Road measurement software
We publish the count and the miss.
Traffic counting, classification and pavement distress measurement from recorded video. Licensed to run on your own machines — offline, on your footage, producing numbers your client can audit back to the frame.
Three sites, Indian arterial roads, live uncontrolled traffic
11 August 2026
| Site | Manual | Counted | Volume | Weighted |
|---|---|---|---|---|
| A | 4,579 | 4,595 | 99.7% | 93.0% |
| B | 5,824 | 5,375 | 92.3% | 91.2% |
| C | 6,157 | 5,759 | 93.5% | 92.3% |
| All | 16,560 | 15,729 | 95.0% | 92.1% |
Manual — hand-counted by an independent survey firm Counted — by the software
We lead with 92.1% weighted, not 95.0% volume. Weighted accuracy asks whether every vehicle landed in the right column. Volume accuracy lets over- and under-counts cancel.
The counting line — 19 canonical classes
18 vehicle categories + Other · IRC SP:19 mandates 17 · see all 19 with PCU factors
What you licence
Tools that run on your machines
Licensed software, not a metered service. Each installation is bound to its machine, verified offline, and needs no portal, no token refresh and no outbound traffic. Your footage never leaves your building.
ATCC
Playcraft ATCC
Automatic traffic counting and classification from footage you already have: CCTV, drone or a phone on a pole. No roadside hardware, no per-kilometre fee, and the footage never leaves your building.
- 18 vehicle categories plus an Other bucket, following IRC/MoRTH survey convention
- PCU conversion applied per IRC:64-1990, overridable per deployment
- Directional counts with 15-minute and hourly aggregation
Distress
Playcraft Distress
Turns network survey vehicle, dashcam or phone footage into a geo-referenced distress inventory. It does not merely flag defects — it sizes them, so quantities feed into maintenance estimation rather than a count of red boxes.
- Up to 14 distress classes: cracking by type, potholes, ravelling, failed patches
- Per-defect dimensions, converted to real-world units where camera calibration is supplied
- GPS and chainage recovered by OCR from the in-video metadata banner
Chainage
Playcraft Chainage
An Android application that turns a phone in a car mount into a survey record. Chainage, position, speed and heading are burnt into the video as it records, so the resulting file is self-describing evidence rather than footage needing a separate log.
- Chainage, GPS, speed, heading, tilt and time composited into the video in real time
- Two chainage modes: cumulative distance, or projected onto a reference alignment from GIS
- Road roughness through a Golden-Car quarter-car model at 20, 100 or 1000 m segments
Airport
Airport Pavement Platform
A web platform for civil aviation pavement teams. Consolidates inspection data from multiple sources into one workspace, scores condition against accepted standards, and compares one inspection against the last.
- Multi-format ingestion: geographic overlays, inspection spreadsheets, geospatial imagery
- Interactive 2D map with severity-coded defects, plus a 3D view where elevation matters
- Filtering by chainage range, facility type, severity and distress category
Seen running
Watch the counters move
Ten seconds of a real survey on a divided carriageway. A five-axle truck, a two-axle truck and two motorcycles, tracked at once in opposing directions across a single counting line.
Each vehicle carries its class, its track identifier and the model’s confidence. The panel increments per class as each one crosses. Nothing here is staged or rendered for this page.
Divided carriageway, both directions
26 JUL 2025 · 06:15Why the number holds
Accuracy is a method, not an adjective
Anyone can put a percentage on a page. The question a reviewing engineer asks is of what, measured how, against what.
Two figures, both disclosed
Volume accuracy answers capacity and PCU questions. Weighted class accuracy asks whether every vehicle landed in the right column. We publish both and headline the stricter one.
Ground truth is hand-counted
16,560 vehicles counted by hand by an independent survey firm — a separate company, not a separate process of ours. Accuracy is stated against those counts, never against another model’s output.
Thin categories excluded
Any class with fewer than 50 manual counts is marked statistically unreliable and kept out of the headline, rather than quietly averaged in.
We name what degrades it
Pixels on target at the counting line. Eight pixels of median two-wheeler height between our best and worst site accounted for roughly six points of accuracy on that class.
The codes we work to
Written for Indian survey practice
Outputs are shaped to the conventions your deliverable is reviewed against, not adapted afterwards. Licensing is lifetime or annual, single machine or many; the mechanics are on the products page.
- IRC SP:19
- Traffic survey procedure and vehicle classification
- IRC:64-1990
- Passenger car unit factors, rural road capacity
- IRC 9
- Seasonal correction to annual average daily traffic
- IRC 37
- Pavement design and cumulative MSA
- IRC 81
- Axle load and vehicle damage factor
- MoRTH
- Survey and reporting convention
Next step
Send us 15 minutes of your footage
We will run it, return the classified count and the annotated verification video, and tell you honestly where the camera position is costing you accuracy. No obligation, and you keep the output.