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/

Zendy Plus

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

Zendy Tools

Zendy Open

Path prediction is an essential task for many real-world Cyber-PhysicalSystems (CPS) applications, from autonomous driving and trafficmonitoring/management to pedestrian/worker safety. These real-world CPSapplications need a robust, lightweight path prediction that can provide auniversal network architecture for multiple subjects (e.g., pedestrians andvehicles) from different perspectives. However, most existing algorithms aretailor-made for a unique subject with a specific camera perspective andscenario. This article presents Pishgu, a universal lightweight networkarchitecture, as a robust and holistic solution for path prediction. Pishgu'sarchitecture can adapt to multiple path prediction domains with differentsubjects (vehicles, pedestrians), perspectives (bird's-eye, high-angle), andscenes (sidewalk, highway). Our proposed architecture captures theinter-dependencies within the subjects in each frame by taking advantage ofGraph Isomorphism Networks and the attention module. We separately train andevaluate the efficacy of our architecture on three different CPS domains acrossmultiple perspectives (vehicle bird's-eye view, pedestrian bird's-eye view, andhuman high-angle view). Pishgu outperforms state-of-the-art solutions in thevehicle bird's-eye view domain by 42% and 61% and pedestrian high-angle viewdomain by 23% and 22% in terms of ADE and FDE, respectively. Additionally, weanalyze the domain-specific details for various datasets to understand theireffect on path prediction and model interpretation. Finally, we report thelatency and throughput for all three domains on multiple embedded platformsshowcasing the robustness and adaptability of Pishgu for real-world integrationinto CPS applications.

Pishgu: Universal Path Prediction Network Architecture for Real-time Cyber-physical Edge Systems