Store analytics that stay in the store
Detection models run on hardware in the store. Frames are processed locally, and what leaves the device is a result, not the footage.
- Inference on local hardware
- IoU tracking
- Video preview before rollout
What this solves
Store analytics usually means streaming camera footage somewhere else, which is expensive and hard to justify to anyone. You bring the cameras; the model runs on a device beside them.
Who this is for
- Retail technology teams
- Systems integrators
- Store operations
Why edge inference fits
Decisions happen locally
Inference runs on the device itself. There is no round trip to a server between a frame and a result.
Keeps working offline
A deployed model runs without a connection. Devices send heartbeats and inference logs when they reconnect.
Data stays where it is captured
Frames are processed on the device. Nothing has to leave the site for a prediction to be made.
The whole pipeline, one stage at a time
Every stage below is a screen in the platform, not a diagram of something you still have to build.
0110
01Stage 1 of 10
Collect data
Upload samples or import an existing folder tree.
Data
What you get in the platform
Bounding-box annotation editor
Draw, adjust and relabel boxes directly on the dataset grid.
NanoVision and Vision Pro detection
Centroid detection with NanoVision v1 or v2, or box detection with Vision Pro.
Detection post-processing
Confidence threshold, class filter, non-maximum suppression and IoU tracking, tuned in the UI.
Video post-processing preview
Run a clip through the pipeline and watch the rendered result before you commit the settings.
Live classification
Send a frame or a device stream through the current model and see the prediction immediately.
Deployment builds
Turn any trained model into a ready-to-run package for the target you pick.
What teams build with it
Shelf stock-out detection
Detect empty facings from a fixed shelf camera.
Queue-length counting
Count people in a defined view with stable identities.
Product-facing verification
Check that products are present and oriented as expected.
Footfall counting
IoU tracking keeps a person who lingers from being counted twice.
Planogram spot-checks
Classify a section against the layout it is meant to match.
Where this runs
The targets teams reach for on this kind of project.
Raspberry Pi
Python inference package
Installs with the device client and runs as a service
UNO Q
Linux runtime package
The on-device runner takes it from there, no glue code to write
TensorFlow Lite
TensorFlow Lite model with an inference library
Embed it in any runtime that can load TensorFlow Lite
Petal Edge builds for six targets in total, each with its own package format and constraints.
See all deployment optionsOne platform, start to finish
Data, labels, training, evaluation, post-processing, deployment and the fleet live in one place, with nothing to stitch together.
The whole lifecycle
Collect, label, train, evaluate, post-process, deploy and monitor without leaving the platform.
Models sized for edge hardware
NanoVision, Vision Pro and MobileNetV2 are built to run on devices, not on datacentre GPUs.
Six deployment targets
One trained model, packaged for the hardware you already run.
A fleet you can reach
Register devices, read their inference logs, and push new models over the air.
What’s included
- Dataset import from COCO, YOLO, Pascal VOC, Open Images and Edge Impulse JSON
- AI-assisted labeling with human review before anything is applied
- Confusion matrix, per-class metrics and model testing across versions
- Post-processing with NMS and IoU tracking
- Over-the-air model updates to registered devices
- Project export, so your data and models stay portable
Keep the footage where it is
Create a project, bring your data, and take it through to a deployed model.