IEEE SPS @ UF

Vie — biologically plausible real-time video scene analysis

A computer-vision research project targeting real-time perception of dynamic and static scene entities with a path toward wearable integration.

Research / IEEE SPS projects / Vie — biologically plausible real-time video scene analysis
Back to IEEE SPS projects GitHub
Vie project logo.

Overview

Vie investigates real-time machine perception systems that jointly model moving and static objects, with reproducible data engineering and demo-first iteration.

Vie is centered on biologically inspired scene analysis: learning dynamic interactions in complex environments while maintaining real-time system behavior suitable for downstream deployment contexts.

What I built

  • A research plan for benchmarking scene-perception baselines and defining evaluation criteria.
  • A data pipeline direction that includes segmentation/annotation workflow and reproducibility standards.
  • A milestone path from prototype perception models to a conference-grade demo and paper artifacts.

Snapshot

Track
IEEE SPS @ UF · computer vision · CVPR track
Status
Active; dataset and initial model pipeline in progress.
Focus
Scene understandingReal-time perceptionDataset + annotation pipeline

Stack

  • Python vision tooling
  • Dataset engineering + annotation
  • Real-time inference prototyping

Glossary

Dynamic entities
Objects in a scene whose state changes over time (for example, people or vehicles in motion).