Accurate Localization and Pose Estimation for Large 3D Models

Svärm, Linus; Enqvist, Olof; Oskarsson, Magnus; Kahl, Fredrik

doi:10.1109/cvpr.2014.75

Cited by 85 publications

(74 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using a finer vocabulary can reduce the problem of voting for unrelated images [22,43,47]. Yet, most large-scale localization approaches rely on directly matching the feature descriptors against the landmark descriptors without any intermediate retrieval step [25,26,41,42,49]. A popular approach to accelerate the matching process is to build a kd-tree for (approximate) nearest neighbor search on top of the landmark descriptors [25,49].…”

Section: Localization Against the Global Modelmentioning

confidence: 99%

“…Yet, most large-scale localization approaches rely on directly matching the feature descriptors against the landmark descriptors without any intermediate retrieval step [25,26,41,42,49]. A popular approach to accelerate the matching process is to build a kd-tree for (approximate) nearest neighbor search on top of the landmark descriptors [25,49]. While offering an excellent search performance, a kdtree is rather slow due to backtracking and irregular memory access [41].…”

Section: Localization Against the Global Modelmentioning

confidence: 99%

“…We compare using a kd-tree [13] (as in [25,49]), a normal inverted index (as in [41,42]), and an inverted multi-index. The inverted index is built using a visual vocabulary with 50,000 words while two vocabularies containing 1,000 words each are used for the inverted multi-index, i.e., the inverted multiindex generates a product vocabulary with 1 million words.…”

Section: B Global 2d-3d Matchingmentioning

confidence: 99%

See 2 more Smart Citations

Get Out of My Lab: Large-scale, Real-Time Visual-Inertial Localization

Lynen

Sattler

Bosse³

et al. 2015

Robotics: Science and Systems XI

239

210

View full text Add to dashboard Cite

Abstract-Accurately estimating a robot's pose relative to a global scene model and precisely tracking the pose in real-time is a fundamental problem for navigation and obstacle avoidance tasks. Due to the computational complexity of localization against a large map and the memory consumed by the model, state-ofthe-art approaches are either limited to small workspaces or rely on a server-side system to query the global model while tracking the pose locally. The latter approaches face the problem of smoothly integrating the server's pose estimates into the trajectory computed locally to avoid temporal discontinuities.In this paper, we demonstrate that large-scale, real-time pose estimation and tracking can be performed on mobile platforms with limited resources without the use of an external server. This is achieved by employing map and descriptor compression schemes as well as efficient search algorithms from computer vision. We derive a formulation for integrating the global pose information into a local state estimator that produces much smoother trajectories than current approaches. Through detailed experiments, we evaluate each of our design choices individually and document its impact on the overall system performance, demonstrating that our approach outperforms state-of-the-art algorithms for localization at scale.

show abstract

Section: Localization Against the Global Modelmentioning

confidence: 99%

Section: Localization Against the Global Modelmentioning

confidence: 99%

Section: B Global 2d-3d Matchingmentioning

confidence: 99%

See 1 more Smart Citation

Get Out of My Lab: Large-scale, Real-Time Visual-Inertial Localization

Lynen

Sattler

Bosse³

et al. 2015

Robotics: Science and Systems XI

239

210

View full text Add to dashboard Cite

show abstract

“…Additionally, if the number of points is very large, the outlier rejection scheme can become extremely slow. Recently, [23] has shown that priors about the orientation of the camera relative to the ground plane can speed up this process. We do not consider these kind of priors for our method, though.…”

Section: Related Workmentioning

confidence: 99%

Efficient monocular pose estimation for complex 3D models

Bandera

Villamizar

Ferraz

et al. 2015

2015 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

Abstract-We propose a robust and efficient method to estimate the pose of a camera with respect to complex 3D textured models of the environment that can potentially contain more than 100, 000 points. To tackle this problem we follow a top down approach where we combine high-level deep network classifiers with low level geometric approaches to come up with a solution that is fast, robust and accurate. Given an input image, we initially use a pre-trained deep network to compute a rough estimation of the camera pose. This initial estimate constrains the number of 3D model points that can be seen from the camera viewpoint. We then establish 3D-to-2D correspondences between these potentially visible points of the model and the 2D detected image features. Accurate pose estimation is finally obtained from the 2D-to-3D correspondences using a novel PnP algorithm that rejects outliers without the need to use a RANSAC strategy, and which is between 10 and 100 times faster than other methods that use it. Two real experiments dealing with very large and complex 3D models demonstrate the effectiveness of the approach.

show abstract

“…Using two matching MSER feature points, an approximate fundamental matrix could be estimated. Lately, methods that optimally find models that maximize the number of inliers, in polynomial time, have been developed, [5,25]. We will in this paper investigate a number of specific geometric problems that have received little or no attention earlier, related to orthographic projections of rigid scenes in two views.…”

Section: Introductionmentioning

confidence: 99%

Two-View Orthographic Epipolar Geometry: Minimal and Optimal Solvers

Oskarsson

2017

J Math Imaging Vis

Self Cite

View full text Add to dashboard Cite

We will in this paper present methods and algorithms for estimating two-view geometry based on an orthographic camera model. We use a previously neglected nonlinear criterion on rigidity to estimate the calibrated essential matrix. We give efficient algorithms for estimating it minimally (using only three point correspondences), in a least squares sense (using four or more point correspondences), and optimally with respect to the number of inliers. The inlier-optimal algorithm is based on a three-point solver and gives a fourth-order polynomial time algorithm. These methods can be used as building blocks to robustly find inlier correspondences in the presence of high degrees of outliers. We show experimentally that our methods can be used in many instances, where the orthographic camera model isn't generally used. A case of special interest is situations with repetitive structures, which give high amounts of outliers in the initial feature point matching.

show abstract

Accurate Localization and Pose Estimation for Large 3D Models

Cited by 85 publications

References 28 publications

Get Out of My Lab: Large-scale, Real-Time Visual-Inertial Localization

Get Out of My Lab: Large-scale, Real-Time Visual-Inertial Localization

Efficient monocular pose estimation for complex 3D models

Two-View Orthographic Epipolar Geometry: Minimal and Optimal Solvers

Contact Info

Product

Resources

About