Inclusion of peripheral correspondences in object and pose estimation for visual servoing path-planning

Abstract

This article addresses the utilization of peripheral image correspondences obtained in cameras obeying the unified model for path-planning-based visual servoing applications. The proposed approach consists of reprojecting available image correspondences onto an oriented virtual plane, which is designed to carry as many reprojections as possible from correspondences, especially those in periphery region. To realize this, a key transformation matrix is proposed and applied to spherical projections of those correspondences. After this transformation, object and pose estimation are realized via the minimization of algebraic and geometric errors by introducing appropriate parametrization and strategies. The geometric error will be defined either on the virtual plane or on the spherical surface. Minimization of error function defined on the spherical surface provides much more accurate estimation results in object structure than that of other error functions as demonstrated in simulation examples. At last, experiment with a fisheye camera mounted on a robot validates the effectiveness of the proposed method.

Keywords

Peripheral correspondence object and pose estimation omnidirectional view visual servoing path-planning

Get full access to this article

View all access options for this article.

References

Chaumette

Hutchinson

Corke

Visual servoing. In: Siciliano

Khatib

(eds) Handbook of robotics. 2nd ed.Berlin: Springer, 2016, pp.841–866.

Shen

Radmard

Chan

et al . Optimized vision-based robot motion planning from multiple demonstrations. Auton Robot 2017; 41: 1–16.

Kneip

Scaramuzza

Siegwart

. A novel parametrization of the perspective-three-point problem for a direct computation of absolute camera position and orientation. In: IEEE conference on computer vision and pattern recognition (CVPR’11), Colorado Springs, CO, 20–25 June 2011, pp.2969–2976. New York: IEEE.

Marchand

Uchiyama

Spindler

Pose estimation for augmented reality: a hands-on survey. IEEE T Vis Comput Gr 2016; 22(12): 2633–2651.

Hartley

RI.

In defense of the eight-point algorithm. IEEE T Pattern Anal 1997; 19(6): 580–593.

Weng

Huang

Ahuja

Motion and structure from two perspective views: algorithms, error analysis, and error estimation. IEEE T Pattern Anal 1989; 11(5): 451–476.

Chesi

Hung

YS.

Fast multiple-view L₂ triangulation with occlusion handling. Comput Vis Image Und 2011; 115(2): 211–223.

Nister

An efficient solution to the five-point relative pose problem. IEEE T Pattern Anal 2004; 26(6): 756–770.

Kneip

Furgale

OpenGV: a unified and generalized approach to real-time calibrated geometric vision. In: IEEE international conference on robotics and automation (ICRA’14), Hong Kong, China, 31 May–7 June 2014, pp.1–8. New York: IEEE.

10.

Triggs

Zisserman

Szeliski

et al . Vision algorithms: theory and practice. In: Triggs

Zisserman

Szeliski

(eds) International workshop on vision algorithms, held during ICCV, Corfu, Greece, September 21-22, 1999, Proceedings. vol. 1883 of lecture notes in computer science. Berlin, Heidelberg: Springer, 2000, pp. x+382.

11.

Dame

Marchand

Using mutual information for appearance-based visual path following. Robot Auton Syst 2013; 61(3): 259–270.

12.

Shen

Radmard

Chan

et al . Motion planning from demonstrations and polynomial optimization for visual servoing applications. In: IEEE/RSJ international conference on intelligent robots and systems (IROS’13), Tokyo, Japan, 3–7 November 2013, pp.578–583. New York: IEEE.

13.

Shen

Chesi

Visual servoing path-planning with elliptical projections. In: Madani

Peaucelle

Gusikhin

(eds) Informatics in control, automation and robotics (LNEE), vol. 430. Cham: Springer, 2017, pp.30–54.

14.

Lima

Simoes

Uchiyama

et al . Depth-assisted rectification for real-time object detection and pose estimation. Mach Vision Appl 2016; 27(2): 193–219.

15.

Tahri

Mezouar

Chaumette

et al . Visual servoing and pose estimation with cameras obeying the unified model. In: Chesi

Hashimoto

(eds) Visual servoing via advanced numerical methods (LNCIS), vol. 401. Berlin: Springer-Verlag, 2010, pp.231–250.

16.

Shen

. Motion and structure estimation for cameras obeying the unified model. In: Proceedings of the 18th world congress: the international federation of automatic control (IFAC’11), Milan, Italy, 28 August–2 September 2011, pp.4747–4752. Laxenburg, Australia: Elsevier.

17.

Courbon

Mezouar

Eckt

et al . A generic fisheye camera model for robotic application. In: IEEE/RSJ international conference on intelligent robots and systems (IROS’07), San Diego, CA, 29 October–2 November 2007, pp.1683–1688. New York: IEEE.

18.

Shen

Chesi

Visual servoing path-planning for cameras obeying the unified model. Adv Robotics 2012; 26(8–9): 843–860.

19.

Mei

Rives

Single view point omnidirectional camera calibration from planar grids. In: IEEE international conference on robotics and automation (ICRA’07), Rome, 10–14 April 2007, pp.3945–3950. New York: IEEE.