Barnes Maze Pipeline

Drag a video here, or

Browse for a video file

Already tracked this one?

Working through several trials?

New here? - fetches a real sample clip and its saved analysis, no video of your own required.

Video & file metadata

Mouse tracking

Measures

Click a measure's name for its definition and how it's calculated. A row marked audited was changed by a human-review override above - re-click "Compute measures" after changing one to recalculate.

Search strategy

Spatial (direct) / serial / random, per Gawel et al. 2019 (Table 1, citing O'Leary & Brown) - not invented here. Exactly one pattern must match to get a verdict; otherwise it's UNCLEAR and all three scores are shown for you to audit against the hole sequence, rather than forcing a guess.

Serial bar Random bar

Export

One tidy row for this trial: every measure above, the search-strategy verdict, the thresholds that produced them, and the tool version - opens directly in Excel, no legend needed. "Video file" is always included, so every exported row stays traceable on its own.

Label audited values (adds "(audited)" to a measure's value when a human correction changed it)

Per-event detail: one row per hole visit (matches Merged Visits above, overrides included) - the "long form" alongside the trial summary's "short form."

Mouse tracking, events, measures, and search strategy review still live in the middle column for now - only background and ROI confirmation have moved up here so far.

Background

Load a video first.

Platform & holes

Compute the background first.

Hough circles on the background: one big circle for the platform, ~20 small ones on its rim for the holes, indexed in ring order by angle.

Detection compute details

Confirm & adjust

Drag a circle's edge to resize it, drag its middle to move it. Click a hole (no drag) to mark it as the target - or use the dropdown below if clicking precisely is awkward on a small screen.

Platform boundary auto

Holes ok

Target hole blank

Or pick it here:

Click the hole on the image that leads to the escape box.

Platform diameter (cm) blank

Required - without it, path length is reported in pixels, not cm.

Trial info

Trial # Cohort Group Animal ID Prior trials completed

Prior trials completed is a human-entered label only - it's never read by the tracker, event detector, or classifier. It just rides along with this trial's numbers into the exported spreadsheet, so a researcher reading it later has context (e.g. "trial 1 of 5, still wandering" reads differently than "trial 9, still wandering").

Events & merged visits

Track the mouse first (see Mouse tracking in the middle column).

Per-hole pixel-change signal, duration-gated. An entry is the signal plus the mouse's own tracked blob going invalid right after; a poke is the signal plus the mouse's speed dropping to at-or-below its own trial's median. Low-confidence candidates are shown, not hidden - disagreement gets flagged, not silently resolved.

Human review survives a reload: a correction here or on the search-strategy verdict below persists and comes back after resuming a session, or after loading a saved project file. Re-detecting events with DIFFERENT thresholds still clears overrides on purpose - frame ranges may have shifted, so a stale override would be misleading, not just outdated. See KNOWN_LIMITATIONS.md for what's still missing (a free-text note per override, a timestamped audit log).

Min center density Min run length (frames) Gap tolerance (frames) Speed ratio (x trial median) Reengage fraction

Detected events

Merged visits

Two events at the same hole are merged into one visit when the raw center-density signal between them never drops close to baseline (reengage fraction x min center density) - a brief dip under the qualifying threshold doesn't end a visit, but a real return to baseline does. See DECISIONS.md 2026-09-04. Feeds the search-strategy classifier's visit sequence and the errors/perseverative-errors measure - not shown elsewhere yet.