Dr Dylan Campbell

I am a Research Fellow of the Australian Centre for Robotic Vision and the College of Engineering and Computer Science of the Australian National University, where I am supervised by Stephen Gould. Previously, I was a PhD student at the Australian National University and Data61/CSIRO, where I worked on geometric vision problems and was supervised by Lars Petersson, Laurent Kneip and Hongdong Li. I was also a research assistant in the Cyber-Physical Systems group of Data61/CSIRO, where I worked on Resource Constrained Vision. Prior to that, I received a BE in Mechatronic Engineering (Hons) from the University of New South Wales.

I have broad research interests within computer vision and robotics, including geometric vision and human-centred vision. In particular, I have investigated the problem of geometric sensor data alignment, such as camera localisation, simultaneous localisation and mapping, and structure from motion, and the underlying geometry and optimisation problems. Currently, I am increasingly looking at problems of recognising, modelling, and predicting human actions, poses and human-object interactions with a view to facilitate robot-human interaction as part of an Australian Centre for Robotic Vision project.

Dylan Campbell, Lars Petersson, Laurent Kneip and Hongdong Li
Globally-Optimal Inlier Set Maximisation for Camera Pose and Correspondence Estimation
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2018
 
Dylan Campbell, Lars Petersson, Laurent Kneip and Hongdong Li
Globally-Optimal Inlier Set Maximisation for Simultaneous Camera Pose and Feature Correspondence
The 16th International Conference on Computer Vision (ICCV), Venice, Italy, 2017 [Oral Presentation]

Dylan Campbell and Lars Petersson
GOGMA: Globally-Optimal Gaussian Mixture Alignment
The 32nd IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, USA, 2016 [Spotlight]

Jiaolong Yang, Hongdong Li, Dylan Campbell and Yunde Jia
Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registration
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2016

Dylan Campbell and Lars Petersson
An Adaptive Data Representation for Robust Point-Set Registration and Merging
The 15th International Conference on Computer Vision (ICCV), Santiago, Chile, 2015

Dylan Campbell and Mark Whitty
Metric-Based Detection of Robot Kidnapping with an SVM Classifier
Robotics and Autonomous Systems (RAS), 2015

Dylan Campbell and Mark Whitty
Metric-Based Detection of Robot Kidnapping
The 6th European Conference on Mobile Robots (ECMR), Barcelona, Spain, 2013 [Oral Presentation]

Dylan Campbell, Mark Whitty and Samsung Lim
Mobile 3D Indoor Mapping Using the Continuous Normal Distributions Transform
The 3rd International Conference on Indoor Positioning and Indoor Navigation (IPIN), Sydney, Australia, 2012 [Oral Presentation]

Marr Prize Honourable Mention
For: Dylan Campbell, Lars Petersson, Laurent Kneip and Hongdong Li, 2017, "Globally-Optimal Inlier Set Maximisation for Simultaneous Camera Pose and Feature Correspondence", The 16th International Conference on Computer Vision (ICCV), Venice, Italy, IEEE.

1st Prize IEEE Australia Council Postgraduate Student Paper Competition
For: Dylan Campbell, Lars Petersson, Laurent Kneip and Hongdong Li, 2018, "Globally-Optimal Inlier Set Maximisation for Camera Pose and Correspondence Estimation", IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2018

Education

Australian National University / Data61 | CSIRO

PhD Engineering & Computer Science 2013-2018

University of New South Wales

BE Mechatronic (Hons) 2008–2012

Academic Service

Teaching & Tutoring

  • Robotics (ENGN4627/ENGN6627), ANU, 2018 [Guest Lecturer]
  • Computer Vision (ENGN4528/ENGN6528), ANU, 2016–2017
  • Engineering Research & Development Project (ENGN3706), ANU, 2016
  • Elements of Mechatronic Systems (MTRN3200), UNSW, 2013
  • Indigenous Tutorial Assistance Scheme, UNSW, 2013

Conference Program Committee Member / Reviewer and Journal Reviewer

  • Conference on Computer Vision and Pattern Recognition (CVPR), 2015, 2016, 2017, 2019
  • International Conference on Computer Vision (ICCV), 2015, 2017
  • Pattern Recognition (PR), 2018
  • Transactions on Image Processing (TIP), 2016, 2018
  • Image and Vision Computing (IMAVIS), 2018

 

ENGN6000 series courses
Code Title Year 20.. Semester
ENGN6513 Fibre Optics Communications Sy... 18, 19, 20, 21 S1
ENGN4000 series courses
Code Title Year 20.. Semester
ENGN4513 Fibre Optics Communications Sy... 18, 19, 20 S1

Updated:  10 February 2019/Responsible Officer:  Dean, CECS/Page Contact:  CECS Marketing