TU Darmstadt / ULB / TUbiblio

Mutual Information-Based Tracking for Multiple Cameras and Multiple Planes

Wen, Zhuoman and Kuijper, Arjan and Fraissinet-Tachet, Matthieu and Wang, Yanjie and Luo, Jun (2017):
Mutual Information-Based Tracking for Multiple Cameras and Multiple Planes.
In: Arabian Journal for Science and Engineering, 42 (8), pp. 3451-3463. ISSN 2193-567X,
DOI: 10.1007/s13369-017-2541-z,
[Article]

Abstract

Based onmutual information (MI), this paper proposes a systematic analysis of tracking a multi-plane object with multiple cameras. Firstly, a geometric model consisting of a piecewise planar object and multiple cameras is setup. Given an initial pose guess, the method seeks a pose update that maximizes the global MI of all the pairs of reference image and camera image. An object pose-dependent warp is proposed to ensure computation precision. Six variations of the proposed method are designed and tested. Mode 1, i.e., computing the 2nd-order Hessian of MI at each step as the object pose changes, leads to the highest convergence rates; Mode 2, i.e., computing the 1st-order Hessian of MI once at the beginning, occupies the least time (0.5-1.0 s). For objects with simple-textured planes, applying Gaussian blur first and then useMode 1 shall generate the highest convergence rate.

Item Type: Article
Erschienen: 2017
Creators: Wen, Zhuoman and Kuijper, Arjan and Fraissinet-Tachet, Matthieu and Wang, Yanjie and Luo, Jun
Title: Mutual Information-Based Tracking for Multiple Cameras and Multiple Planes
Language: English
Abstract:

Based onmutual information (MI), this paper proposes a systematic analysis of tracking a multi-plane object with multiple cameras. Firstly, a geometric model consisting of a piecewise planar object and multiple cameras is setup. Given an initial pose guess, the method seeks a pose update that maximizes the global MI of all the pairs of reference image and camera image. An object pose-dependent warp is proposed to ensure computation precision. Six variations of the proposed method are designed and tested. Mode 1, i.e., computing the 2nd-order Hessian of MI at each step as the object pose changes, leads to the highest convergence rates; Mode 2, i.e., computing the 1st-order Hessian of MI once at the beginning, occupies the least time (0.5-1.0 s). For objects with simple-textured planes, applying Gaussian blur first and then useMode 1 shall generate the highest convergence rate.

Journal or Publication Title: Arabian Journal for Science and Engineering
Journal volume: 42
Number: 8
Uncontrolled Keywords: Computer vision, Camera tracking, Image registration, Mutual information (MI), Nonlinear optimization
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Mathematical and Applied Visual Computing
Date Deposited: 04 May 2020 12:41
DOI: 10.1007/s13369-017-2541-z
Official URL: https://link.springer.com/journal/13369/42/8/page/2
Export:
Suche nach Titel in: TUfind oder in Google
Send an inquiry Send an inquiry

Options (only for editors)
Show editorial Details Show editorial Details