Minimal Cases for Computing the Generalized Relative Pose using Affine Correspondences

• URL: http://arxiv.org/abs/2007.10700v2
• Date: Thu, 19 Aug 2021 04:41:28 GMT
• Title: Minimal Cases for Computing the Generalized Relative Pose using Affine Correspondences
• Authors: Banglei Guan, Ji Zhao, Daniel Barath, Friedrich Fraundorfer
• Abstract summary: We propose three novel solvers for estimating the relative pose of a multi-camera system from affine correspondences (ACs) It is shown that the accuracy of the estimated poses is superior to the state-of-the-art techniques.
• Score: 41.35179046936236
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose three novel solvers for estimating the relative pose of a multi-camera system from affine correspondences (ACs). A new constraint is derived interpreting the relationship of ACs and the generalized camera model. Using the constraint, we demonstrate efficient solvers for two types of motions assumed. Considering that the cameras undergo planar motion, we propose a minimal solution using a single AC and a solver with two ACs to overcome the degenerate case. Also, we propose a minimal solution using two ACs with known vertical direction, e.g., from an IMU. Since the proposed methods require significantly fewer correspondences than state-of-the-art algorithms, they can be efficiently used within RANSAC for outlier removal and initial motion estimation. The solvers are tested both on synthetic data and on real-world scenes from the KITTI odometry benchmark. It is shown that the accuracy of the estimated poses is superior to the state-of-the-art techniques.

Related papers

• Vanishing Point Estimation in Uncalibrated Images with Prior Gravity Direction [82.72686460985297]
  We tackle the problem of estimating a Manhattan frame. We derive two new 2-line solvers, one of which does not suffer from singularities affecting existing solvers. We also design a new non-minimal method, running on an arbitrary number of lines, to boost the performance in local optimization.
  arXiv  Detail & Related papers  (2023-08-21T13:03:25Z)
• AffineGlue: Joint Matching and Robust Estimation [74.04609046690913]
  We propose AffineGlue, a method for joint two-view feature matching and robust estimation. AffineGlue selects potential matches from one-to-many correspondences to estimate minimal models. Guided matching is then used to find matches consistent with the model, suffering less from the ambiguities of one-to-one matches.
  arXiv  Detail & Related papers  (2023-07-28T08:05:36Z)
• Affine Correspondences between Multi-Camera Systems for Relative Pose Estimation [11.282703971318934]
  We present a novel method to compute the relative pose of multi-camera systems using two affine correspondences (ACs) This paper shows that the 6DOF relative pose estimation problem using ACs permits a feasible minimal solution. Experiments on both virtual and real multi-camera systems prove that the proposed solvers are more efficient than the state-of-the-art algorithms.
  arXiv  Detail & Related papers  (2023-06-22T15:52:48Z)
• Finding Geometric Models by Clustering in the Consensus Space [61.65661010039768]
  We propose a new algorithm for finding an unknown number of geometric models, e.g., homographies. We present a number of applications where the use of multiple geometric models improves accuracy. These include pose estimation from multiple generalized homographies; trajectory estimation of fast-moving objects.
  arXiv  Detail & Related papers  (2021-03-25T14:35:07Z)
• On Relative Pose Recovery for Multi-Camera Systems [7.494426244735998]
  We propose a complete solution to relative pose estimation from two ACs for multi-camera systems. The solver generation is based on Cayley or quaternion parameterization for rotation and hidden variable technique to eliminate translation. The proposed AC-based solvers and PC-based solvers are effective and efficient on synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2021-02-24T00:39:57Z)
• Globally Optimal Relative Pose Estimation with Gravity Prior [63.74377065002315]
  Smartphones, tablets and camera systems used, e.g., in cars and UAVs, are typically equipped with IMUs that can measure the gravity vector accurately. We propose a novel globally optimal solver, minimizing the algebraic error in the least-squares sense, to estimate the relative pose in the over-determined pose. The proposed solvers are compared with the state-of-the-art ones on four real-world datasets with approx. 50000 image pairs in total.
  arXiv  Detail & Related papers  (2020-12-01T13:09:59Z)
• P1AC: Revisiting Absolute Pose From a Single Affine Correspondence [38.350811942642565]
  We introduce the first general solution to the problem of estimating the pose of a calibrated camera. The advantage of our approach is that it requires only a single correspondence. We show that P1AC achieves more accurate results than the widely used P3P algorithm.
  arXiv  Detail & Related papers  (2020-11-17T17:36:16Z)
• Pose Estimation for Vehicle-mounted Cameras via Horizontal and Vertical Planes [37.653076607939745]
  We propose two novel solvers for estimating the egomotion of a calibrated camera mounted to a moving vehicle from a single affine correspondence. Both methods are solved via a linear system with a small matrix coefficient, thus, being extremely efficient. They are tested on synthetic data and on publicly available real-world datasets.
  arXiv  Detail & Related papers  (2020-08-13T08:01:48Z)
• Relative Pose from Deep Learned Depth and a Single Affine Correspondence [37.04516812025321]
  We propose a new approach for combining deep-learned non-metric monocular depth with affine correspondences. Considering the depth information and affine features, two new constraints on the camera pose are derived. The proposed solver is usable within 1-point RANSAC approaches.
  arXiv  Detail & Related papers  (2020-07-20T13:24:28Z)
• Making Affine Correspondences Work in Camera Geometry Computation [62.7633180470428]
  Local features provide region-to-region rather than point-to-point correspondences. We propose guidelines for effective use of region-to-region matches in the course of a full model estimation pipeline. Experiments show that affine solvers can achieve accuracy comparable to point-based solvers at faster run-times.
  arXiv  Detail & Related papers  (2020-07-20T12:07:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.