Rasik Labs
← Back to projects

Computer Vision

Retail shelf intelligence and inventory monitoring

Upload a shelf photo and get product counts, empty zone detection, and stock-level alerts — no manual audit needed.

Problem

Field teams armed with clipboards cannot scale across hundreds of SKUs and dozens of aisles. Existing inventory systems rely on POS data that only reflects what was sold, not what is missing right now. The challenge is a vision system that handles real-world shelf variation — different lighting conditions, densely packed products, rotation across store formats, and delivers actionable alerts fast enough to matter.

System demo

Inference running on SKU-110K public dataset · YOLOv8m pretrained checkpoint · Annotations rendered with OpenCV

Architecture

Step 1

Shelf image upload

Step 2

Region detection

Step 3

Product / facing count

Step 4

Empty zone flagging

Step 5

Alert generation

Step 6

Dashboard export

MetricsPrototype benchmarks measured on SKU-110K public dataset — to be replaced with production results

mAP@50 · product detection

84.7%

mAP@50 · empty zone detection

89.1%

Precision

88.3%

Recall

85.6%

Inference (GPU)

42ms

False stockout rate

6.2%

Tech stack

Python 3.11YOLOv8m / YOLOv8sOpenCVAlbumentationsSKU-110K + Roboflow Empty Shelf datasetFastAPIStreamlitadaptable to your existing BI tools or dashboard infrastructureDocker

Edge deployment — we've shipped this on hardware

On-device inference keeps raw footage on-premises, eliminates cloud latency, and works reliably in stores with poor connectivity. We are experienced deploying vision models on edge hardware across a range of devices and can assess, recommend, and configure the right platform for your throughput, power budget, and environment.

NVIDIA Jetson OrinRaspberry Pi 5Qualcomm AI Hub (QCS series)...and other devices per your requirements

Production considerations

  • Camera placementfixed ceiling or aisle-end mount recommended over handheld; consistency directly impacts model accuracy
  • Lighting variationaugmentation pipeline handles brightness and contrast shifts across store formats and times of day
  • SKU rotationnew product introductions degrade accuracy over time; a retraining trigger and workflow is built into every delivery
  • Alert threshold tuninghigh-velocity SKUs (beverages, dairy) need tighter thresholds than slow movers; configurable per category
  • Dashboard integrationalert output can feed your existing store management system, POS platform, or BI tool via webhook or REST API; Streamlit is the default for standalone deployments
  • Privacyon-device inference means raw footage never leaves the store; only structured alert data is transmitted

Explore this project

Live demo and source code links will be added as they become available.

View demo — Coming soonView repository — Coming soon