Study of Pose Detection Algorithm for Specific Object Based on Monocular Vision

Abstract

This paper brings forward a monocular vision detection algorithm in allusion to the specific object’s pose based on Hausdorff Distance. At first, according to the mathematic model which has been established, the 2D template sequence is generated by projecting the specific object in different poses into the image plane of a virtual camera. Then, in order to predigest calculations and accelerate the matching speed during the image matching, the algorithm adopts the local-mean Hausdorff Distance as matching estimate and adopts the search strategy based on hiberarchy which reduces the searching rang by the threshold method before accurate match. In the end of this paper, the experiment that measures the poses of the clamp via the different clamp images respectively is given to testify the validity and speediness of this algorithm.

Pose Determination of a Robot Manipulator Based on Monocular Vision

“…The multivariate nonlinear regression is also performed by a Matlab function nlinfit. The objective functions are the residuals of ( 8) to (19), which are the same as (22) and will be minimized to estimate the eight parameters as…”

“…Chen et al [18] proposed a pose determination method using monocular vision, where a quaternion formulation of four feature points is used to develop six nonlinear equations on the image coordinates. Liu et al [19] presented a monocular vision detection algorithm, where the different poses of the object are projected onto a virtual camera and the local-mean Hausdorff Distance is used to accelerate the image matching. Wu et al [20] developed a method to measure the position and attitude parameters of a weld stud using monocular vision, where the mathematical model related to the position and attitude of the weld stud is included.…”