An Improved Pose Estimation Method Based on Projection Vector With Noise Error Uncertainty

Abstract

Aiming at the problem of anomalous and non-independent distribution of the image errors in the feature-based visual pose estimation, a method of monocular visual pose estimation based on the uncertainty of noise error established by projection vector is proposed. First, by using the covariance matrix to describe the uncertainty of the feature point direction and integrating the uncertainty of the feature point direction into the pose estimation, characteristic point measurement error with different degrees of directional uncertainty can be adapted that can makes the algorithm robust. Then, by introducing the projection vector and combining the depth information of each feature point to represent the collinearity error, the model nonlinear problem caused by the camera perspective projection can be eliminated that can make the algorithm have global convergence. Finally, we use global convergence theorem to prove the global convergence of the proposed algorithm. The results show that the proposed method has good robustness and convergence while adapting to different degrees of error uncertainty, which can meet practical engineering applications.

CNN-Based Pose Estimation System for Close-Proximity Operations Around Uncooperative Spacecraft

“…The authors proposed a method for computing the covariance which takes different camera poses to create a fictitious distribution around each detected keypoint. Furthermore, other authors [9] proposed an improved pose estimation method based on projection vector in which the covariance is associated to the image gradient magnitude and direction at each feature location. However, in both methods the derivation of features covariance matrices cannot be directly related to the actual detection uncertainty.…”

Method for Horizontal Alignment Deviation Measurement Using Binocular Camera Without Common Target

“…where c stands for cos and s stands for sin; α, β and γ are the Euler angles around the Z -, X -and Y -axes; β is the pitch angle and γ is the roll angle. In addition, the counterclockwise direction is positive, and the translation matrix defined by the three-dimensional coordinate transformation is expressed as t = (t x , t y , t z ) T [30]. Consequently, the rotation matrix from the bottom reference coordinate system to the upper alignment coordinate system can be expressed as R 1 = R ; the translation matrix is t 1 = (t x1 , t y1 , t z1 ) T and t = −R 1 t 1 .…”

The Influence of Camera and Optical System Parameters on the Uncertainty of Object Location Measurement in Vision Systems

“…Vision systems have been very popular for over 20 years. They are used not only in military solutions (biometric systems, automatic missile guidance, reconnaissance systems) and technology [ 1 , 2 ] (among others, modern human–computer interfaces, examination of object features, sorting products, inspection of dimensions and contours, checking correctness and completeness of product performance, food control [ 3 ]), but also in medicine (laboratory tests [ 4 ], surgical procedures, telemedicine), cartography and ecology (site map analysis for mineral exploration or pollution monitoring), transport (rail [ 5 , 6 , 7 , 8 , 9 , 10 ], air), the exploration of the Earth and the Universe (interpretation of satellite and astronomical images), and security measures and surveillance, such as reading license plates, detecting explosives at airports, and monitoring crowd behaviour.…”