Real-time RGB-D-based Object and Manipulator Pose Estimation

Karl Pauwels; Leonardo Rubio; Vladimir Ivan; Sethu Vijayakumar; Eduardo Ros

Real-time RGB-D-based Object and Manipulator Pose Estimation

Karl Pauwels, Leonardo Rubio, Vladimir Ivan, Sethu Vijayakumar, Eduardo Ros

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

We present an overview of our recent work on real-time model-based object pose estimation from intensity and depth cues. We have developed a system that can simultaneously track the pose of hundreds of rigid objects. By incorporating proprioceptive information, objects can be tracked together with their robotic manipulator, enabling accurate visual servo-control even in the presence of severe camera motion. By imposing constraints on the relative poses of object parts, the same system can be used to detect and track the pose of articulated objects as well.

Original language	English
Title of host publication	Workshop on RGB-D: Advanced Reasoning with Depth Cameras, Robotics: Science and Systems (R:SS 2014)
Number of pages	3
Publication status	Published - 2014
Event	RGB-D: Advanced Reasoning with Depth Cameras 2014 - Freiburg im Breisgau, Germany Duration: 12 Jul 2014 → 12 Jul 2014 http://www.cs.cornell.edu/~hema/rgbd-workshop-2014/

Conference

Conference	RGB-D: Advanced Reasoning with Depth Cameras 2014
Abbreviated title	R:SS 2014
Country/Territory	Germany
City	Freiburg im Breisgau
Period	12/07/14 → 12/07/14
Internet address	http://www.cs.cornell.edu/~hema/rgbd-workshop-2014/

Access to Document

pauwels-RSS2014Accepted author manuscript, 3.46 MB

Cite this

@inproceedings{0d14485e2caa475db3b4fdc8aeaae7d7,

title = "Real-time RGB-D-based Object and Manipulator Pose Estimation",

abstract = "We present an overview of our recent work on real-time model-based object pose estimation from intensity and depth cues. We have developed a system that can simultaneously track the pose of hundreds of rigid objects. By incorporating proprioceptive information, objects can be tracked together with their robotic manipulator, enabling accurate visual servo-control even in the presence of severe camera motion. By imposing constraints on the relative poses of object parts, the same system can be used to detect and track the pose of articulated objects as well.",

author = "Karl Pauwels and Leonardo Rubio and Vladimir Ivan and Sethu Vijayakumar and Eduardo Ros",

year = "2014",

language = "English",

booktitle = "Workshop on RGB-D: Advanced Reasoning with Depth Cameras, Robotics: Science and Systems (R:SS 2014)",

note = "RGB-D: Advanced Reasoning with Depth Cameras 2014, R:SS 2014 ; Conference date: 12-07-2014 Through 12-07-2014",

url = "http://www.cs.cornell.edu/~hema/rgbd-workshop-2014/",

}

TY - GEN

T1 - Real-time RGB-D-based Object and Manipulator Pose Estimation

AU - Pauwels, Karl

AU - Rubio, Leonardo

AU - Ivan, Vladimir

AU - Vijayakumar, Sethu

AU - Ros, Eduardo

PY - 2014

Y1 - 2014

N2 - We present an overview of our recent work on real-time model-based object pose estimation from intensity and depth cues. We have developed a system that can simultaneously track the pose of hundreds of rigid objects. By incorporating proprioceptive information, objects can be tracked together with their robotic manipulator, enabling accurate visual servo-control even in the presence of severe camera motion. By imposing constraints on the relative poses of object parts, the same system can be used to detect and track the pose of articulated objects as well.

AB - We present an overview of our recent work on real-time model-based object pose estimation from intensity and depth cues. We have developed a system that can simultaneously track the pose of hundreds of rigid objects. By incorporating proprioceptive information, objects can be tracked together with their robotic manipulator, enabling accurate visual servo-control even in the presence of severe camera motion. By imposing constraints on the relative poses of object parts, the same system can be used to detect and track the pose of articulated objects as well.

M3 - Conference contribution

BT - Workshop on RGB-D: Advanced Reasoning with Depth Cameras, Robotics: Science and Systems (R:SS 2014)

T2 - RGB-D: Advanced Reasoning with Depth Cameras 2014

Y2 - 12 July 2014 through 12 July 2014

ER -

Real-time RGB-D-based Object and Manipulator Pose Estimation

Abstract

Conference

Access to Document

Fingerprint

Cite this