Search Results for author: Mihnea-Alexandru Tomita

Found 3 papers, 0 papers with code

Data-Efficient Sequence-Based Visual Place Recognition with Highly Compressed JPEG Images

no code implementations26 Feb 2023 Mihnea-Alexandru Tomita, Bruno Ferrarini, Michael Milford, Klaus McDonald-Maier, Shoaib Ehsan

The sequence length that enables 100% place matching performance is reported and an analysis of the amount of data required for each VPR technique to perform the transfer on the entire spectrum of JPEG compression is provided.

Image Compression Visual Place Recognition

Data Efficient Visual Place Recognition Using Extremely JPEG-Compressed Images

no code implementations17 Sep 2022 Mihnea-Alexandru Tomita, Bruno Ferrarini, Michael Milford, Klaus McDonald-Maier, Shoaib Ehsan

Moreover, this paper demonstrates how fine-tuning a CNN can be utilised as an optimisation method for JPEG compressed data to perform more consistently with the image transformations detected in extremely JPEG compressed images.

Image Compression Visual Place Recognition

Cannot find the paper you are looking for? You can Submit a new open access paper.