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

Visual place recognition (VPR) is one of the research hotspots in robotics,which uses visual information to locate robots. Recently, the hierarchicaltwo-stage VPR methods have become popular in this field due to the trade-offbetween accuracy and efficiency. These methods retrieve the top-k candidateimages using the global features in the first stage, then re-rank thecandidates by matching the local features in the second stage. However, theyusually require additional algorithms (e.g. RANSAC) for geometric consistencyverification in re-ranking, which is time-consuming. Here we propose aDynamically Aligning Local Features (DALF) algorithm to align the localfeatures under spatial constraints. It is significantly more efficient than themethods that need geometric consistency verification. We present a unifiednetwork capable of extracting global features for retrieving candidates via anaggregation module and aligning local features for re-ranking via the DALFalignment module. We call this network AANet. Meanwhile, many works use thesimplest positive samples in triplet for weakly supervised training, whichlimits the ability of the network to recognize harder positive pairs. Toaddress this issue, we propose a Semi-hard Positive Sample Mining (ShPSM)strategy to select appropriate hard positive images for training more robustVPR networks. Extensive experiments on four benchmark VPR datasets show thatthe proposed AANet can outperform several state-of-the-art methods with lesstime consumption. The code is released at https://github.com/Lu-Feng/AANet.

AANet: Aggregation and Alignment Network with Semi-hard Positive Sample Mining for Hierarchical Place Recognition