From the Transportation edition of October 31, 2026
Smart Roadway Incident Detection Pilot Program (Valerann Lanternn on I-485 Express Lanes)
North Carolina Turnpike Authority (NCDOT) · State DOT / toll authority · North Carolina, US
- Publisher
- NCDOT
- Original publication
- Page last updated October 13, 2026
- Source retrieved
- 2026-11-01
- Event date
- 2026-05-01
What happened
The North Carolina Turnpike Authority is piloting Valerann's AI-powered Lanternn platform on the I-485 Express Lanes in Charlotte. Development began in March 2026 and the pilot began in May 2026. Lanternn analyzes NCTA's existing traffic cameras, navigation platforms and third-party data to flag crashes, stopped or slow vehicles, pedestrians, wrong-way drivers and other unusual conditions for Traffic Management Center operators, replacing continuous manual scanning of camera feeds. The page claims earlier detection and faster verification but reports no measured results.
Why it matters
A toll authority is testing AI incident detection layered over existing cameras and third-party data rather than new roadside hardware, a pattern other DOT traffic management centers can evaluate.
Evidence and measured results
Agency program page describing an active pilot; no detection rates, false-alarm rates, response-time changes or evaluation plan are published.
Limitations and uncertainty
Self-description of a pilot without outcome data; claims of faster, more accurate detection are unquantified; single corridor.
Put this evidence to work
Lighthouse Advisory interpretation, grounded in this source. Enriched 2026-10-31; this does not change the original publication date. Each role follows the same checklist so takeaways compare across sources.
Sales
Role takeaway
- Customer problem
- TMC operators must scan many camera feeds to spot incidents, which delays detection on express lanes.
- Stakeholders
- NCTA Traffic Management Center operators
- NCTA and NCDOT ITS leadership
- Valerann (vendor)
- Incident responders
- Discovery questions
- What detection lead time and false-alarm rate will define pilot success?
- Which third-party data sources feed the platform, under what terms?
- How do operators verify and act on AI alerts today?
- Value hypothesis
- AI fusion of existing data could shorten incident detection and reduce manual camera scanning, if pilot metrics confirm it.
- Potential engagement
- A bounded pilot-evaluation design: baseline TMC metrics, alert-quality measures and a go/no-go rubric.
- Unsupported claims
- Proven faster or more accurate detection (no data published)
- Crash or secondary-crash reductions
- Staffing savings
Pre-sales engineering
Role takeaway
- Fit
- Fits agencies with camera coverage and a staffed TMC that want detection without new field hardware.
- Architecture and integration
- Ingests camera feeds, navigation-platform and third-party data; outputs alerts to TMC operators.
- Prerequisites
- Camera feed access for the vendor platform
- Third-party data agreements
- Historical incident logs for baselining
- Constraints
- Single express-lane corridor
- Coverage limited by existing cameras
- Third-party data availability varies by jurisdiction
- Security
- Vendor access to live camera feeds and external data requires access controls, retention limits and data-use terms.
- Proof of value
- Compare alert timestamps with TMC incident logs
- Measure false-positive rate by incident type
- Time operator verification per alert
Delivery
Role takeaway
- Work
- Run the pilot evaluation and decide on expansion based on measured detection and workload results.
- Dependencies
- Valerann platform
- NCTA camera network
- Third-party data providers
- TMC staff
- Ownership
- NCTA Traffic Management Center operations
- Skills and adoption
- Operators need training on alert triage and on recording verification outcomes for evaluation.
- Governance checkpoints
- Evaluation metrics agreed before results are reviewed
- Data-sharing terms reviewed
- Expansion decision documented
- Acceptance criteria
- Proposed: median detection lead time improves versus baseline TMC logs
- Proposed: false-alert rate per shift below an agreed threshold
- Proposed: all alerts logged with verification outcome
- Risks
- Alert fatigue from false positives
- Vendor lock-in on data fusion
- Unpublished results limiting accountability
Implementation considerations
Lighthouse Advisory interpretation across the operating dimensions a public-sector buyer must settle before this evidence becomes a design. Each note answers the question under its heading for this specific source.
Architecture and integration
What must connect, and where does the AI sit in the workflow?
Software fusion of existing camera feeds, navigation-app data and third-party sources into TMC alerts; no new field devices described.
Governance
Who approves, reviews and stays accountable for outcomes?
Agencies should define how AI alerts are verified by operators and what evaluation will decide whether the pilot continues.
Security and privacy
What data, permissions and controls need testing?
Third-party data sharing and camera-feed access by a vendor platform need data-use terms; the page does not describe them.
Accessibility and workforce
Who is affected, and what skills or accommodations follow?
Shifts TMC operator work from continuous camera scanning to reviewing prioritized alerts.
Procurement
What should contracts, pricing and exit terms secure?
Pilot structured as a partnership with a software vendor; scaling would require a procurement decision informed by pilot metrics.
Operating model
Which teams own the service once it runs?
TMC operators remain responsible for verification and response; the platform changes how incidents are surfaced, not who acts.
Publication history
- 2026-10-31Transportation · Issue 0312 resources
Stable resource ID: ncta-lanternn-ai-incident-detection-i485-pilot