Very Fast Solution to the PnP Problem with Algebraic Outlier Rejection

Ferraz, Luis; Binefa, Xavier; Moreno-Noguer, Francesc

doi:10.1109/cvpr.2014.71

Cited by 154 publications

(148 citation statements)

References 34 publications

Supporting

Mentioning

137

Contrasting

Unclassified

Order By: Relevance

“…This reformulation of the problem, jointly with the use of linearization strategies, permitted dealing with hundreds of correspondences in real time. The EPnP has been revisited in [5], where the problem is reformulated in terms of an Efficient Procrustes PnP (EPPnP), yielding to even additional speed-ups. Subsequent works have improved the accuracy of the EPnP, still in O(n), by replacing the linearization with polynomial solvers.…”

Section: Related Workmentioning

confidence: 99%

“…More specifically, we first state the PnP problem and review the EPPnP [5] linear formulation. Then, we reformulate the EPPnP in order to integrate feature uncertainties and estimate the camera pose based on an approximated Maximum Likelihood procedure.…”

Section: Covariant Eppnpmentioning

confidence: 99%

“…Note that the barycentric coordinates α i j are independent on the coordinate system, and specifically they remain the same when writing the reference points in the camera coordinate system c. That is, p c i = ∑ 4 j=1 α i j c c j . From the EPPnP [5], after some operations and matrix manipulations, Eq. 1 can be rewritten as the following Kronecker product:…”

Section: Problem Statement and Eppnp Linear Formulationmentioning

confidence: 99%

“…2. The EPPnP [5] proposes to estimate R, t and γ in closed-form using a generalization of the Orthogonal Procrustes problem [29]:…”

Section: Problem Statement and Eppnp Linear Formulationmentioning

confidence: 99%

“…Subsequent works [11,19,33,34] have improved, also with O(n) complexity, the accuracy of the EPnP specially for the minimal cases with n = {3, 4, 5} correspondences. In addition, the flexibility of the linear formulation of the EPnP has allowed reformulations of the problem to also estimate the intrinsic parameters of an uncalibrated camera [26], or to integrate an algebraic outlier rejection criterion which does not require executing multiple RANSAC iterations [5].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Leveraging Feature Uncertainty in the PnP Problem

Ferraz¹,

Binefa²,

Moreno-Noguer³

2014

Proceedings of the British Machine Vision Conference 2014

Self Cite

View full text Add to dashboard Cite

We propose a real-time and accurate solution to the Perspective-n-Point (PnP) problem -estimating the pose of a calibrated camera from n 3D-to-2D point correspondencesthat exploits the fact that in practice the 2D position of not all 2D features is estimated with the same accuracy. Assuming a model of such feature uncertainties is known in advance, we reformulate the PnP problem as a maximum likelihood minimization approximated by an unconstrained Sampson error function, which naturally penalizes the most noisy correspondences. The advantages of this approach are thoroughly demonstrated in synthetic experiments where feature uncertainties are exactly known.Pre-estimating the features uncertainties in real experiments is, though, not easy. In this paper we model feature uncertainty as 2D Gaussian distributions representing the sensitivity of the 2D feature detectors to different camera viewpoints. When using these noise models with our PnP formulation we still obtain promising pose estimation results that outperform the most recent approaches.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Covariant Eppnpmentioning

confidence: 99%

Section: Problem Statement and Eppnp Linear Formulationmentioning

confidence: 99%

“…2. The EPPnP [5] proposes to estimate R, t and γ in closed-form using a generalization of the Orthogonal Procrustes problem [29]:…”

Section: Problem Statement and Eppnp Linear Formulationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Leveraging Feature Uncertainty in the PnP Problem

Ferraz¹,

Binefa²,

Moreno-Noguer³

2014

Proceedings of the British Machine Vision Conference 2014

Self Cite

View full text Add to dashboard Cite

show abstract

Adaptive neural network control for visual docking of an autonomous underwater vehicle using command filtered backstepping

Zhang

Gao

Chen

et al. 2022

Intl J Robust & Nonlinear

View full text Add to dashboard Cite

This article proposes an unscented Kalman filter-based visual docking controller for underactuated underwater vehicles using a position-based visual servoing (PBVS) approach. The relative pose of an underwater vehicle with respect to a moving docking station is estimated by an unscented Kalman filter with the visual measurements of multiple point features installed on the station. Based on the estimated pose, the Euler angles commands are designed via an integral cross-tracking docking method to drive the underwater vehicle to move along the desired docking path. Then, an adaptive neural network (NN) controller is designed to track the desired yaw and pitch angles using command filtered backstepping, in which a single-hidden-layer (SHL) neural network is employed to compensate for dynamic uncertainties and external disturbances. A barrier Lyapunov function is defined to improve the stability of tracking errors under attitude constraints to ensure the features are in the field of view, and hyperbolic tangent functions are utilized to deal with input saturation. Simulation studies and pool experiments are provided to demonstrate the performances of the proposed visual docking controller.

show abstract

Eigendecomposition-Free Training of Deep Networks with Zero Eigenvalue-Based Losses

Dong

et al. 2018

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Many classical Computer Vision problems, such as essential matrix computation and pose estimation from 3D to 2D correspondences, can be solved by finding the eigenvector corresponding to the smallest, or zero, eigenvalue of a matrix representing a linear system. Incorporating this in deep learning frameworks would allow us to explicitly encode known notions of geometry, instead of having the network implicitly learn them from data. However, performing eigendecomposition within a network requires the ability to differentiate this operation. Unfortunately, while theoretically doable, this introduces numerical instability in the optimization process in practice. In this paper, we introduce an eigendecomposition-free approach to training a deep network whose loss depends on the eigenvector corresponding to a zero eigenvalue of a matrix predicted by the network. We demonstrate on several tasks, including keypoint matching and 3D pose estimation, that our approach is much more robust than explicit differentiation of the eigendecomposition, It has better convergence properties and yields state-of-the-art results on both tasks.

show abstract

Very Fast Solution to the PnP Problem with Algebraic Outlier Rejection

Cited by 154 publications

References 34 publications

Leveraging Feature Uncertainty in the PnP Problem

Leveraging Feature Uncertainty in the PnP Problem

Adaptive neural network control for visual docking of an autonomous underwater vehicle using command filtered backstepping

Eigendecomposition-Free Training of Deep Networks with Zero Eigenvalue-Based Losses

Contact Info

Product

Resources

About