SOURCE-LINKED INTELLIGENCE

RoadOcc Learns When to Persist, Transport, or Refresh Memory for Roadside Occupancy Prediction

arXiv · AI, language, vision and robotics · article · Sep 23, 2026 · UTC

Fixed roadside cameras repeatedly observe a stable scene overlaid by sparse moving traffic. Temporal memory can recover weak observations, but reusing moving evidence at stale locations can corrupt occupancy predictions. Motion compensation addresses displacement, while reliance on the resulting history remains a separate learning problem. We introduce RoadOcc, which learns soft routing among fixed-coordinate history (\emph{Persist}), velocity-addressed history (\emph{Transport}), and current evidence (\emph{Refresh}). Motion state and class-consistent historical support supervise these source

Read original source ↗ Open in workspace

recordType

paper

region

Global