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

Drone-to-drone detection using visual feed has crucial applications, such asdetecting drone collisions, detecting drone attacks, or coordinating flightwith other drones. However, existing methods are computationally costly, follownon-end-to-end optimization, and have complex multi-stage pipelines, makingthem less suitable for real-time deployment on edge devices. In this work, wepropose a simple yet effective framework, \textit{TransVisDrone}, that providesan end-to-end solution with higher computational efficiency. We utilizeCSPDarkNet-53 network to learn object-related spatial features and VideoSwinmodel to improve drone detection in challenging scenarios by learningspatio-temporal dependencies of drone motion. Our method achievesstate-of-the-art performance on three challenging real-world datasets (AveragePrecision@0.5IOU): NPS 0.95, FLDrones 0.75, and AOT 0.80, and a higherthroughput than previous methods. We also demonstrate its deployment capabilityon edge devices and its usefulness in detecting drone-collision (encounter).Project: \url{https://tusharsangam.github.io/TransVisDrone-project-page/}.

TransVisDrone: Spatio-Temporal Transformer for Vision-based Drone-to-Drone Detection in Aerial Videos