Evidence

What we built, and how we checked it

One deployment and two engineering notes, because how a measurement problem was actually solved tells you more about whether a vendor can solve yours than a logo does.

MethodologyThree surveys counted by hand by a separate firm; our count compared against theirs, class by class, and both figures published.The accuracy method is its own page →

Deployment

NKMPV

  • Crack detection
  • ATCC
  • Deployed

Road survey software for a civil engineering consultancy

Crack detection and traffic counting, deployed and in production for a civil engineering and materials-testing consultancy.

Outcome

Both systems run in production. The distress and counting work directly informed the products now offered here.

How, technically

Challenge

A civil engineering and materials testing consultancy running road condition and traffic survey work needed software fitted to Indian survey convention rather than adapted from Western tooling.

Approach

We built and deployed a crack detection system for pavement distress from survey footage, and an automatic traffic counting and classification platform calibrated for the local vehicle mix. We also built and maintain their public website.

Engineering note

Playcraft ATCC

289
vehicles recovered
36
windows re-checked
0
regressions
  • Computer vision
  • Verification
  • Engineering

Three defects that were costing 289 vehicles

We found three counting defects, fixed them, re-ran every survey and checked that the extra 289 vehicles were real.

Outcome

A full production re-run recovered 289 vehicles. A 36-window sweep across one clip showed 31 windows counting more, 5 unchanged and zero regressions. Per-vehicle ground truth on a slit-scan window confirmed the gain was real at the level of individual vehicles, not just in aggregate.

How, technically

Challenge

Counts were stable but conservative. Aggregate accuracy alone could not say whether a change was a genuine improvement or a metric artefact.

Approach

Three interacting defects were isolated: a deduplication rule that swallowed genuinely distinct vehicles, a segment authorisation window that expired before the cooldown it depended on, and an isotropic dedup bubble that could not distinguish an identity switch from the next motorcycle. Each was fixed and verified separately.

Engineering note

Playcraft Distress

  • Photogrammetry
  • Measurement
  • Geometry

Measuring defect area from a single phone camera

Defect sizes in metres from an ordinary camera, once its height, field of view and tilt are known.

Outcome

Defect length, width and area in metres from a phone on a hood mount, once the mount is calibrated — without a survey-grade rig.

How, technically

Challenge

A defect flagged is not a defect quantified. Maintenance estimation needs square metres, but survey footage arrives from cameras mounted at unknown heights and angles, with no calibration data.

Approach

A ground-plane model of the camera — height, field of view and tilt — maps every pixel to a point on the road, so a pixel near the top of the frame counts for the far larger area of road it covers. Detections from every frame are fused on that metric grid, and each connected region becomes one defect with its own area.

Where we stand

We would rather show you working software than a client list

We are a small team and our commercial history is short. What is not short is the engineering. If you want to see the code, the architecture, or the tool running on footage you choose, that is how we prefer to be evaluated.

Next step

See it run on a call

  • The tool running on footage you choose, or ours
  • Every output file opened and explained
  • A plain answer on fit before commercials
See it run on a callSend us footage instead