Visual Behaviors for Docking

Santos-Victor, José; Sandini, Giulio

doi:10.1006/cviu.1997.0528

Cited by 56 publications

(24 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Techniques based on constrained projective geometry determined by robotic embodiment are common in active perceptual-based systems, such as divergent stereo and other systems for docking (e.g., [49]). In divergent stereo, robots navigate along corridors remaining centred between textured walls.…”

Section: Other Active Vision Systemsmentioning

confidence: 99%

Embodied categorisation for vision-guided mobile robots

Barnes

Liu

2004

Pattern Recognition

View full text Add to dashboard Cite

This paper outlines a philosophical and psycho-physiological basis for embodied perception, and develops a framework for conceptual embodiment of vision-guided robots. We argue that categorisation is important in all stages of robot vision. Further, that classical computer vision is unsuitable for this categorisation, however, through conceptual embodiment, active perception can be e ective. We present a methodology for developing vision-guided robots that applies embodiment, explicitly and implicitly, in categorising visual data to facilitate e cient perception and action. Finally, we present systems developed using this methodology, and demonstrate that embodied categorisation can make algorithms more e cient and robust. Crown

show abstract

Section: Other Active Vision Systemsmentioning

confidence: 99%

Embodied categorisation for vision-guided mobile robots

Barnes

Liu

2004

Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…Calculating the derivative of optical flow to estimate TTC further amplifies noise, generally leading to an unstable and unreliable estimate of TTC. Most demonstrations of this approach tend to use highly textured objects in order to obtain a dense velocity fields [3]. Such textured objects may provide a useful laboratory demonstration, but are not generally representative of the objects observed in real world scenes.…”

Section: Introductionmentioning

confidence: 99%

“…When affine camera models are assumed [7], [4], [3], then affine image conditions are required 1 . Camera motion is sometimes restricted to planar motion [3], [8] or to not include vertical displacements [7] or cyclotorsion [8] An alternative approach is to compute TTC from scaled depth [1], [5]. This approach [9] is more complex and can be shown to introduce new constraints and additional errors when these constrains are not fully satisfied.…”

Section: Introductionmentioning

confidence: 99%

A comparison of three methods for measure of Time to Contact

Alenyà

Nègre

Crowley

2009

2009 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

Abstract-Time to Contact (TTC) is a biologically inspired method for obstacle detection and reactive control of motion that does not require scene reconstruction or 3D depth estimation. Estimating TTC is difficult because it requires a stable and reliable estimate of the rate of change of distance between image features. In this paper we propose a new method to measure time to contact, Active Contour Affine Scale (ACAS). We experimentally and analytically compare ACAS with two other recently proposed methods: Scale Invariant Ridge Segments (SIRS), and Image Brightness Derivatives (IBD). Our results show that ACAS provides a more accurate estimation of TTC when the image flow may be approximated by an affine transformation, while SIRS provides an estimate that is generally valid, but may not always be as accurate as ACAS, and IBD systematically over-estimate time to contact.

show abstract

“…To avoid this a priori knowledge, some authors propose modelfree approaches [7], [8] but note that the desired visual features are needed. Other works [9], [10], based on dynamic visual features, do not require the desired image but require a model of the object. Besides, note that, for now, these works are only dedicated to planar objects.…”

Section: Introductionmentioning

confidence: 99%

Using Robust Estimation for Visual Servoing Based on Dynamic Vision

Collewet

Chaumette

2007

Proceedings 2007 IEEE International Conference on Robotics and Automation

View full text Add to dashboard Cite

To cite this version:Christophe Collewet, François Chaumette. Using robust estimation for visual servoing based on dynamic vision. IEEE Int. Conf. on Robotics and Automation, ICRA'07, 2007, Roma, Italy, France. pp.2835-2840, 2007. Using Robust Estimation for Visual Servoing Based on Dynamic VisionChristophe Collewet and François Chaumette Abstract-The aim of this article is to achieve accurate visual servoing tasks when the shape of the object being observed as well as the final image are unknown. More precisely, we want to control the orientation of the tangent plane at a certain point on the object corresponding to the center of a region of interest and to move this point to the principal point to fulfill a fixation task. To do that, we perform a 3D reconstruction phase during the servoing. It is based on the measurement of the 2D displacement in the region of interest and on the measurement of the camera velocity. Since the 2D displacement depends on the scene, we introduce an unified motion model to deal with planar as well with non-planar objects. Unfortunately, this model is only an approximation. In [1], we propose to use active vision to enlarge its domain of validity and a 3D reconstruction based on a continuous approach. In this paper, we propose to use robust estimation techniques and a 3D reconstruction based on discrete approach. Experimental results compare both approaches.

show abstract

Visual Behaviors for Docking

Cited by 56 publications

References 22 publications

Embodied categorisation for vision-guided mobile robots

Embodied categorisation for vision-guided mobile robots

A comparison of three methods for measure of Time to Contact

Using Robust Estimation for Visual Servoing Based on Dynamic Vision

Contact Info

Product

Resources

About