Interpreting The Movement

Sculpture A

Sculpture B

Sculpture C

Sculpture D

Research & Development

Credits

Accessing the Data

To make the data tangible, we built a custom Python importer to parse raw .bin files from the nuScenes dataset, unlocking LiDAR point clouds, radar returns, camera feeds, and spatial object recognition data simultaneously.

From this we simulated how every point must move toward its nearest detected object, reconstructing the landscape of risk and awareness an autonomous vehicle must continuously navigate.

Not a map of the world as we see it, but as an AV must.

Research & Development

The Process

We started with footage of animals moving in groups - pigeons over a hillside, squirrels close to camera, pronghorns darting across a landscape. From there, we used Claude Code to build a custom tracking pipeline inside ComfyUI, combining Meta's SAM3 segmentation model with Hungarian algorithm tracking to identify and follow individual animals across every frame.

⠘

The pipeline runs in two phases. First, SAM3 segments and tracks each subject, assigning a persistent ID across the sequence. Second, Claude reads every tenth frame alongside the SAM3 tracking data and conducts a behavioural analysis of the collective - then breaks that reading into five separate lenses, each interpreting the scene through a different analytical frame: movement, hierarchy, hesitation, deviation, consensus.

⠯

All of it - the tracking data, the IDs, the behavioural labels, the lens groupings, is all exported to Houdini as geometry. Every animal carries its reading with it. The footage becomes a dataset that can be re-lit, re-rendered, and re-interpreted.

⠳

The Flight

⠾

The Feed

⠭

The Hunt

⠭

Research and Development

⠻