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) enables autonomous systems to localizethemselves within an environment using image information. While ConvolutionNeural Networks (CNNs) currently dominate state-of-the-art VPR performance,their high computational requirements make them unsuitable for platforms withbudget or size constraints. This has spurred the development of lightweightalgorithms, such as DrosoNet, which employs a voting system based on multiplebio-inspired units. In this paper, we present a novel training approach forDrosoNet, wherein separate models are trained on distinct regions of areference image, allowing them to specialize in the visual features of thatspecific section. Additionally, we introduce a convolutional-like predictionmethod, in which each DrosoNet unit generates a set of place predictions foreach portion of the query image. These predictions are then combined using thepreviously introduced voting system. Our approach significantly improves uponthe VPR performance of previous work while maintaining an extremely compact andlightweight algorithm, making it suitable for resource-constrained platforms.

Patch-DrosoNet: Classifying Image Partitions With Fly-Inspired Models For Lightweight Visual Place Recognition