Browser-based motion analysis

Turn Video Into Measurable Motion Data

Review motion frame by frame, measure angles and distances, track movement, and compare trials in one workspace. Build graphs and export quantitative results directly from your browser. For biomechanics, gait, sports technique, and ergonomics.

Source videos stay on your device Browser or optional desktop install Frame-accurate tools
motionlab.biosystemsone.com/app
Actual MotionLab workspace showing a deadlift video, a tracked landmark, calibration reference, and side-by-side position and speed graphs.

Actual MotionLab workspace: a local video, calibrated landmark tracking, and position and speed graphs side by side. Select the screenshot to view it at full size.

Why MotionLab

A modern alternative to desktop motion analysis software.

Work from a browser or install MotionLab in its own desktop window. Your video, tracking tools, graphs, and report options stay together.

No Installation Required

Open the app in a supported desktop browser. Optional installation adds a desktop shortcut and a dedicated window. AI models download when needed.

Privacy-First Processing

Video decoding, tracking, measurements, and graphs run on your computer. Source footage stays local; you choose whether to sync analysis projects.

Modern Motion Analysis

Choose manual digitization, image-feature tracking, or AI pose estimation. Review uncertain points, calibrate your study, and report the methods behind the results.

How It Works

Open a video. Analyze the motion. Export the results.

Name the trial, select the working range, and move through the analysis steps. Dedicated Report, Settings, and Annotations menus keep each task within reach.

Stage 1

Open Video

Name your trial and open a video or image. Set In and Out to choose the portion to analyze, confirm the recording rate, then calibrate distance and coordinates. The default origin is the bottom-left corner, with Y upward.

  • Step 1 · Video
  • Step 2 · Calibration
  • Step 3 · Coordinates
Stage 2

Analyze Motion

Choose an anatomical landmark template, mark or estimate its landmarks, and select the tracking method suited to the footage. Then define the joint angles and distances required by the study.

  • Step 4 · Tracking
  • Step 5 · Measurements
Stage 3

Export Results

Plot time series or X–Y paths over the selected range. Arrange multiple graphs, adjust their dimensions and line styles, then choose the data, figures, and report sections to export with Pro.

  • Step 6 · Graphs

Source footage stays on your device. Saved projects retain analysis settings and results; reopening a project may require selecting its original video again.

Capabilities

Everything the measurement actually needs.

Local tracking, calibrated measurements, flexible graphs, and configurable reports. Pro adds AI pose tracking, multi-video comparison, and professional exports.

Video Analysis

Frame-accurate stepping, adjustable playback speed, a working range, and a scrubber that shows every frame as a tick. High-speed footage reports true times rather than playback times.

Motion Tracking

Track manually placed landmarks from frame to frame, or use Pro AI pose tracking to estimate anatomical landmarks across the selected range. Review low-confidence and occluded points before using the results.

Angle & Distance Measurement

Measure joint angles, segment orientation, and calibrated distances. Set a known length or use four-point plane calibration for perspective within the reference plane. Motion outside that plane remains a limitation.

Trajectory Visualization

Landmark paths grow as you advance through the video and shorten when you scrub backward. Adjust labels, landmarks, and segment thickness; save the current frame with analysis overlays using Pro.

Data Export

Export tracking and graph data to Excel (.xlsx) or CSV. Save graph figures, print to PDF, or build an HTML report with the trial name, model-fitting image, selected graphs, summaries, and methods.

Project Management

Name and rename trials, save locally or sync projects with an account. Recovery keeps analysis after a refresh; select the source video again when requested. Folder saving is available in supported browsers.

Multi-video Comparison Pro

Add two, three, or four videos or images in the same workspace. A colored border identifies the active view for the shared tools. Focus on one view without closing the others.

Flexible Graphs

Plot position, velocity, acceleration, angles, or an X–Y joint path. Arrange graphs side by side, in rows, tabs, or an overlay. Resize the graph area and edit parameters, colors, weights, and styles from the legend.

Technology

Every number arrives with its working shown.

Build a report around your study. Choose the images, graphs, and results to include, and add methods and point provenance so readers can interpret the analysis.

Report builder

Choose what your report includes

Trial identityProject or trial name
Model-fitting imageThe first frame with all linked landmarks placed, with segment overlays
GraphsSelected parameters, legends, and the working In–Out range
ResultsMeasurements, range summaries, and events
MethodsFrame rate, calibration, coordinates, filtering, and tracking provenance
Multiple videosArrange model-fitting images side by side or one after another
Report contents are selectable. Pro supports HTML reports and printing to PDF, plus separate Excel, CSV, and figure exports.

The methods behind it

Select the tracking and processing settings that fit your footage. Check estimated landmarks against the video before interpreting derived motion.

  • FilteringZero-lag dual-pass Butterworth with the cutoff correction from Winter, Biomechanics and Motor Control of Human Movement — applied forward and backward so no phase shift is introduced.
  • Cutoff selectionResidual analysis after Winter, or residual autocorrelation after Challis (1999). MotionLab plots the curve it used, so the choice is visible rather than asserted.
  • Perspective correctionFour-point planar calibration maps image coordinates into a known reference plane. It does not recover three-dimensional movement.
  • AI pose estimationLocal RTMPose models estimate anatomical landmarks, with MediaPipe as a fallback. Model confidence helps flag uncertainty; it is not a measurement of anatomical accuracy.
  • Image-feature trackingPyramidal optical flow between adjacent frames, zero-mean normalised correlation refinement, forward–backward verification, and conservative template re-acquisition.
  • Gap handlingOptional gap estimates use recent motion and linked segment constraints. They remain labeled as estimates, including gaps without a confirmed reacquisition; review them before reporting.

Single-camera 2D cannot measure motion toward or away from the lens. MotionLab states that limit rather than working around it, and records the calibrated plane every measurement depends on.

Who It Is For

Built for people who have to defend the number.

Biomechanics researchers Gait and human-movement research, normalised to percent of cycle so trials of different length compare directly. Methods metadata included.
Sports scientists Technique and performance from high-speed phone footage, with the true capture rate applied so velocities are not silently wrong.
Ergonomics professionals and engineers Review working posture, measure joint angles during reaching or lifting, and document how a tool or workstation changes movement. Carry annotated frames and measurements into technical reports.
Educators Teach calibration, manual digitization, trajectories, and measurement uncertainty on desktop browsers. Free supports local analysis; Pro adds exports and advanced tools.

Your Data

The footage stays yours.

Movement video of a real person is identifiable, often clinical, and frequently covered by an ethics approval. MotionLab is built so it never has to leave the machine it was recorded on.

Source videos remain local Your browser reads the file straight from disk and decodes it in memory. There is no upload step and no server waiting for it.
The analysis runs on your machine Tracking, filtering, angles and graphs are all computed in the browser tab — not on our hardware.
Projects store analysis, not footage Saved projects contain settings, landmark coordinates, and results. Account, subscription, and optional project-sync data are handled separately; see the Privacy Policy.
You decide what leaves Choose local project storage or optional cloud sync. Exported files are saved to your device, ready for you to share.

Pricing

Free to learn on. Paid to publish with.

Start with local video analysis, manual and image-feature tracking, measurements, and graphs. Pro adds AI pose tracking, multi-video comparison, estimated kinetics, and data, image, figure, and report exports.

Free
$0

Learning, teaching and evaluation. No account needed to start.

  • Video review, manual digitization, image-feature tracking
  • Calibration, coordinates, and landmark templates
  • Angles, distances, events, graphs
  • Save projects on your device
  • Sign in free to save your projects online so your work follows you between machines
  • No Excel, CSV, image, figure, or report export

For coursework, self-teaching, classroom demonstration and trying MotionLab on your own data before you buy. Signing in is free and optional — it saves your projects, it does not unlock exports.

Start Free

Prices in USD. Visit Pricing for subscription details or contact support about academic and lab options.

Who Builds It

Developed by BioSystems One Inc.

A research and development company working across biomedical and biosystems engineering. MotionLab came out of biomechanics research needs that existing tools met awkwardly or expensively.

Built by people who use it. The workflow follows how a trial is actually analysed, not how software is usually organised.
Published methods, named. Winter's filtering and residual analysis, Challis's autocorrelation criterion, planar homography, Lucas–Kanade optical flow, and normalised cross-correlation.
Limits stated, not hidden. Single-camera 2D cannot measure depth. MotionLab says so, and records the assumptions behind every export.
No ads, no tracking, no resale. There is no analytics pixel following you around this site and no third-party request on this page.

Questions

Before you start.

Do I need to install anything?

No. Open MotionLab in a supported desktop browser. Chrome and Edge also support desktop installation and local-folder access. Prepare the app and required AI models while online before working offline. Browser support for codecs and advanced features varies.

Will it work without a network connection?

Once the app shell is cached, local analysis can reopen offline. AI needs its model files downloaded first. Sign-in, billing, and cloud sync require a connection; Pro access may require online verification. Recovery restores analysis, but the original source video may need to be selected again.

Do you ever store my video?

Source videos and images are read locally. Optional cloud projects store analysis settings and results, not footage. Account, billing, and email services handle their own necessary data, as described in the Privacy Policy.

How do I sign in?

Use Google or email and password. An account is optional for local analysis and required for cloud project sync and Pro features. Password reset is available from the sign-in page.

What video formats work?

Anything your browser can decode — MP4 (H.264) and WebM are the safest. Some MOV, HEVC and ProRes files will not open; re-encoding to H.264 MP4 fixes it. For still work, JPG, PNG and WebP are all supported.

How accurate is it really?

Accuracy depends on calibration, camera placement, resolution, motion blur, occlusion, and landmark placement. AI locations are estimates and can identify the wrong joint or subject. Review tracks against the footage; a confidence score does not guarantee accuracy. Single-camera 2D does not measure depth.

Can I use it for a publication?

Yes — that is what the report is for. It records the frame rate and where it came from, the calibration method and reference, the filter type and cutoff, the analysed range, and how many points were measured versus estimated. Anything unconfirmed is flagged rather than hidden.

Where exactly is the line between Free and Pro?

Free includes local video review, calibration, manual and image-feature tracking, measurements, and graphs. Pro adds AI pose tracking, multi-video comparison, estimated kinetics, and exports. A free account can sync analysis projects.

What happens to my work if I stop paying?

When Pro access ends, your account returns to Free. Basic analysis and project access remain available; exports, AI pose tracking, multi-video comparison, and other Pro tools require an active entitlement.

Start Analyzing Motion Today

Open a local video and begin with calibration, landmarks, and measurements. No account is needed to try the core analysis tools.