---
lang: en
title: "AI pallet and product counting with your existing cameras"
url: https://nabrio.com/use-cases/item-and-pallet-counting
canonical: https://nabrio.com/use-cases/item-and-pallet-counting
updated: 2026-10-27
publisher: Nabrio Co., Ltd. (nabrio.com)
---

# AI pallet and product counting with your existing cameras

Nara counts items, parts, products and pallets from IP or industrial cameras, and object tracking makes sure each one is counted exactly once. Totals appear live on a dashboard and can go straight to your MES or ERP, all processed on your own hardware.

- Sectors: [Manufacturing](https://nabrio.com/industries/manufacturing.md)
- What it takes: Ready to configure. Works with Nara’s built-in models. You set up the zones, rules and outputs. Unusual items can be trained in Reva.
- Products: [Nara](https://nabrio.com/nara.md), [Reva](https://nabrio.com/reva.md)

## The problem

Manual counts of output, pallets, parts or batches are slow, error-prone and never real-time.

## How it works

- **Input:** IP or industrial camera over the line, dock or storage area
- **Process:** Object detection and tracking with a counting line or zone, so each item is counted once
- **Action:** Counts logged and shown live, sent to MES or ERP, with batch-complete or short-batch alerts

Draw a counting line or zone on the camera view. Nara detects each item, tracks it across frames and counts it once as it crosses the line or enters the zone. Counts are stored in Nara’s built-in database, shown on dashboard counters and charts, and published over MQTT or HTTP to your production systems. A count-to node can raise a batch-complete or short-batch alert.

## What you need

- An IP camera (RTSP) or Basler industrial camera with a clear view of the items
- A PC, industrial PC or NVIDIA Jetson running Nara
- Optional: an MQTT broker or HTTP endpoint for your MES or ERP

## Nara building blocks

- Camera nodes
- Object detection
- Tracker count line and count zones
- Count-to
- Database table
- Dashboard counters and charts
- MQTT and HTTP output

AI models: [General object detection](https://nabrio.com/nara/ai-models.md), [Object tracking and analytics](https://nabrio.com/nara/ai-models.md)

## What it improves

- Count accuracy
- Labour hours saved
- Real-time production visibility

## Frequently asked questions

### Can it count our own products?

Common objects are detected out of the box. If your items are unusual, we train a model on them in Reva and Nara uses it in the same flow.

### Will the same item be counted twice?

No. Nara tracks each item across frames and counts it once, when it crosses the line or enters the zone.

### Can we use the cameras we already have?

Usually, yes. Nara reads standard IP cameras over RTSP, as well as Basler industrial cameras, USB webcams and video files.

## Related use cases

- [Barcode and label inspection](https://nabrio.com/use-cases/barcode-and-label-inspection.md)
- [Sorting and grading](https://nabrio.com/use-cases/sorting-and-grading.md)
- [Robot and AMR orchestration](https://nabrio.com/use-cases/robot-and-amr-orchestration.md)

Talk to us about item and pallet counting: sales@nabrio.com. [Download Nara](https://nabrio.com/download.md).