Cricket broadcast technology that runs from one machine at the ground.

Traditional crew

15–20

people on site

With Chrio

1

operator, one machine

Day rate today

$20–30k

before logistics

Logistics with Chrio

$0

no truck, no travel

Three products, one detection pipeline

One camera feed in. Three products out.

Every Chrio product reads the same feed through the same detection and event pipeline, trained on 30 TB of footage from PSL, National T20 and Tri-Nation cricket. Improving the tracker improves all three at once.

Technology

Six stages, one workstation, broadcast out over NDI.

The camera feed comes in. Three detectors, YOLOv8, YOLOv11 and Detectron2, vote on every frame, and SAHI sliced inference recovers the balls too small for a full pass. An LSTM and XGBoost stack predicts the shot. Blender renders the avatar. The finished overlay leaves the machine as an NDI (Network Device Interface) stream the broadcast truck already knows how to take.

Models are trained with TensorFlow and Roboflow and served on Nvidia hardware. Detection accuracy on cricket gameplay footage is 98.67% in model V5, September 2025, up from 20.95% in the first model version in September 2024.

Measured, not asserted

From 20.95% to 98.67% across five model versions.

Detection accuracy on cricket gameplay footage went from 20.95% in the first model version, September 2024, to 98.67% in version five, September 2025 — 4.7× the original.

The largest jump came between V4 and V5. The training set reached 30 TB of PSL, National T20 and Tri-Nation footage along the way, and the validation set is more than 10,000 deliveries of professional match footage.

How we measure detection accuracy

Distribution

Trans Group and TPT carry CritShot to a national broadcast.

Trans Group is one of Pakistan's leading sports rights, media and production groups; Trans Production and Technologies is its production arm. The partnership takes CritShot from a review desk at a national-level test to the live feed millions of fans watch.

Chrio has been incubated by the National Incubation Center Islamabad, NSTP PITB and Invest2Innovate, whose support has carried R&D, funding readiness and product development.

Abdullah Zubair Ghouri

Co-founder. Started Chrio in May 2024 as a second-year computer science student at FAST-NUCES, raised the SAFE and signed the Trans Group partnership. He leads the company and the commercial side. Also worked on RL agents at Motive and LLM training at MAVN AI.

“Every game deserves technology that makes cricket more intelligent, transparent, and exciting. That is the future we are building at Chrio.”

Saffi Muhammad Hashir

Co-founder. Owns the technology end to end — the detection models, the real-time vision pipeline that holds 30 FPS on a single GPU, and the NDI layer that puts it on air. Cut per-frame inference from 200 ms to 33 ms; his VFXGen research placed first on the FiVE-Bench benchmark at ICCV 2025, at a twentieth of the compute. Has led a team of 25 engineers and contractors across seven platforms.

“The best technology becomes part of the game itself. Our goal is to make powerful AI feel instant, reliable, and effortless.”

Recognition

• Google for Startups Cloud ProgramScale Tier, up to $25,000 credits · Sept 2025
• National Ignite AI Wrapper AwardRunner-up · Oct 2025
• HBL P@SHA ICT AwardsRunner-up · Sept 2025

Incubated at NIC Islamabad, NSTP PITB and Invest2Innovate.

Also built here

Dhundo: the same engineering pattern, a different problem.

Chrio also builds Dhundo, a product search engine for Pakistan that reads 136 stores in parallel and returns one list sorted by price. It runs at dhundo.store.

It is on this page for one reason: it is the same engineering problem as the cricket work. Fan out across many sources at once, reconcile what comes back, and answer under a deadline. CritShot runs three detectors as a parallel consensus ring; Dhundo runs 136 store adapters across three scraper fleets and reranks what returns. Two problems, one habit.

Dhundo also publishes a page whose entire purpose is to limit its own claims, including a section headed "What cannot move the score". Review and AggregateRating structured data cannot ship, and a test in CI enforces it.

Bring CritShot to your broadcast.

If you produce cricket — a league, a board, a tournament or a channel — the fastest way to find out whether this fits your fixture list is a thirty-minute call with the engineers who built it.

We reply within two working days. The first call is thirty minutes with an engineer, not a salesperson.

Cricket products

Technology

Company