Why PolarEye™

Most behavior is still scored by hand.

Preclinical neuroscience depends on watching animals behave. Yet in most labs that behavior is still scored the way it was decades ago: a trained researcher watches hours of video with a stopwatch and a clicker. It is slow and subjective, and two observers, or two labs, rarely score the same animal the same way.

PolarEye™ automates it. The camera drops into the experiments you already run, records standardized high-definition video, and measures the whole animal in real time, so the scoring comes from the camera instead of a person with a clicker.

Better data.

Every animal measured the same way, every time, in every lab. Objective, repeatable measurements replace hand counts.

Better drugs.

Richer, more consistent measurements help researchers see real drug effects sooner, and spot the ones that won’t hold up.

Fewer animals.

Less noise in the data means smaller groups can reach the same answer.

The High-Definition Smart Camera

PolarEye™ high-definition smart camera

PolarEye™

The high-definition smart camera for every behavioral assay you already run. Patent-pending cross-polarized NIR optics reject background in hardware, real-time pose estimation runs on the device itself — and it drops into your existing protocol without changing a single step.

Request a Demo See it at SfN 2026 →

Any Assay

Keep every assay.
Change nothing but the camera.

There are roughly 200 published rodent behavioral assays. Dedicated instruments exist for only a handful of them. PolarEye™ is designed to capture any of them — point it at the experiment you already run, with zero protocol change, and record standardized, analysis-ready video from day one.

Your legacy assays aren't a compromise. Decades of validated endpoints stay valid — PolarEye™ simply measures them better.

Zero protocol change

No new arena, no new workflow, no re-validation of your experiment. PolarEye™ drops into the assay as it exists today.

Background rejection in hardware

Cross-polarized NIR illumination cancels glare and background before a single line of software runs. Clean signal in, cleaner data out.

Intelligence on the device

Real-time pose estimation runs on the camera itself — edge AI that turns raw frames into kinematics as they're captured.

The Complete Readout

Legacy tracking reduces the animal to a dot. PolarEye™ measures the whole animal.

An animal in pain and a healthy animal can look nearly identical — the same silhouette, the same track through the arena. The signal that separates them is subtle: micro-adjustments in posture and gait, and the facial expressions researchers quantify with grimace scales. Legacy systems miss it. PolarEye™ measures it.

85 anatomical keypoints

Full-body pose across body, head, tail, and face at 95 frames per second — 8,075 postural keypoints measured every second, on the device itself.

Expression & identity

Grimace-scale facial expression analysis for pain and welfare, plus continuous tracking of grouped animals that keeps each animal's identity straight from the first frame to the last.

Invisible observation

PolarEye™ images at 850 nm, beyond the visual range of mice and rats. No visible light, no observer in the room, no behavioral artifact from the act of measurement itself.

Automated Assays

Assays PolarEye™ can run automatically.

Set it up, press start, and let the camera keep the record. Seven classic assays PolarEye™ is designed to automate, plus help adding your own — no stopwatch, no manual scoring, and consistent results from run to run.

More than a dot on a maze arm

Every assay gets a second layer of data: posture.

An ordinary webcam or a device’s built-in camera can follow where the animal goes. It can’t see how the animal holds its body. PolarEye™ adds full-body postural data to every assay, so instead of tracking a dot on a maze arm you also capture stretching, crouching, rearing, and other complex behaviors: an extra layer of behavioral and neurological information from the same session, with no change to your protocol.

  • RearingExploration and vertical activity
  • StretchingStretch-attend and risk assessment
  • CrouchingFreezing and defensive posture
  • Gait & posture shiftsMotor and neurological function

Open Field

The open field test measures how a rodent explores a new arena: how far and how fast it moves, and how much time it spends near the walls versus the center. It is a classic readout of activity and anxiety-like behavior.

Mount PolarEye™ overhead, press start, and walk away. It is designed to deliver the whole session’s results with no hand-scoring and no stopwatch, and the same answer no matter who runs the test. Beyond distance and center time, it captures rearing, stretching, and crouching as they happen.

Rotarod

The rotarod measures motor coordination and balance. The animal walks on a slowly accelerating rotating rod, and researchers record how long it stays on.

PolarEye™ is designed to log every lane and every fall for you, so nobody has to hover over the rod with a stopwatch, and no drop is missed or disputed.

Von Frey

The von Frey test measures sensitivity to touch. Fine filaments press gently on the paw to find the lightest pressure that makes the animal respond. It is a standard measure in pain research.

PolarEye™ is designed to record each trial and its outcome for you in a clean, time-stamped log, so results stay consistent from experimenter to experimenter and from day to day.

Hargreaves

The Hargreaves test measures sensitivity to heat. A gentle radiant heat source warms the paw from below, and the readout is how long the animal takes to respond.

PolarEye™ is designed to log every trial’s result automatically, so you can test more animals with less hands-on time and keep a consistent record of every session.

Elevated Plus Maze

The elevated plus maze measures anxiety-like behavior. The animal explores a raised, plus-shaped maze with two open and two enclosed arms, and researchers record how much time it spends in the open arms.

PolarEye™ is designed to log arm entries and time in each arm for you, so every session is scored the same way, with no hand-tallying. It also captures the stretch-attend postures a dot-tracker misses.

Conditioned Place Preference

Conditioned place preference measures reward. After one chamber is paired with a drug or other stimulus, researchers record whether the animal chooses to spend more time there.

PolarEye™ is designed to log time in each chamber across every session for you, so preference scores stay consistent and nobody has to score hours of video. You also see how the animal behaves in each chamber, such as rearing and crouching, not just where it sits.

Morris Water Maze

The Morris water maze measures spatial learning and memory. The animal swims in a pool to find a hidden platform, and researchers record how quickly it learns where the platform is.

PolarEye™ is designed to record every trial’s path and time to platform for you, so learning curves come straight from the session with no manual tracking.

Your Assay

Running a different behavioral assay? We can help you train PolarEye™ to run it automatically.

Tell us about your setup and what you measure, and we’ll work with you to get it running with the same hands-off, consistent results.

Automated assay support is in development. We’ll confirm availability for each assay at launch.

Built for Machine Vision, Not for Humans

Every design decision optimizes what the model sees.

Consumer and legacy scientific cameras are designed to produce images that look good to people. PolarEye™ is designed to produce data that machines measure precisely. The differences are not cosmetic.

Global shutter

Every pixel in every frame is exposed simultaneously. Rolling-shutter cameras smear fast limb movement across the readout — a silent killer of gait metrics. PolarEye™ never rolls.

850 nm bandpass optics

A narrow bandpass filter on AR-coated optics rejects ambient room light entirely. Your data looks the same at noon and at midnight, lights on or lights off.

High-speed capture

Frame rates up to 95 fps at full 5 MP resolution — fast enough to resolve the individual footfall dynamics of a running mouse, with the temporal resolution that stride-level kinematics demand.

Resolution where it counts

The optical path delivers at least 3 pixels per millimeter at the imaging plane across the full field of view — enough to segment individual digits on a mouse paw.

Hardware synchronization

Dedicated hardware trigger input with sub-millisecond frame timing — a hardware guarantee, not a software timestamp.

Provenance on every frame

Every unit ships with a machine-readable hardware profile — sensor, optics, filter, firmware, calibration record — and every frame is tagged with it. Your methods section writes itself.

[ Cross-Polarized NIR — Block Diagram ]

How It Works

A physics advantage, not a software patch.

PolarEye™ illuminates the scene with polarized 850 nm near-infrared light — invisible to rodents — and images it through cross-oriented polarizing optics. Glare and background cancel in the optical path itself, rendering the animal as a clean, high-contrast form.

Contrast is generated by the physics of the light path, before a single line of software runs. Every measurement inherits clean, consistent, high-signal input. On-device pose estimation then turns those frames into kinematics in real time.

The cross-polarized NIR optics are patent-pending.

Context Is Data

The variables you couldn't control become variables you measure.

Behavior doesn't happen in a vacuum — it happens in a room. Every PolarEye™ session automatically records its own experimental context and stores it with the data.

The room*

Ambient light level, background sound, temperature, pressure, and humidity — logged continuously alongside every frame.

The ultrasonic channel

Ultrasonic vocalizations across the full murine and rat range, captured in sync with video — an affective signal most rigs never record.

Reproducible by default

Every recording carries a machine-readable record of the exact hardware that captured it, so results stay comparable across rigs, sites, and years.

Why it matters

Uncontrolled variables become measured covariates. The variance you could never explain becomes variance you can model — and remove.

*Ambient light level, background sound, temperature, pressure, and humidity measures require the optional data capture module.

Real-Time, Closed-Loop

A camera that doesn't just watch. It participates.

Because scoring happens on the device in real time, PolarEye™ can act on behavior the moment it occurs.

State-gated stimuli

Deliver von Frey or Hargreaves stimuli only when the animal is in the correct posture — gating validated by the camera, not the experimenter's eye.

Behavior-triggered protocols

Trigger recording or stimulation the instant a target behavior appears — including real-time place preference experiments with no physical partitions at all.

Adaptive designs & welfare

Run staircase and Bayesian-adaptive designs that converge in fewer trials, and set welfare alerts that catch distress behaviors for faster intervention.

Hardware-accurate synchronization with your existing equipment — TTL/GPIO trigger in and out, frame-timing pulses.

Specifications

PolarEye™ at a glance.

Target specifications. Final performance figures are verified on production units.

Optics
Cross-polarized NIR, hardware background rejection (patent-pending)
Mounting
Flexible — overhead, side, or custom configurations
Illumination
850 nm polarized NIR — invisible to rodents
On-device AI
Real-time pose estimation on the camera (edge AI)
Sensor
High-definition 5 MP, global shutter
Frame rate
Up to 95 fps
Imaging-plane resolution
≥3 px/mm across full field of view
Optical filtering
850 nm bandpass, AR-coated optics
Synchronization
Hardware trigger input, <1 ms frame timing
Interface
USB3 / GigE, wired acquisition
Data provenance
Machine-readable hardware profile on every frame
Behavioral readout
Location plus full-body posture: rearing, stretching, crouching, and other complex behaviors
Assay coverage
Designed for any published rodent behavioral assay — zero protocol change
Species validated
Mouse, rat
Pricing
$25,000 academic*
$50,000 enterprise license

*Academic pricing. Commit at SfN 2026 and receive 30% off as a Founding Customer — meet us in Washington, DC →

SfN 2026 · Washington, DC

See PolarEye™
in person.

Meet the team at SfN 2026 in Washington, DC, November 14–18, Booth 429. Book a time and we’ll show you PolarEye™ live.

Meet us at SfN 2026 Talk to a Scientist