Build a safety detector on your own footage
Petal Edge does not ship a pre-trained safety model. You label footage from your own site, train a detector on it, tune the thresholds against a real clip, then deploy.
- AI-assisted labeling
- Threshold and class filters
- IoU tracking
What this solves
An off-the-shelf safety model was trained on someone else's site, with their cameras, angles and lighting. Yours are different, which is why the detector has to be trained on your footage.
Who this is for
- EHS and site safety teams
- Systems integrators
- ML engineers
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.
AI-assisted labeling
Describe what you are looking for in plain text and review the proposed boxes before they land.
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.
Over-the-air model updates
Resolve the compatible deployment for a device and push the update without touching the hardware.
What teams build with it
Helmet check at an entry gate
Detect whether head protection is present as people pass a fixed camera.
High-visibility vest detection
Trained on your own yard footage, in your own lighting.
Glove detection at a workstation
Small-object detection close to the work surface.
Counting entries into a monitored area
IoU tracking keeps one identity per person, so one crossing counts once.
Tuning alert sensitivity before rollout
Move the confidence threshold, render a real clip, and see the effect first.
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
Label your footage and train a detector
Create a project, bring your data, and take it through to a deployed model.