Precision 3-D motion tracking for binocular microscopic vision system

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalNot applicablepeer-review

1 Scopus Citations
View graph of relations

Author(s)

Detail(s)

Original languageEnglish
Article number8624552
Pages (from-to)9339-9349
Journal / PublicationIEEE Transactions on Industrial Electronics
Volume66
Issue number12
Online published23 Jan 2019
Publication statusPublished - Dec 2019

Abstract

In this paper, a three-dimensional (3-D) motion tracking method is proposed for binocular microscopic vision system to precisely record the motion trajectories of millimeter size objects in the Cartesian space. Primarily two fundamental problems are solved. The first problem arises from the limited depth of field (DOF) of microscope. Considering the motion of the objects, the existing autofocusing methods requiring sequential images either in focus or defocus are not workable. Therefore, a one-shot prior autofocusing approach is desired, which needs to take the motion tendency of objects into account. Besides, the autofocusing process always lags behind the motion of objects, and there inevitably will be prediction deviation on the motion tendency of objects. This leads to the second problem to estimate the 3-D motion states from defocused images. In this paper, we first explain the defocusing process from the perspective of S-Transform, based on which the Bayesian inference inspired method to estimate the depth from defocus from one single image is derived thereafter. Afterwards, a motion states, including both the position and velocity, estimation approach is developed within the Kalman filter framework. The above two aspects mutually supply the necessary information for each other to be functional to accurately realize the DOF tracking and motion tracking of moving objects. Experiments were well-designed to validate the effectiveness of the proposed method, and experiments result showed a tracking precision of 3 μm was achieved.

Research Area(s)

  • Bayesian inference, binocular microscopic vision, depth of field (DOF) tracking, Kalman filtering, Three-dimensional (3-D) motion tracking