Epipolar Angular Factorisation of Essential Matrix for Camera Pose Calibration

2009 ◽  
pp. 401-412
Author(s):  
Władysław Skarbek ◽  
Michał Tomaszewski
Keyword(s):  
Essential Matrix ◽  
Camera Pose

Quaternion epipolar decomposition for camera pose identification and animation

2013 ◽  
Vol 21 (1) ◽  
Author(s):  
W. Skarbek ◽  
M. Tomaszewski
Keyword(s):  
Computer Vision ◽  
Measurement Error ◽  
Computer Graphics ◽  
Quadratic Form ◽  
Essential Matrix ◽  
Virtual Camera ◽  
Camera Systems ◽  
Camera Pose ◽  
Pose Identification ◽  
And Robotics

AbstractIn the literature of computer vision, computer graphics and robotics, the use of quaternions is exclusively related to 3D rotation representation and interpolation. In this research we found how epipoles in multi-camera systems can be used to represent camera poses in the quaternion domain. The rotational quaternion is decomposed in two epipole rotational quaternions and one z axis rotational quaternion. Quadratic form of the essential matrix is also related to quaternion factors. Thus, five pose parameters are distributed into three independent rotational quaternions resulting in measurement error separation at camera pose identification and greater flexibility at virtual camera animation. The experimental results refer to the design of free viewpoint television.

scholarly journals Accumulative Errors Optimization for Visual Odometry of ORB-SLAM2 Based on RGB-D Cameras

2019 ◽  
Vol 8 (12) ◽  
pp. 581 ◽  
Author(s):  
Jiangying Qin ◽  
Ming Li ◽  
Xuan Liao ◽  
Jiageng Zhong
Keyword(s):  
Image Matching ◽  
Accurate Determination ◽  
Visual Odometry ◽  
Camera Motion ◽  
Feature Points ◽  
Camera Tracking ◽  
Essential Matrix ◽  
Approximate Nearest Neighbors ◽  
Camera Pose ◽  
Simultaneous Location And Mapping

Oriented feature from the accelerated segment test (oFAST) and rotated binary robust independent elementary features (rBRIEF) SLAM2 (ORB-SLAM2) represent a recognized complete visual simultaneous location and mapping (SLAM) framework with visual odometry as one of its core components. Given the accumulated error problem with RGB-Depth ORB-SLAM2 visual odometry, which causes a loss of camera tracking and trajectory drift, we created and implemented an improved visual odometry method to optimize the cumulative error. First, this paper proposes an adaptive threshold oFAST algorithm to extract feature points from images and rBRIEF is used to describe the feature points. Then, the fast library for approximate nearest neighbors strategy is used for image rough matching, the results of which are optimized by progressive sample consensus. The image matching precision is further improved by using an epipolar line constraint based on the essential matrix. Finally, the efficient Perspective-n-Point method is used to estimate the camera pose and a least-squares optimization problem is constructed to adjust the estimated value to obtain the final camera pose. The experimental results show that the proposed method has better robustness, higher image matching accuracy and more accurate determination of the camera motion trajectory.

scholarly journals Learning Two-View Correspondences and Geometry via Local Neighborhood Correlation

Entropy ◽  
2021 ◽  
Vol 23 (8) ◽  
pp. 1024
Author(s):  
Luanyuan Dai ◽  
Xin Liu ◽  
Jingtao Wang ◽  
Changcai Yang ◽  
Riqing Chen
Keyword(s):  
Pose Estimation ◽  
Contextual Information ◽  
Local Region ◽  
K Nearest Neighbor ◽  
Outlier Rejection ◽  
Essential Matrix ◽  
Camera Pose Estimation ◽  
Local Neighborhood ◽  
Camera Pose ◽  
Neighborhood Correlation

Seeking quality feature correspondences (also known as matches) is a foundational step in computer vision. In our work, a novel and effective network with a stable local constraint, named the Local Neighborhood Correlation Network (LNCNet), is proposed to capture abundant contextual information of each correspondence in the local region, followed by calculating the essential matrix and camera pose estimation. Firstly, the k-Nearest Neighbor (KNN) algorithm is used to divide the local neighborhood roughly. Then, we calculate the local neighborhood correlation matrix (LNC) between the selected correspondence and other correspondences in the local region, which is used to filter outliers to obtain more accurate local neighborhood information. We cluster the filtered information into feature vectors containing richer neighborhood contextual information so that they can be used to more accurately determine the probability of correspondences as inliers. Extensive experiments have demonstrated that our proposed LNCNet performs better than some state-of-the-art networks to accomplish outlier rejection and camera pose estimation tasks in complex outdoor and indoor scenes.

On Camera Pose Estimation for 3D Scene Reconstruction

2020 ◽  
Author(s):  
Athul Thaliyachira Reji ◽  
Shashi Shekhar Jha ◽  
Ekta Singla
Keyword(s):  
Pose Estimation ◽  
Scene Reconstruction ◽  
Camera Pose Estimation ◽  
Camera Pose ◽  
3D Scene ◽  
3D Scene Reconstruction

scholarly journals Novel View Synthesis from only a 6-DoF Camera Pose by Two-stage Networks

2021 ◽  
Author(s):  
Xiang Guo ◽  
Bo Li ◽  
Yuchao Dai ◽  
Tongxin Zhang ◽  
Hui Deng
Keyword(s):  
View Synthesis ◽  
Two Stage ◽  
Camera Pose
Sign in / Sign up

Export Citation Format

Share Document