My research interests are with the design of computer vision systems practical for field robotic applications. Computer vision, although a very promising perceptual tool, has been under-utilized in field robotics because of the difficulties creating reliable systems. It is
the harsh nature of the environments that is especially challenging for computer vision systems. There are field robotic applications where computer vision is the only feasible perceptual mechanism due to its small size, low weight, long working range, and the rich nature of the information it provides. Therefore it is essential to keep researching ways to improve the performance of computer vision systems under challenging conditions in order to further progress the development of field robotics.
My PhD work on visual localisation - while I was at the CSIRO Autonomous Systems Lab and the University of Queensland, Australia - demonstrated that visual systems can in fact perform well in environments where historically lasers and other range sensors were thought to be the only possible sensory modalities for building reliable robotic systems.
My current work at the Carnegie Mellon University - Field Robotics Center is on visual localization and object tracking for small UAVs and coupling these perception tasks with UAV control. Additionally, the other thread of my present work is on wide baseline stereo in urban
settings.
In general, I'm interested in the following research topics;
- Visual localisation/SLAM
- Visual tracking
- Visual motion detection
- Wide baseline stereo
- Quantization of high-dimensional image-feature vectors under viewing
condition disturbances
- Color (chrominance) constancy
- Utilizing lighting models within computer vision systems
- Designing computer vision systems that can operate in non-uniform
dynamic lighting conditions
|
