International Computer Vision Developer Shared How to Maximize Facial Recognition Efficiency in Safe City Projects

3DiVi, an international computer vision company,  has shown a new deployment framework designed to help municipalities maintain high accuracy and operational stability in citywide facial recognition systems.

In 2026, municipalities worldwide continue to integrate facial recognition technology (FRT) into their city CCTV networks to identify missing or wanted individuals on watchlists, helping secure public spaces and support law enforcement investigations. But as safe-city operators move these systems from pilot to production, many are learning a hard lesson: deploying facial recognition is more than turning on an algorithm. 

In a recent closed 3DiVi survey of 89 system integrators, public safety leaders, product owners, and CTOs, 83% reported unexpected spikes in false acceptance rates (FAR) after FRT deployment. Even more concerning: 75% admitted they treat facial recognition as a one-time setup rather than a continuously tuned operational system.

“In a Safe City environment — where sudden FRT accuracy drops can mean missed threats, and public distrust — that mindset is risky,” says Leonid Leshukov, Head of Product Development at 3DiVi.

“Real-world performance rarely mirrors lab conditions, and that gap is where operational failures emerge. That’s why our team decided to develop a practical, field-tested framework that city agencies can adopt to ensure their FRT pipelines remain stable, transparent, and resilient from day one.”

Why Safe Cities Meet FRT Failures After Go-Live

Lab Data vs. Real Urban Conditions

Training and validation datasets are usually captured in an ideal environment. Street cameras, however, deal with:

• Crowd density and movement speed
• Varying weather and lighting conditions
• Head poses, hats, masks, glasses, and other partial face occlusions
• Low-resolution streams from legacy CCTV
• Large demographic diversity

This mismatch can cause sudden accuracy drops once the system meets the chaos of the urban environment.

Confidence Thresholds Tuned for Dev Data

In most projects, face matching confidence thresholds are calibrated on clean development datasets. That may look good in a benchmark report, but it rarely survives urban reality. A threshold that minimizes errors in a lab can break down when exposed to crowded streets, aging cameras, motion blur, or diverse demographics.

For Safe City deployments, metrics like False Accept Rate (FAR) need to align with real-world risk tolerance, not just lab performance.

Profile Photos Ageing — a Silent Accuracy Killer

Facial images used as reference database photos for face search—whether captured only once or of low quality—degrade in reliability over time as people’s appearances change. In city-wide surveillance networks, these subtle drifts accumulate, turning a once-accurate match into a false accept months later.

Operational Scale Exposes Weaknesses

In production, FRT pipelines face:

• High-volume, real-time video streams
• Network congestion
• Hardware load variability
• Video compression artifacts

Any weak link can slow processing and reduce recognition accuracy, revealing issues that didn’t appear during development.

From Challenges to a Three-Phase Deployment

To tackle the challenges of citywide facial recognition, 3DiVi team has developed a controlled, predictable deployment process. Their three-phase framework — pilot deployment, load testing, and city-wide scaling — allows municipalities to identify and resolve potential failure points before full production.

Phase 1: Pilot Deployment

• Install a small number of cameras following recommended placement guidelines.
• Check the configuration and placement of each camera and adjust if performance is low.
• Measure detection rates (faces detected among those passing through the identification zone). If below the target (typically 85–95%), adjust camera or software settings.
• Upload facial images and create watchlists. Filter out low-quality images to maintain recognition accuracy.
• Form a test group for identification evaluation and add their faces to the database.
• Set an initially low recognition threshold (e.g., 0.7) to allow thorough testing.
• Define test scenarios for each camera (day/night, weather conditions, etc.) and have the test group perform multiple passes. Record camera streams for later load testing.
• Evaluate identification performance and optimize recognition thresholds based on test results.

Phase 2: Load Testing

• Select a server unit based on theoretical load estimates.
• Perform load testing using the recorded videos. Gradually increase the number of video streams until recognition quality metrics start to degrade (allowed deterioration: ≤5%).
• Record the maximum number of streams per server that maintains quality metrics as the recommended configuration.

Phase 3: City-Wide Scaling

• Install cameras according to the parameters defined in Phase 1.
• Check each camera’s configuration and placement, adjusting if necessary.

Ongoing Operations

• Every six months, check each camera for environmental changes or degradation.
• Continuously monitor:
  • Total detections per camera
  • Correct identifications
  • False identifications
  • Any anomalies, such as misalignment or lens obstruction

This structured, phased approach ensures the system is optimized before scaling and maintains reliable performance over time.

Final Insights

For Safe City leaders, deploying face recognition means building an adaptive operational ecosystem around high-accuracy FRT model.

A production-ready FRT system requires:

• Representative testing on real-world data
• Risk-aligned thresholds
• Continuous database photo management
• Full-pipeline performance testing
• Live monitoring, alerting, and auditing
• Clear and defensible decision logic

Cities that treat FRT as a static procurement item will face system drift, public backlash, and operational risks. Municipalities that treat it as a living system — continuously tuned and monitored — will build safer, more transparent, and more resilient urban environments.