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

Discriminating small moving objects within complex visual environments is asignificant challenge for autonomous micro robots that are generally limited incomputational power. By exploiting their highly evolved visual systems, flyinginsects can effectively detect mates and track prey during rapid pursuits, eventhough the small targets equate to only a few pixels in their visual field. Thehigh degree of sensitivity to small target movement is supported by a class ofspecialized neurons called small target motion detectors (STMDs). ExistingSTMD-based computational models normally comprise four sequentially arrangedneural layers interconnected via feedforward loops to extract information onsmall target motion from raw visual inputs. However, feedback, anotherimportant regulatory circuit for motion perception, has not been investigatedin the STMD pathway and its functional roles for small target motion detectionare not clear. In this paper, we propose an STMD-based neural network withfeedback connection (Feedback STMD), where the network output is temporallydelayed, then fed back to the lower layers to mediate neural responses. Wecompare the properties of the model with and without the time-delay feedbackloop, and find it shows preference for high-velocity objects. Extensiveexperiments suggest that the Feedback STMD achieves superior detectionperformance for fast-moving small targets, while significantly suppressingbackground false positive movements which display lower velocities. Theproposed feedback model provides an effective solution in robotic visualsystems for detecting fast-moving small targets that are always salient andpotentially threatening.

A Time-Delay Feedback Neural Network for Discriminating Small, Fast-Moving Targets in Complex Dynamic Environments