How does AI tire scanning work?

TyreCam AI runs a hybrid pipeline: a Stage 0 defect gatekeeper in the browser, then server-side ROI detection, Depth U-Net, wear classification, TWI grid/heatmap and a Physics-Based Fusion Engine with Safety Shield. Upload a tire tread photo to get estimated depth in mm, wear level and safety guidance in seconds.

Is the tire scanner free to use?

Yes. You can run 3 scans per day without registration, or 10 scans per month with a free account. Core analysis features stay free while we improve model accuracy.

How accurate is the AI tire analysis?

The system fuses multiple ONNX models (depth U-Net and wear classifier) through an equal-mean Fusion Engine and Safety Shield, with conservative depth ranges. Results are estimates from a single photo and may be marked Preliminary. For safety-critical decisions always consult a professional tire technician.

What tire wear levels does the scanner detect?

TyreCam AI maps estimated tread depth into 5 categories: New (≥7mm), Good (5–6.9mm), Medium (3–4.9mm), Worn (1.6–2.9mm) and Critical (<1.6mm). The 1.6mm threshold is the common legal minimum in many countries.

Do I need to download an app?

No app download required. TyreCam AI works directly in your web browser on smartphone, tablet or computer.

What does TyreCam AI not detect yet?

Current scope is tread depth estimation and wear scoping from a tread photo. Cracks, dry rot, sidewall damage and complex uneven wear patterns are on the roadmap and are not a substitute for live professional inspection.

ABOUT // MISSION

About TyreCam AI

Automated optical tire tread depth analysis & physical safety scoping

Our Mission

TyreCam is an automated computer vision system designed for non-destructive, contactless inspection of pneumatic tires. We provide instant tread depth estimation, Wear Indicator (TWI) verification, and diagnostic PDF reports for car owners, used car inspectors, auto repair shops, and commercial fleets worldwide.

The Computer Vision Challenge

Optical Tread Geometry Analysis

Analyzing tire tread from a single 2D camera photo presents significant challenges: variable shadow depth, rubber micro-textures, dirt distortion, and angled perspectives. TyreCam solves this by combining client-side defect gating with a multi-model server-side neural pipeline and a Physics-Based Fusion Engine.

Our Technology Architecture

Stage 0 Gatekeeper

In-browser ONNX model pre-filters non-tire images and flags critical physical defects (cuts, hernia, cord exposure) before server analysis.

Multi-Model Depth Pipeline

Server-side ONNX models run in parallel: ROI detection, Depth U-Net, 5-class wear classifier, and geometric TWI grid/heatmap consensus.

Physics-Based Fusion Engine

Fuses neural predictions with physical tire constraints, applying Safety Shield bracket clamping and conservative range estimation.

ONNX Runtime Core

Optimized CPU-threaded inference pipeline built on ONNX Runtime for low-latency, high-throughput image processing.

System Capabilities & Roadmap

Tread Depth (mm)

Absolute mm estimation synced with legal thresholds

TWI Verification

Consensus checking of Tread Wear Indicator markers

PDF Diagnostic Reports

Downloadable summary with metadata for archives

Sidewall OCR (Roadmap)

Planned feature: automated embossed size extraction

ACTIVE V0.4.1

Current Production Status

• Live hybrid AI pipeline with Safety Shield guardrails.
• Optimized for global standards (EU 1.6mm / US 2/32" legal minimums).
• Continuous neural dataset expansion and accuracy improvements.