am a faculty member of the College of
Engineering and Computer Science,
(Australian National University). I do research in Computer Vision,
Pattern Recognition, Image Processing and Machine
Learning @ANU. My main interests
include 3D Vision, Robot Vision, Visual Odometry, UAV and robot navigation, Computer
Graphics, Virtual and Augmented Reality,
Optimisation, Pattern Recognition and Deep Learning.
Currently I am a Chief Investigator and Deputy Theme Leader for Australia
ARC Centre of Excellence for Robotic Vision. I serve in the Program Committees and Area Chair for CVPR, IEEE ICCV, ECCV and
BMVC, and an Associate
Editor for IET-Computer Vision,
IVC-Journal of Image and Vision Computing, ISPJ Journal of CVA (Computer
Vision and Application), etc. I
serve the Area Chair for IEEE ICCV, CVPR, and
ECCV in recent years, as well as an Area Chair for BMVC and
3DV, etc. I am a Program Co-Chair for ACRA 2015 (Australiasian conference on robotics and
automation), Program Co-Chair for the 1st International workshop
on Big Data in 3D Computer Vision at ICCV’13, Application of Computer Vision in
Biological Science workshop at ICCV’13, and Area Chair for ECCV 2016.
Previously, I was a contributing researcher to the Bionic Vision Australia and as an
AI-Associate Investigator on the ARC-funded Australia Bionic Eye Project
(special initiative). Prior to 2010
I was a Fellow with
the RSISE @ ANU and a Senior Research Scientist with
NICTA (National ICT Australia), Canberra
Labs, where I am greatly privileged to be working under the mentoring
of Professor Richard
Hartley who is a pioneer researcher in 3D computer vision and a
co-author of MVG (the
bible in Multiview
link) , Professor Hartley and Professor
A. Zisserman). My research
career in 3D computer vision started from my post-doc period under Richard’s supervision.
researches have been funded by the ARC (Australia Research Council), ARC
Centre of Excellence, National ICT Australia (NICTA), Bionic Vision
Australia (via the Australia Bionic Eye project), Microsoft Research (via
an ARC Linakge grant), NSFC (National Natural Science Foundation of China,
as International Partner Investigator), as well as global companies and
manufacturers (Toshiba, JVC, Microsoft Australia, General Motors,
etc.). Potential practical
application areas include 3D reconstruction, 3D modelling, virtual reality
and augmented reality, robot vision navigation and SLAM, machine learning,
multimedia information retrieval, autonomous
driving, human robot interaction, image understanding, medical imaging,
visual data analysis, and UAV drone autonomous flying, visual guidance.
In the past,
jointly with my PhD students I have won a number of prestigious awards in
Computer Vision research, including the CVPR Best Paper Award,
IEEE ICPR Best Student Paper Award, IEEE ICIP Best Student Paper Award,
DSTO Best Paper Prize, CiSRA Best Paper Award at DICTA.
I have supervised and co-supervised over 20 PhD
students, most of them in the area of Computer Vision and Pattern
recognition, Image processing, Geometry, Robotic Vision, and Machine
Learning. ANU has various
scholarship schemes available for PhD applicants. We also welcome students with other
source of funding (e.g. Chinese CSC scholarship, Brazilian, and Chilean
Government PhD Scholarship) to apply the ANU Computer Vision PhD
Program. I obtained my PhD and MSc
degree from Zhejiang University China, where I conducted research in
robotics, and pattern classification.
I was a member of the ALV research group –China’s first autonomous
ANU is the finest research university in
Australia, located in the beautiful “Bush Capital”- city of Canberra.
Current Research Projects
Novel Camera Sensors for
robust robotic vision (funded by ARC Centre of Excellence for Robotic
Unorganised image based
City-scale 3D modelling (funded by an ARC Discovery project).
Visual Navigation for
autonomous driving cars (self-driving cars, funded by a global automobile
and human-computer interaction for medical images (funded by Microsoft Research,
via an ARC Linkage grant).
Non-rigid Shape and Motion
Capture and Motion Segmentation via subspace or sub-manifold clustering.
Global optimisation and
inference for MRF/CRF.
Artificial neural networks
and deep learning for visual object tracking and object detection.
Mathematics Optimisation in
low level computer vision problems.
Autonomous driving/flying of
in all-weather conditions.
Dr. Yuchao Dai, ARC DECRA
Dr. Laurent Kneip, ARC DECRA
Dr. Viorela Ila, ACRV
Dr. Anoop Cherian, ACRV
Dr. Dingfu Zhou, ANU Postdoctoral Fellow
The CVPR, ICCV and
ECCV are premier conferences in Computer Vision research community. The
IEEE TPAMI,TIP, IJCV are top journals in the field of computer
vision, image and pattern recognition.
Learning image matching by watching a video, ECCV 2016
Rolling Shutter Camera Relative Pose, IEEE CVPR 2016
Flow Estimation of Double-Layer Images under Transparency or
Reflection, IEEE CVPR 2016
Search: Tracking Objects Everywhere with Instance-Specific Proposals,
IEEE CVPR 2016
Feature Tracker: A Segmentation-free Approach, IEEE CVPR 2016
Pan Ji, Mathieu
Salzmann, Hongdong Li,
Matrix Revisited and Robustified: Efficient
Subspace Clustering with Corrupted and Incomplete Data, IEEE ICCV 2015, Oral (3%
Hongyu Wang, Hongdong Li, Xiuqing
Ye, Weikang Gu: Training an artificial neural networks
for image edge detection,
JZJU-Science, vol-2, 2000.
3D computer vision for self-driving car: Visual odometry
and vehicle egomotion estimation for autonomous
driving using side-viewing multiple-camera rig, TR-ANU-CVRG, Jan. 2016.
Alvaro Parra Bustos, Tat-Jun Chin, et
al, Fast Rotation
Search with Stereographic Projections for 3D Registration, accepted by
IEEE T-PAMI, 2016.
A. Thalaiyasingam, R.
Hartley, M. Salzmann and H. Li
Reweighted Ishikawa Graph Cut for Multi-label MRFs with Non-convex
IEEE Conference on Computer Vision and
Pattern Recognition (CVPR), Boston, MA, June 2015.
Jiaolong Yang, Hongdong Li,
Highly-Accurate Optical Flow Computation: the Piecewise Parametric Model
IEEE Conference on Computer Vision and
Pattern Recognition (CVPR), Boston, MA, June 2015. ( Code will be
method for multibody motion segmentation with unknown correspondences, in ECCV
Ji, Mathieu Salzmann, Hongdong
Efficient dense subspace clustering.
IEEE WACV 2014:
Sadeep Jayasumana, Richard Hartley, Mathieu Salzmann, Hongdong Li and
Combining Multiple Manifold-valued
Descriptors for Improved Object Recognition, IEEE DICTA 2013, CiSRA"Best Recognition Paper Award".
Yansheng Ming, Hongdong Li, Xuming He
Contour Cue and Region cue Salient Image Segmentation
(PDF coming soon..).
IEEE CVPR 2013 (poster).
< For more papers,
please see Publications