English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Sequence-based place recognition methods for all-weather navigation arewell-known for producing state-of-the-art results under challenging day-nightor summer-winter transitions. These systems, however, rely on complexhandcrafted heuristics for sequential matching - which are applied on top of apre-computed pairwise similarity matrix between reference and query imagesequences of a single route - to further reduce false-positive rates comparedto single-frame retrieval methods. As a result, performing multi-frame placerecognition can be extremely slow for deployment on autonomous vehicles orevaluation on large datasets, and fail when using relatively short parametervalues such as a sequence length of 2 frames. In this paper, we proposeDeepSeqSLAM: a trainable CNN+RNN architecture for jointly learning visual andpositional representations from a single monocular image sequence of a route.We demonstrate our approach on two large benchmark datasets, Nordland andOxford RobotCar - recorded over 728 km and 10 km routes, respectively, eachduring 1 year with multiple seasons, weather, and lighting conditions. OnNordland, we compare our method to two state-of-the-art sequence-based methodsacross the entire route under summer-winter changes using a sequence length of2 and show that our approach can get over 72% AUC compared to 27% AUC for DeltaDescriptors and 2% AUC for SeqSLAM; while drastically reducing the deploymenttime from around 1 hour to 1 minute against both. The framework code and videoare available at https://mchancan.github.io/deepseqslam

DeepSeqSLAM: A Trainable CNN+RNN for Joint Global Description and Sequence-based Place Recognition