Arjuna
arjuna - clear, bright, of unclouded sight
Real-time video analytics on the CCTV you already have.
Arjuna is Wayam's video-analytics accelerator: real-time understanding on ordinary RTSP streams from the CCTV you already run. It detects, tracks, counts, and alerts, and monitors safety compliance, with on-premise deployment as the default.
Workflow
Problem
Most CCTV estates only help after something goes wrong, and nobody can watch every screen.
Outcome
Detection, tracking, counting, zone alerts, and safety compliance on existing cameras, on your infrastructure.
01
Connect
Point Arjuna at existing RTSP streams. No new cameras required.
02
Detect
People, vehicles, zones, density, and compliance events fire in real time.
03
Apply your rules
Site policies become alerts, not after-the-fact footage review.
04
Act
Operators get the signal while there is still time to intervene.
Modules
People & vehicle intelligence
Tracking, counting, classification, and re-identification across cameras.
Zones & dwell
Intrusion, loitering, crowd density, and occupancy alerts in real time.
Safety compliance
Rule-based monitoring like handrail and PPE compliance on live streams.
On-prem by default
Runs on your infrastructure with retrofit RTSP streams, not rip-and-replace cameras.
Representative use cases
Autonomous Worker Safety & PPE Compliance Monitoring in Heavy Plants
A primary steel manufacturing mill operating high-risk melt shops, rolling mills, and heavy material handling yards equipped with 250 existing CCTV security cameras.
Real-Time Intrusion & Unauthorized Zone Detection in High-Security Sub-Stations
An electric utility provider managing 120 unstaffed high-voltage electrical sub-stations protected by perimeter fence security cameras.
Automated Package & Label Defect Inspection on High- Speed Conveyor Lines
A high-volume consumer packaged goods (CPG) facility producing 120,000 packaged food items daily across 6 high-speed conveyor lines.
Forklift Hazard & Pedestrian Proximity Prevention in Warehouses
A 500,000 sq. ft. logistics distribution center operating 40 industrial forklifts alongside 150 warehouse order pickers in high-density rack aisles.
Fleet Yard Traffic Management & License Plate Recognition at Docks
An intermodal logistics hub managing 1,000 daily tractor-trailer arrivals across 80 loading docks and staging yards.
Flame, Smoke & Chemical Leak Micro-Detection in Oil Refineries
A petro-chemical refinery operating hazardous process units, tank farms, and pipe racks monitored by 400 outdoor industrial CCTV cameras.
Evidence
What Wayam can show for this entry
Curated solution design with an owner and a review date. No performance or production claim.
Allowed claims at this tier: Possible workflow, typical stack, prerequisites.
- Evidence tier
- T4 · Reference pattern
- Integration status
- Typical enterprise system
- Metric status
- Scenario only
- Evidence owner
- Not yet attached
- Validated
- Not yet attached
- Valid until
- —
- Content version
- 2026.09
Pending evidence attachment
This entry represents an enterprise architectural reference pattern. Customer benchmarks, run replays, and metric verifications are established during technical discovery.
Limitations
- Headline metrics are representative until a customer result is attached.
Representative metrics · Reference · scenario only
Retrofit
AI on existing cameras
These describe the intended outcome of the design. They are not measured customer results until a validated case is attached above.
Architecture & controls
Composed across the operating loop
Ingest
Connect the systems of record and read the signals the work already produces.
Covered by the platform
Reason
Ground context, score options against policy and the stated goal, draft the next step.
3 agent roles
Act
Execute an approved step in the system of record and keep the evidence.
5 agent roles
Govern
Set policy, gate consequential actions on a named approver, and audit what ran.
2 agent roles
Pack Architecture & Agent Composition Graph
10 Composed Agents- AGT-0787
Worker Safety Monitoring CV Agent
Vision
- AGT-0344
Safety Incident Prevention Agent
Manufacturing Operations
- AGT-0791
Industrial Vision Analytics Agent
Vision
- AGT-0468
Workplace Safety and Security Agent
Real Estate
- AGT-0201
Computer Vision Quality Inspection Agent
Manufacturing Operations
- AGT-0345
Quality Inspection Reporting Agent
Quality
- AGT-0349
First-Pass Yield Improvement Agent
Quality
- AGT-0100
Close Acceleration Agent
Finance
Control gates
- A named approver on every consequential write-back
- Evidence and audit trail kept with every run
- In-boundary deployment available
- Policy and compliance checks on retrieved context
Capability atoms
- vision-perception
- anomaly-detection
- alert-routing
- policy-compliance
- in-boundary-deployment
Typical enterprise systems
Typical stack for solution design; compatibility is validated during discovery.
- Cognex VisionPro
- NVIDIA Jetson
- AWS Panorama
- ROS
- Siemens MES MCP
- SAP S/4HANA
- PI System
- IBM Maximo
Designed for
manufacturing, retail-cpg, public-sector, technology
Business case
Model a Arjuna scenario with your own baseline
Three scenarios from the numbers you enter. Capacity released is time; it becomes a saving only when roles or costs are actually removed or avoided.
Improvement is seeded at the midpoint of this entry's directional band (20–40%). Source status: scenario only. Edit it to your own estimate.
| Scenario | Improvement | Capacity released | Cashable savings | Net annual | Payback |
|---|---|---|---|---|---|
| Conservative | 11% | — | — | — | — |
| Expected | 21% | — | — | — | — |
| Upside | 29% | — | — | — | — |
Enter an annual volume and a baseline cost to see figures.
Illustrative planning scenario, not a guarantee. Results depend on process baseline, adoption, data quality, integration scope, controls, and deployment costs.
Pilot this
From solution design to a bounded pilot
Step 1 · 3–4 weeks
Discovery Sprint
Validate the workflow, data, controls, baseline and business case before anything is built.
Gate: Blueprint and pilot plan signed by the business owner, technical owner and Wayam.
Step 2 · 6–10 weeks
Bounded Pilot
Prove quality and value on agreed data against agreed acceptance tests.
Gate: Acceptance thresholds met on the evaluation set; go/no-go decision recorded.
Agrani · evidence pending1 Agrani candidate in this solution: Computer Vision Quality Inspection AgentPairs well with