Generalized Pose Estimation from Line Correspondences with Known Vertical Direction

Horányi, Nóra; Kató, Zoltán

doi:10.1109/3dv.2017.00036

Cited by 16 publications

(19 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The method [28] studied two solvers for the newly proposed minimal configuration of a combination of points and lines. Subsequently, the approach [29] still employed the Plücker coordinate to estimate the pose in the urban environment. Employment of the IMU sensors simplifies the pose estimation to 4 DoF (Degree of Freedom) problem [29].…”

Section: Related Workmentioning

confidence: 99%

Coarse‐to‐fine 3D road model registration for traffic video augmentation

Cui

Zhang

et al. 2020

IET image process

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

Coarse‐to‐fine 3D road model registration for traffic video augmentation

Cui

Zhang

et al. 2020

IET image process

View full text Add to dashboard Cite

“…It has been widely studied for large n as well as for the minimal case of n = 3 (see [7] for a recent overview). Using line correspondences yields the Perspective n Line (PnL) problem [8], [9] (see [8] for a detailed overview). Several applications dealing with multimodal sensors make use of fused 2D radiometric and 3D depth information from uncalibrated cameras.…”

Section: Introductionmentioning

confidence: 99%

Absolute Pose Estimation of Central Cameras Using Planar Regions

Fröhlich

Tamás

Kató

2021

IEEE Trans. Pattern Anal. Mach. Intell.

Self Cite

View full text Add to dashboard Cite

A novel method is proposed for the absolute pose estimation of a central 2D camera with respect to 3D depth data without the use of any dedicated calibration pattern or explicit point correspondences. The proposed method has no specific assumption about the data source: plain depth information is expected from the 3D sensing device and a central camera is used to capture the 2D images. Both the perspective and omnidirectional central cameras are handled within a single generic camera model. Pose estimation is formulated as a 2D-3D nonlinear shape registration task which is solved without point correspondences or complex similarity metrics. It relies on a set of corresponding planar regions, and the pose parameters are obtained by solving an overdetermined system of nonlinear equations. The efficiency and robustness of the proposed method were confirmed on both large scale synthetic data and on real data acquired from various types of sensors.

show abstract

“…This vertical direction vector, or up-vector, can be accurate from 0.5°for the cheapest embedded sensors to 0.02°for less affordable sensors [8]. Some PnP and PnL methods rely on the provided up-vector to reduce the number of potential pose solutions, to reduce the general problem complexity in case of minimal formulation, or to increase performance [8] [9] [10] [11].…”

mentioning

confidence: 99%

Camera Pose Estimation Based on PnL With a Known Vertical Direction

Lecrosnier

Boutteau

Vasseur

et al. 2019

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

In this paper, we address the problem of camera pose estimation using 2D and 3D line features, also known as PnL (Perspective-n-Line) with a known vertical direction. The minimal number of line correspondences required to estimate the complete camera pose is 3 (P3L) in the general case, yielding to a minimum of 8 possible solutions. Prior knowledge of the vertical direction, such as provided by common sensors (e.g. Inertial Measurement Unit, or IMU), reduces the problem to a 4 Degree of Freedom (DoF) problem and outputs a single solution. We benefit this fact to decouple the remaining rotation estimation and the translation estimation and we present a twofold contribution: (1) we present a linear formulation of the PnL problem in Plücker lines coordinates with a known vertical direction, including a Gauss-Newton-based orientation and location refinement to compensate IMU sensor noise. (2) we propose a new efficient RANdom SAmple Consensus (RANSAC) scheme for both feature pairing and outliers rejection based solely on rotation estimation from 2 line pairs. This greatly diminishes the computational cost compared to a RANSAC3 or RANSAC4 scheme. We evaluate our algorithms on synthetic data and on our own real dataset. Experimental results show state of the art results in term of accuracy and runtime, when facing 2D noise, 3D noise and vertical direction sensor noise. Index Terms-Computer Vision for Other Robotic Applications, Sensor Fusion, Localization I. INTRODUCTION Camera pose estimation consists in determining the position and the orientation of a camera with respect to a reference frame. This process requires known correspondences between real world features and their projection onto the image plane. When these features are points, we refer to the well-studied Perspective-n-Point (PnP) problem [1] [2] [3] [4] [5]. In the case of line features, we are facing the challenging, more recent and less studied Perspective-n-Line (PnL) problem. A recent review of the latter methods is presented in [6]. Once the 2D and 3D lines extraction process is completed, feature pairing is not a simple task: lines lack effective descriptors, and descriptor-based pose estimation methods are computationally more expensive.

show abstract

Generalized Pose Estimation from Line Correspondences with Known Vertical Direction

Cited by 16 publications

References 29 publications

Coarse‐to‐fine 3D road model registration for traffic video augmentation

Coarse‐to‐fine 3D road model registration for traffic video augmentation

Absolute Pose Estimation of Central Cameras Using Planar Regions

Camera Pose Estimation Based on PnL With a Known Vertical Direction

Contact Info

Product

Resources

About