Publications by authors named "Sylvain Colomer"
Autonomous vehicles require efficient self-localisation mechanisms and cameras are the most common sensors due to their low cost and rich input. However, the computational intensity of visual localisation varies depending on the environment and requires real-time processing and energy-efficient decision-making. FPGAs provide a solution for prototyping and estimating such energy savings.
View Article and Find Full Text PDFArticle Synopsis
- Autonomous vehicles need accurate self-localization for navigation in changing environments, which is addressed by visual place recognition (VPR) that identifies locations despite visual differences.
- The paper introduces the Log-Polar Max-Pi (LPMP) model, a bio-inspired neural network that processes visual data through separate pathways to create a unique visuospatial code for locations.
- Three key contributions include comparing LPMP with other VPR models, proposing a benchmarking test for evaluation, and analyzing how different detection methods affect localization performance.