IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 230 citations · 27 references
ComputingComputer Science3D ModelingComputer VisionMachine Vision3D ReconstructionCamera GeometryCamera ModelsMulti-view GeometryPose EstimationVisual Odometry3D Pose EstimationAnalytic ApproximationsCamerasCorrespondence ProblemLarge-scale LocalizationLocal LocalizationRobot Pose EstimationSearch Space Pruning
We consider the problem of localizing a novel image in a large 3D model, given that the gravitational vector is known. In principle, this is just an instance of camera pose estimation, but the scale of the problem introduces some interesting challenges. Most importantly, it makes the correspondence problem very difficult so there will often be a significant number of outliers to handle. To tackle this problem, we use recent theoretical as well as technical advances. Many modern cameras and phones have gravitational sensors that allow us to reduce the search space. Further, there are new techniques to efficiently and reliably deal with extreme rates of outliers. We extend these methods to camera pose estimation by using accurate approximations and fast polynomial solvers. Experimental results are given demonstrating that it is possible to reliably estimate the camera pose despite cases with more than 99 percent outlier correspondences in city-scale models with several millions of 3D points.
27
FAST APPROXIMATE NEAREST NEIGHBORS WITH AUTOMATIC ALGORITHM CONFIGURATION
Marius Muja, David Lowe · 2009 · 2.6K citations · Full text
IM2GPS: estimating geographic information from a single image
James Hays, Alexei A. Efros · 2008 · 890 citations · Full text
City-Scale Location Recognition
Grant Schindler, Matthew A. Brown · 2007 · 629 citations
Pose estimation from corresponding point data
R.M. Haralick, H. J. Joo, C. Lee et al. · IEEE Transactions on Systems Man and Cybernetics · 1989 · 622 citations