Robust camera pose and scene structure analysis for service robotics

Grigorescu, Sorin Mihai; Macesanu, Gigel; Cocias, Tiberiu T.; Puiu, Dan; Moldoveanu, Florica

doi:10.1016/j.robot.2011.07.005

Cited by 23 publications

(14 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The orientation angle difference ψ between the platform and the rotating camera is included in the image-based controller by using the concept of an infinite "virtual image plane," which is obtained by rotating the physical image plane by the varying angle ψ (which is continuously measured by the camera) [33,34]. In this way, the platform and the camera point in the same direction, and the controller gains J y im K can be used in the standard way by introducing to J y im the transformed feature values corresponding to the virtual image plane.…”

Section: Image-based Mobile Robot Visual Servoingmentioning

confidence: 99%

Mobile Robot Control V

Tzafestas

2014

Introduction to Mobile Robot Control

View full text Add to dashboard Cite

Section: Image-based Mobile Robot Visual Servoingmentioning

confidence: 99%

Mobile Robot Control V

Tzafestas

2014

Introduction to Mobile Robot Control

View full text Add to dashboard Cite

“…The second process, suppose to transforms each pair of correspondent 2D pixels into 3D points. For determining the new position, the following relations are used [14]:…”

Section: D Pose Estimationmentioning

confidence: 99%

Real time facial features tracking using an active vision system

Macessanu

Grigorescu

Ferreira

et al. 2012

2012 13th International Conference on Optimization of Electrical and Electronic Equipment (OPTIM)

Self Cite

View full text Add to dashboard Cite

In this paper, an active vision system used for real time facial features tracking is presented, where a human head region is searched using a stereo camera. This region is divided such that a person's nose will be searched in a smaller spatial domain. The 2D coordinates of the nose are determined based on a Haar classifier and colour segmentation. Its 3D coordinates, computed via the constraints of the epipolar geometry, represent a reference signal used within a control system for controling the stereo camera's pan and tilt. A method for determining the system's parameters and for designing a proper controller is further proposed. The controller is design such that it integrates the maximum time delay that can be inserted into the control system by the machine vision component. Finally, the overall architecture is tested in a real facial feature tracking application.

show abstract

“…The block diagram of the proposed scene perception system can be seen in figure 1. The reference coordinates of the obtained visual information is related to the on-line determined position and orientation (pose) of a robot, that is, of a robot's stereo camera system (Grigorescu et al, 2011). Once a certain pose is determined, the imaged scene can be reconstructed and segmented for the purpose of environment understanding.…”

Section: Machine Vision Aparatusmentioning

confidence: 99%

Object Volumetric Estimation Based on Generic Fitted Primitives for Service Robotics

Cocias

Grigorescu

Moldoveanu

2012

Proceedings of the International Conference on Computer Vision Theory and Applications

View full text Add to dashboard Cite

This paper present an approach for object surface estimation from a single perspective using a stereo camera configuration. The goal of the method is to capture the particularity of an object of interest by fitting a generic primitive who best models the recognized shape. The shape modeling process is performed on 3D Regions of Interest (ROI) obtained by classifying the objects present in disparity maps. The principle uses a number of control points, calculated from the primitive Point Distribution Model (PDM). These control points drive the modeling behavior in the disparity point cloud data based on the principle of active contours, or snakes. Finally a compact 3D object mesh can be generated using Delaunay triangulation. The obtained PDM models are intended to be used for the purpose of precise object manipulation in service robotics applications.

show abstract

Robust camera pose and scene structure analysis for service robotics

Cited by 23 publications

References 20 publications

Mobile Robot Control V

Mobile Robot Control V

Real time facial features tracking using an active vision system

Object Volumetric Estimation Based on Generic Fitted Primitives for Service Robotics

Contact Info

Product

Resources

About