Research on pose estimation for stereo vision measurement system by an improved method: uncertainty weighted stereopsis pose solution method based on projection vector

Abstract

We present UWSPSM, an algorithm of uncertainty weighted stereopsis pose solution method based on the projection vector which to solve the problem of pose estimation for stereo vision measurement system based on feature points. Firstly, we use a covariance matrix to represent the direction uncertainty of feature points, and utilize projection matrix to integrate the direction uncertainty of feature points into stereo-vision pose estimation. Then, the optimal translation vector is solved based on the projection vector of feature points, as well the depth is updated by the projection vector of feature points. In the absolute azimuth solution stage, the singular value decomposition algorithm is used to calculate the relative attitude matrix, and the above two stages are iteratively performed until the result converges. Finally, the convergence of the proposed algorithm is proved, from the theoretical point of view, by the global convergence theorem. Expanded into stereo-vision, the fixed relationship constraint between cameras is introduced into the stereoscopic pose estimation, so that only one pose parameter of the two images captured is optimized in the iterative process, and the two cameras are better bound as a camera, it can improve accuracy and efficiency while enhancing measurement reliability. The experimental results show that the proposed pose estimation algorithm can converge quickly, has high-precision and good robustness, and can tolerate different degrees of error uncertainty. So, it has useful practical application prospects.

Optical character recognition (OCR) using partial least square (PLS) based feature reduction: an application to artificial intelligence for biometric identification

“…In this step, the presented algorithm extracts two types of features for classification including geometric feature and texture features from output of ROI ψtrue(finalimgtrue). One geometric feature that is histogram of oriented gradient (HOG) (Hong et al , 2020; Kazmi et al , 2020) and two texture features including local binary pattern (LBP) and Haralick features (Al-wajih and Ghazali, 2020; Cui et al , 2020) are extracted. In order to extract Haralick features, the proposed algorithm extracted 14 Haralick texture features from GLCM, which are described in Table 1.…”

Human Motion Gesture Recognition Based on Computer Vision

“…e literature [6,7] uses the HOG method to extract the information of each part of the human body in the image and then uses the classical algorithm support vector machine and random forest to identify and classify. Cui et al [8] found the global optimal features from many features such as Fourier descriptors, shape context, edges, and gradients to quickly and accurately complete the backprojection process from features to three-dimensional poses. Zhang and Lu [9] used the histogram of gradient directions to restore the human pose and trained multiple local linear regressions to restore the human pose in a single frame of image.…”

Calibration and uncertainty analysis of a combined tracking-based vision measurement system using Monte Carlo simulation

“…However, input parameters other than stereo angles were not considered, which may affect the evaluation accuracy. Cui et al [27] presented an uncertainty weighted pose measurement method, in which the covariance matrix was utilized to determine the direction of the feature points' uncertainty that was integrated into the stereovision pose estimation by the projection matrix. This method improves the accuracy of pose estimation.…”