer Science (R0)