Controlling Depth Estimation for Robust Robotic Perception

Grigorescu, Sorin Mihai; Moldoveanu, Florica

doi:10.3182/20110828-6-it-1002.00436

Cited by 3 publications

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Knowing the geometry of the stereo camera, the ROI vector can be reprojected into a virtual 3D environment by calculating the disparity between p L i and p R i (Brown et al, 2003). The volumetric properties of the ROI, namely its 3D volume, are calculated from the reprojected depth map, that is, from the 3D distribution of the disparity points calculated using the robust Block Matching approach from (Grigorescu and Moldoveanu, 2011). The center of the ROI over the Z axis is given by the highest disparity points density obtained as a maximization over the disparity value.…”

Section: D Object Volumetric Modelingmentioning

confidence: 99%

STEREO VISION-BASED 3D CAMERA POSE AND OBJECT STRUCTURE ESTIMATION - An Application to Service Robotics

Grigorescu

Cocias

Macesanu

et al. 2012

Proceedings of the International Conference on Computer Vision Theory and Applications

View full text Add to dashboard Cite

In this paper, a robotic pose (position and orientation) estimation and volumetric object modeling system is proposed. The main goal of the methods is to reliably detect the structure of objects of interest present in a visualized robotic scene, together with a precise estimation of the robot's pose with respect to the detected objects. The robustness of the robotic pose estimation module is achieved by filtering the 2D correspondence matches in order to detect false positives. Once the pose of the robot is obtained, the volumetric structure of the imaged objects of interest is reconstructed through 3D shape primitives and a 3D Region of Interest (ROI).

show abstract

Section: D Object Volumetric Modelingmentioning

confidence: 99%