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

Autonomous driving perception techniques are typically based on supervisedmachine learning models that are trained on real-world street data. A typicaltraining process involves capturing images with a single car model andwindshield configuration. However, deploying these trained models on differentcar types can lead to a domain shift, which can potentially hurt the neuralnetworks performance and violate working ADAS requirements. To address thisissue, this paper investigates the domain shift problem further by evaluatingthe sensitivity of two perception models to different windshieldconfigurations. This is done by evaluating the dependencies between neuralnetwork benchmark metrics and optical merit functions by applying a Fourieroptics based threat model. Our results show that there is a performance gapintroduced by windshields and existing optical metrics used for posingrequirements might not be sufficient.

Sensitivity analysis of AI-based algorithms for autonomous driving on optical wavefront aberrations induced by the windshield