Simultaneous Pose and Correspondence Determination Combining Softassign and Orthogonal Iteration

Dong, Hang; Sun, Changku; Zhang, Baoshang; Peng, Wang

doi:10.1109/access.2019.2939020

Cited by 10 publications

(5 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It only considers the correspondence of each feature point with its 2D projection. -the Perspective-Ray-Based (PRB)+LHM method [16,17]: It is the LHM method [14] with the perspective-ray-based camera model. It is one of the iterative methods with the best accuracy.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

An accurate and stable pose estimation method for planar cases considering the line constraints between every two points

Zimiao,

Hao,

Fumin

et al. 2023

Metrology and Measurement Systems

View full text Add to dashboard Cite

The current solutions for pose estimation problems using coplanar feature points (PnP problems) can be divided into non-iterative and iterative solutions. The accuracy, stability, and efficiency of iterative methods are unsatisfactory. Therefore, non-iterative methods have become more popular. However, the non-iterative methods only consider the correspondence of the feature points with their 2D projections. They ignore the constraints formed between feature points. This results in lower pose estimation accuracy and stability. In this work, we proposed an accurate and stable pose estimation method considering the line constraints between every two feature points. Our method has two steps. In the first step, we solved the pose non-iteratively, considering the correspondence of the 3D feature points with their 2D projections and the line constraints formed by every two feature points. In the second step, the pose was refined by minimizing the re-projection errors with one iteration, further improving accuracy and stability. Simulation and actual experiment results show that our method's accuracy, stability, and computational efficiency are better than the other existing pose estimation methods. In the −45 • to +45 • measuring range, the maximum angle measurement error is no more than 0.039 • , and the average angle measurement error is no more than 0.016 • . In the 0 mm to 30 mm measuring range, the maximum displacement measurement error is no more than 0.049 mm, and the average displacement measurement error is no more than 0.012 mm. Compared to other current pose estimation methods, our method is the most efficient based on guaranteeing measurement accuracy and stability.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Sun et al made some improvements to the LHM method. They used the LHM method based on a perspective-ray-based camera model [16,17].…”

Section: Introductionmentioning

confidence: 99%

An accurate and stable pose estimation method for planar cases considering the line constraints between every two points

Zimiao,

Hao,

Fumin

et al. 2023

Metrology and Measurement Systems

View full text Add to dashboard Cite

show abstract

“…where ς ∈ R 3×1 is a random vector with mean of [0.005, 0.005, 0.005] T rad/s. Since the visual sensors can provide the angular information directly after processing captured visual images [30]- [32], we have the following measurement model:…”

Section: B Vision/imu Integrated Attitude Measurement Modelmentioning

confidence: 99%

Maximum Correntropy Square-Root Cubature Kalman Filter for Non-Gaussian Measurement Noise

Sun

Zhang

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

Cubature Kalman filter (CKF) is widely used for non-linear state estimation under Gaussian noise. However, the estimation performance may degrade greatly in presence of heavy-tailed measurement noise. Recently, maximum correntropy square-root cubature Kalman filter (MCSCKF) has been proposed to enhance the robustness against measurement outliers. As is generally known, the square-root algorithms have the benefit of low computational complexity and guaranteed positive semi-definiteness of the state covariances. Therefore, MCSCKF not only possesses the advantages of square-root cubature Kalman filter (SCKF), but also is robust against the heavy-tailed measurement noise. Nevertheless, MCSCKF is prone to the numerical problems. In this paper, we propose a new maximum correntropy square-root cubature Kalman filter (NMCSCKF) based on a cost function which is obtained by a combination of weighted least squares (WLS) to handle the Gaussian process noise and maximum correntropy criterion (MCC) to handle the heavy-tailed measurement noise. Compared to MCSCKF, the proposed method is more time-efficient and most importantly, it avoids the numerical problem. A univariate non-stationary growth model and a multi-rate vision/IMU integrated attitude measurement model are used to demonstrate the superior performance of the proposed method. INDEX TERMS Square-root cubature Kalman filter, maximum correntropy criterion, vision/IMU integrated measurement.

show abstract

“…In contrast to the approach of this work, a pose of the stereo camera system or the object is calculated over a large set of feature points using RANSAC for pose estimation [ 24 , 25 ]. Another method for solving the correspondence problem is “simultaneous pose and correspondence determination” [ 26 ] and its extension [ 27 ]. This algorithm does not only use subsets of hypothesized correspondences to find the optimal pose of the object, but all available image and object points are used simultaneously for iterative correspondence analysis.…”

Section: Introductionmentioning

confidence: 99%

Automatic Real-Time Pose Estimation of Machinery from Images

Bertels

Jutzi

Ulrich

2022

Sensors

View full text Add to dashboard Cite

The automatic positioning of machines in a large number of application areas is an important aspect of automation. Today, this is often done using classic geodetic sensors such as Global Navigation Satellite Systems (GNSS) and robotic total stations. In this work, a stereo camera system was developed that localizes a machine at high frequency and serves as an alternative to the previously mentioned sensors. For this purpose, algorithms were developed that detect active markers on the machine in a stereo image pair, find stereo point correspondences, and estimate the pose of the machine from these. Theoretical influences and accuracies for different systems were estimated with a Monte Carlo simulation, on the basis of which the stereo camera system was designed. Field measurements were used to evaluate the actual achievable accuracies and the robustness of the prototype system. The comparison is present with reference measurements with a laser tracker. The estimated object pose achieved accuracies higher than 16mm with the translation components and accuracies higher than 3mrad with the rotation components. As a result, 3D point accuracies higher than 16mm were achieved by the machine. For the first time, a prototype could be developed that represents an alternative, powerful image-based localization method for machines to the classical geodetic sensors.

show abstract

Simultaneous Pose and Correspondence Determination Combining Softassign and Orthogonal Iteration

Cited by 10 publications

References 35 publications

An accurate and stable pose estimation method for planar cases considering the line constraints between every two points

An accurate and stable pose estimation method for planar cases considering the line constraints between every two points

Maximum Correntropy Square-Root Cubature Kalman Filter for Non-Gaussian Measurement Noise

Automatic Real-Time Pose Estimation of Machinery from Images

Contact Info

Product

Resources

About