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

We introduce a novel learning-based method for view birdification, the taskof recovering ground-plane trajectories of pedestrians of a crowd and theirobserver in the same crowd just from the observed ego-centric video. Viewbirdification becomes essential for mobile robot navigation and localization indense crowds where the static background is hard to see and reliably track. Itis challenging mainly for two reasons; i) absolute trajectories of pedestriansare entangled with the movement of the observer which needs to be decoupledfrom their observed relative movements in the ego-centric video, and ii) acrowd motion model describing the pedestrian movement interactions is specificto the scene yet unknown a priori. For this, we introduce a Transformer-basednetwork referred to as ViewBirdiformer which implicitly models the crowd motionthrough self-attention and decomposes relative 2D movement observations ontothe ground-plane trajectories of the crowd and the camera throughcross-attention between views. Most important, ViewBirdiformer achieves viewbirdification in a single forward pass which opens the door to accuratereal-time, always-on situational awareness. Extensive experimental resultsdemonstrate that ViewBirdiformer achieves accuracy similar to or better thanstate-of-the-art with three orders of magnitude reduction in execution time.

ViewBirdiformer: Learning to recover ground-plane crowd trajectories and ego-motion from a single ego-centric view