Geometry & SLAM
Novel Camera Architectures for Localization and Mapping on Intelligent Mobile Platforms
Doctoral thesis · Australian National University · PQDT-Global · 2021
RESEARCH SUMMARY
This PhD thesis studies localization and mapping with surround-view multi-camera systems and event cameras, linking sensor geometry, vehicle motion constraints and continuous-time estimation.
Read the supporting paper ↗THE RESEARCH QUESTION
What connects surround-view cameras and event-based localization?
Both architectures offer alternatives to conventional vision-only navigation: wider geometric coverage in one case, and precise change measurements under difficult imaging conditions in the other. [Paper]
How the method works
- The multi-camera work covers metric-scale initialization, relative motion and spline-based trajectory refinement.
- The event-camera work investigates globally optimized motion estimation and joint motion–structure estimation through volumetric contrast.
RESEARCH INTERPRETATION
What this contribution means
The thesis connects front-end initialization with back-end refinement across complementary sensing architectures. This overview follows the ANU repository abstract; individual papers linked below provide focused technical treatments.
This section explains the contribution in context. For experimental protocols, numerical results and comparisons, consult the original paper.
Scope and limitations
The chapters address different assumptions and motion models. Their guarantees should be read individually rather than combined into a universal navigation claim. [Paper]
Questions about this research
Where is the official thesis record?
The Australian National University's open research repository hosts the thesis record and download.
Sources, paper & code
Primary research sources support the summary above. Project resources provide demonstrations or implementations; Google Scholar is a bibliographic index.
- Primary sourceANU — official thesis record ↗openresearch-repository.anu.edu.au
- Primary sourceFull paper — PDF ↗openresearch-repository.anu.edu.au
- Metadata indexGoogle Scholar — bibliographic listing ↗scholar.google.com