boc/vims-backend

VIMS - Visual Infrastructure Monitoring System

Overview

Production-ready AI-driven visual monitoring for critical infrastructure. Detects anomalies and changes in ATMs, charging stations, parking meters, and more.

Quick Start

# Clone and setup
git clone https://github.com/landvex/vims-backend.git
cd vims-backend

# Run setup script
./scripts/setup.sh

# Start services
docker-compose up -d

# Run tests
npm test

# Start development
npm run dev

Architecture

┌─────────────┐     ┌─────────────┐     ┌─────────────┐
│  quiXzoom   │────→│  VIMS API   │────→│  PostgreSQL │
│    App      │     │   (3450)    │     │  (Database) │
└─────────────┘     └──────┬──────┘     └─────────────┘
                           │
                    ┌──────▼──────┐
                    │    Redis    │
                    │   (Queue)   │
                    └──────┬──────┘
                           │
              ┌────────────┼────────────┐
              ▼            ▼            ▼
        ┌─────────┐ ┌──────────┐ ┌──────────┐
        │ Object  │ │ Change   │ │  Risk    │
        │Detection│ │Detection │ │Classifier│
        └─────────┘ └──────────┘ └──────────┘

Features

• Object Detection: YOLO-based component detection (card readers, PIN pads, etc.)
• Change Detection: Compare observations with baseline images
• Risk Classification: Green/Yellow/Orange/Red levels
• Real-time Alerts: Email, SMS, webhook, push notifications
• Dashboard: Map view, timeline, statistics
• API: RESTful API with JWT authentication

API Endpoints

Authentication

• POST /api/v1/auth/register - Register new user
• POST /api/v1/auth/login - Login
• POST /api/v1/auth/refresh - Refresh token
• GET /api/v1/auth/me - Get current user

Objects

• GET /api/v1/objects - List monitored objects
• POST /api/v1/objects - Create new object
• GET /api/v1/objects/:id - Get object details
• POST /api/v1/objects/:id/baseline - Set baseline images

Observations

• POST /api/v1/observations - Upload observation images
• GET /api/v1/observations/:id - Get observation
• POST /api/v1/observations/:id/process - Reprocess observation

Detections

• GET /api/v1/detections - List AI detections
• POST /api/v1/detections/:id/verify - Verify detection

Alerts

• GET /api/v1/alerts - List alerts
• PUT /api/v1/alerts/:id/status - Update alert status
• POST /api/v1/alerts/:id/escalate - Escalate alert

Dashboard

• GET /api/v1/dashboard/overview - Dashboard statistics
• GET /api/v1/dashboard/objects - Objects for map view
• GET /api/v1/dashboard/timeline - Activity timeline

AI Training

Data Collection

# Generate synthetic training data
node src/training/data-collection.js atm 1000

# Validate dataset
node src/training/data-collection.js atm --validate

Model Training

# Install Python dependencies
pip install ultralytics

# Train YOLO model
python src/training/train-yolo.py atm --epochs 100

# Validate model
python src/training/train-yolo.py atm --validate

Deployment

Docker Compose (Development)

docker-compose up -d

Kubernetes (Production)

# Apply configurations
kubectl apply -f k8s/

# Check status
kubectl get pods -n vims

AWS

# Setup AWS infrastructure
./scripts/setup-aws.sh

# Deploy
./scripts/deploy-aws.sh

Configuration

Environment Variables

Variable	Required	Default	Description
NODE_ENV	Yes	development	Environment mode
PORT	No	3450	API port
DB_HOST	Yes	-	PostgreSQL host
DB_PASSWORD	Yes	-	Database password
REDIS_HOST	Yes	-	Redis host
JWT_SECRET	Yes	-	Secret for JWT tokens
S3_BUCKET	Yes	-	S3 bucket for images
AWS_ACCESS_KEY_ID	Yes	-	AWS access key
AWS_SECRET_ACCESS_KEY	Yes	-	AWS secret key

See .env.example for all options.

Testing

# Run all tests
npm test

# Run with coverage
npm run test:coverage

# Run specific test
npm test -- objectDetection.test.js

Monitoring

Health Checks

• GET /health - Basic health
• GET /health/ready - Readiness probe
• GET /health/live - Liveness probe

Metrics

• Prometheus metrics at /metrics
• Grafana dashboards
• CloudWatch integration

Documentation

• API Documentation
• Deployment Guide
• Production Plan

Support

• Email: support@landvex.com
• Documentation: https://docs.landvex.com/vims
• Issues: https://github.com/landvex/vims/issues

License

Proprietary - Landvex AB