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

Loop closure detection (LCD) is an indispensable part of simultaneouslocalization and mapping systems (SLAM); it enables robots to produce aconsistent map by recognizing previously visited places. When robots operateover extended periods, robustness to viewpoint and condition changes as well assatisfactory real-time performance become essential requirements for apractical LCD system.  This paper presents an approach to directly utilize the outputs at theintermediate layer of a pre-trained convolutional neural network (CNN) as imagedescriptors. The matching location is determined by matching the imagesequences through a method called SeqCNNSLAM. The utility of SeqCNNSLAM iscomprehensively evaluated in terms of viewpoint and condition invariance.Experiments show that SeqCNNSLAM outperforms state-of-the-art LCD systems, suchas SeqSLAM and Change Removal, in most cases. To allow for the real-timeperformance of SeqCNNSLAM, an acceleration method, A-SeqCNNSLAM, isestablished. This method exploits the location relationship between thematching images of adjacent images to reduce the matching range of the currentimage. Results demonstrate that acceleration of 4-6 is achieved with minimalaccuracy degradation, and the method's runtime satisfies the real-time demand.To extend the applicability of A-SeqCNNSLAM to new environments, a methodcalled O-SeqCNNSLAM is established for the online adjustment of the parametersof A-SeqCNNSLAM.

CNN Feature boosted SeqSLAM for Real-Time Loop Closure Detection