Help centre

Any stable position facing oncoming or passing traffic works. A few practical notes:

• Window mount (interior, facing street): the most common setup. Clean the glass, avoid reflections. Portrait or landscape both work.
• Dashboard: works for roads in front of you. Avoid dashboard glare on the windshield.
• Tripod (exterior, pointing at a cross-street): best accuracy because the camera stays put. Use a mount rated for outdoor use.
• Height: roughly head-height above road level with a slight downward angle gives the auto-calibrator enough perspective to converge quickly.
• Angle to road: anywhere from a shallow side view to nearly perpendicular is fine. The app compensates.

Avoid: airbag deployment zones, pointing directly at the sun, and any position where the phone vibrates continuously. Steady camera, steady readings.

SpeedCam AI offers two calibration paths:

Automatic (default): runs quietly in the background as traffic passes. The indicator turns green once enough data has accumulated, which typically happens within a few minutes on a moderately busy street.

Manual 2-point line (faster): open the Tool Palette (upper-left), tap the line icon, drag two endpoints onto any road feature of known real-world length (a painted crosswalk stripe, a lane-width marker, parking bay lines), enter the distance in meters or feet, tap Done. The app uses that ground-truth reference immediately.

If auto-calibration stalls:

• Make sure the camera is stable. Any movement restarts the fit.
• Vehicles need to be in motion. Parked cars do not contribute calibration data.
• Switch to the manual line on low-traffic streets.
• Tap the calibration indicator and choose “Start Fresh” to discard a bad fit.

SpeedCam AI is engineered for trend detection and side-by-side comparisons. The kind of question you’d ask about your own street: “Is traffic faster this week than last month?” “Did the new speed bump change anything?” Those answers come through cleanly.

The implementation is grounded in published computer-vision research on monocular speed estimation. Readings are calibrated to your specific shooting angle, cross-validated on-device, and outlier-filtered before they reach the dashboard. Accuracy is naturally best with a stable mount, a moderate camera angle, good lighting, and a calibration that has converged. The calibration indicator and confidence chips in Analytics flag anything that looks borderline.

Use SpeedCam AI for what it’s good at: neighborhood-scale patterns, before/after comparisons, per-session distributions, and surfacing outlier events for context. Do not rely on readings as the sole input to formal legal proceedings. This is not certified calibration equipment.

Four export formats are available from the Incidents tab or Analytics screen:

• PDF: formatted report with summary statistics, speed distribution chart, and smart-highlight-reel thumbnails.
• JSON: raw incident and observation records, machine-readable.
• CSV: spreadsheet-compatible; one row per vehicle observation with speed, class, confidence, timestamp, and GPS coordinates.
• TMAS: Traffic Monitoring Analysis System format, compatible with FHWA traffic-study tooling.

Exports honor whatever campaign, session, or confidence filter you have selected. Files are shared via the iOS share sheet: AirDrop, Mail, Files, or any other extension you have installed.

No data is uploaded to a server during export. Files are generated entirely on-device.

Very little, and none of it is footage.

On-device only (never transmitted):

• Camera frames
• Incident images and burst stills
• Bounding-box coordinates and vehicle appearance fingerprints
• GPS coordinates of incidents
• Chat queries to “Ask About Your Data”

Transmitted to SpeedCam AI’s analytics backend (aggregate counts only):

• Anonymous session-started events
• Incident-recorded counts (no images, no GPS)
• Crash reports (stack traces only)
• App performance metrics
• Subscription status (no payment details; those stay with Apple)

The app hardware-attests itself on launch so we can tell legitimate installs apart from tampered ones, without identifying you personally. No cloud database, no cloud storage.

Outbound webhooks (Pro) send event data only to endpoints you configure yourself, signed with your own HMAC secret. SpeedCam AI does not sit in the middle.

Full details are in the Privacy Policy.

Open the Sources tab and tap Import Video File. The iOS photo picker opens. Select any video from your library, including security-camera exports.

Next, choose a camera FOV preset matching the camera that recorded the video:

• Wide-angle cam: 110°
• Security cam: 130°
• Security cam: 140°
• iPhone: 77°
• GoPro: 170°

If your camera is not listed, choose the closest match or select Custom and enter the horizontal field of view.

The app processes every frame at the video’s native framerate (native encoding is preserved, no re-transcoding). All vehicles travelling ≥5 mph are recorded as a speed survey, not just threshold violators. Results appear as a session in the Incidents tab tagged “Video Import.”

SpeedCam AI supports RTSP streaming from any ONVIF-compatible IP camera. Video decoding runs on your iPhone. No cloud round-trips.

This feature is Pro (both Annual and Lifetime; see Pricing). Open the Sources tab and tap Connect IP Camera:

• ONVIF auto-discovery: the app scans your local network and lists compatible cameras automatically. Tap a camera to connect.
• Manual RTSP URL: if your camera does not appear, enter the RTSP URL and credentials from your camera’s admin panel directly.

H.264 and H.265 streams are both supported. Save the camera to reconnect with Face ID next time.

Incident images are saved to the app’s private Documents directory at Documents/SpeedCamEvidence/{YYYY-MM-DD}/. They do not appear in your Photos library unless you explicitly share them.

To back up:

• Connect to a Mac and use Finder → iPhone → Files → SpeedCam AI to copy the SpeedCamEvidence folder.
• Or use the Export function (PDF or JSON) to create a portable record.

Clearing data in Settings → Clear All removes all incidents, sessions, and stored media permanently. This action cannot be undone.

SpeedCam AI requires iPhone 12 or newer running iOS 26. The on-device object detector runs on the Apple Neural Engine, so performance scales naturally with your iPhone’s hardware: the minimum spec runs smoothly, and newer chips (A18 and later) process detection frames noticeably faster. The on-device AI analyst additionally requires an iPhone that supports Apple Intelligence.

Two options: Pro Annual at $19.99/year (auto-renews) or Pro Lifetime at $59.99 one-time (no renewal, transfers across your iPhones). Both unlock the same features: recording on your own footage, incident capture, video import, IP camera support, and analytics on your own data. (Free already includes live detection in viewer mode, the analytics dashboard with demo data, and all export formats on that demo data.) Full details including feature comparison on the Pricing page.

Why a subscription? SpeedCam AI is built for the long run. Subscription revenue funds every release: smarter on-device detection, new features, and broader compatibility. There are no ads, no tracking, and no cloud upsell.

Cancel anytime via your Apple ID: iPhone Settings → your name → Subscriptions → SpeedCam AI → Cancel. Cancellation stops the next renewal; access continues through the end of the current billing period.

SpeedCam AI measures and records vehicle speed from your own property or a public right-of-way, using your iPhone camera. This is generally lawful for personal, research, and advocacy purposes in most jurisdictions, under the same legal framework that applies to filming from a public space. Laws vary by location, particularly around data retention, sharing footage of licence plates, and using data in formal proceedings. If you intend to share data publicly or present it to authorities, consult local laws. SpeedCam AI does not provide legal advice.