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 dynamic complexity is a ubiquitous, hidden attribute of the visualworld that every dynamic vision system is faced with. However, it is implicitand intractable which has never been quantitatively described due to thedifficulty in defending temporal features correlated to spatial imagecomplexity. To fill this vacancy, we propose a novel bio-robotic approach toprofile visual dynamic complexity which can be used as a new metric. Here weapply a state-of-the-art brain-inspired motion detection neural network modelto explicitly profile such complexity associated with spatial-temporalfrequency (SF-TF) of visual scene. This model is for the first time implementedin an autonomous micro-mobile robot which navigates freely in an arena withvisual walls displaying moving sine-wave grating or cluttered natural scene.The neural dynamic response can make reasonable prediction on surroundingcomplexity since it can be mapped monotonically to varying SF-TF of visualscene. The experiments show this approach is flexible to different visualscenes for profiling the dynamic complexity. We also use this metric as apredictor to investigate the boundary of another collision detection visualsystem performing in changing environment with increasing dynamic complexity.This research demonstrates a new paradigm of using biologically plausiblevisual processing scheme to estimate dynamic complexity of visual scene fromboth spatial and temporal perspectives, which could be beneficial to predictinginput complexity when evaluating dynamic vision systems.

Profiling Visual Dynamic Complexity Using a Bio-Robotic Approach