Industry
Manufacturing and Industrial Sites
Worker safety, PPE compliance, perimeter integrity, and vehicle-gate operations — built for shop floors with grease, vibration, low light, and a deep allergy to anything that interrupts production.
Typical client profile
Single-plant manufacturers through multi-site industrial groups. Deployment ranges from a 40-camera SME plant to a 600-camera multi-block facility.
Indicative scope
Manufacturing Discovery centres on a shop-floor walkthrough with plant safety and operations leadership. We default to module configurations that protect workers; we decline scope that converts vision into a productivity-surveillance tool.
Compliance considerations
- Factories Act 1948 — occupational safety obligations, with vision as a supporting layer not a replacement for safety officers
- Statutory PPE rules per industry segment (chemical, food, automotive, electronics)
- Union and works-council consultation on any worker-monitoring deployment — we provide the documentation template
Manufacturing stack
Modules typically deployed in this vertical.
The platform supports more — this is the configuration we most often land on for clients in this category.
PPE / Mask Compliance
Configurable per industry — hard hat, safety glasses, masks, gloves, hi-vis vests, boots — with site-specific class definitions.
Accuracy: 92% on standard PPE classes at entry checkpoints; lower in busy multi-class shop floors where we recommend zone-by-zone tuning.
Intrusion Detection
Polygon-defined perimeter and restricted zones, schedule-aware, with separate models for human vs. animal vs. vehicle.
Accuracy: 93% detection on humans crossing defined polygons; <2 false alerts per camera per night with proper masking.
ANPR / Licence Plate Recognition
Read Indian commercial and private plates at vehicle gates — single-lane, multi-lane, and toll-style installations.
Accuracy: 94% on standard high-security plates in daylight · 88% on aged/dirty plates · 85% at night with IR fill.
RFID + Face Hybrid
Two-factor entry for high-security zones: RFID badge presents, face confirms — one fails, both fail.
Accuracy: 98% true-accept with both factors present; explicit reject on any mismatch.
Fire / Smoke Early Detection
Visual smoke and flame detection as an early warning layer that complements — not replaces — fire-panel sensors.
Accuracy: 85% on visible flame within camera FOV; smoke detection accuracy is highly scene-dependent and is treated as supporting, not primary.
Multi-Camera Tracking
Handoff of a tracked entity across overlapping camera fields, with behavioural threading for incident reconstruction.
Accuracy: Track integrity is scene-dependent. We publish per-deployment integrity numbers rather than a single headline metric.
People Counting
Footfall and occupancy by zone, by hour, with per-site calibration. Counts are de-identified at the edge.
Accuracy: 97% at zone entries with overhead camera; 92% at oblique angles.
Audio Analytics
Edge-deployed acoustic models for gunshot, glass-break, scream, and distress sounds. Calibrated per-site to suppress local ambient noise.
Accuracy: Class-dependent: 92% gunshot in semi-urban environments, 88% glass-break, 80% scream in noisy interiors.
AI-Prioritised Alert Routing
Severity ranking, dedupe and suppression rules, escalation chains with on-call windows, and SLAs per alert class.
Accuracy: We measure mean-time-to-acknowledge and false-positive rate per class, monthly.
Behavioural Pattern Analysis
Aggregate behavioural baselining with privacy-preserving thresholds — flag deviations, never label individuals.
Accuracy: Reported as deviation z-score against a per-site baseline; we do not claim absolute accuracy.
Custom CV Modules
Bespoke modules built to client requirements — laboratory protocols, equipment status, niche compliance checks.
Accuracy: Committed per module after a 4–6 week data study and pilot.
Run a manufacturing site through Discovery.
Tell us about the site count, the existing camera estate, and the compliance perimeter. We'll come back with a scoping outline.