Skip to content
HSCAM

Application · Realtime Droplet Inspection, Fraunhofer IIS/EAS Dresden

STREAMER watches every droplet. NANO picks the frame to characterize.

A research pipeline at Fraunhofer IIS/EAS Dresden pairs two HSCAM products. A STREAMER camera, backlit through precision optics, watches the whole droplet path at a high frame rate and builds the labelled image set an AI needs to learn what a good droplet looks like. An HSCAM NANO unit triggers on the image itself: it captures a single frame at the right moment and characterizes it on the camera, with no host PC.

A laptop screen showing a live, high-contrast silhouette of a single paint droplet captured by the camera rig beside it. Research application — Fraunhofer IIS/EAS Dresden

Why this exists

Learn it, then look only where it matters

A machine-vision AI that will monitor paint or coating droplets — flagging a missing droplet, a misshapen one, or a satellite spray — first has to be trained on a large number of clear, correctly labelled example images. That's the first half of this pipeline.

Recording every frame of every droplet would bury the evaluation in data. That's the second half: NANO scans the image, triggers on its content and captures only the frame that matters. That frame is characterized on the camera, and the characterization is the basis for regulating the droplet generator, a development goal of the project with Fraunhofer.

Half one — STREAMER

A camera, a beam-splitter, and a single droplet

A compact HSCAM STREAMER camera looks through a beam-splitter cube along the same axis as a backlight, so each droplet from the dispensing valve appears as a sharp, high-contrast silhouette — the clearest possible image to label by hand or feed to a model.

A compact HSCAM camera with a telecentric lens, aligned to a beam-splitter cube for coaxial backlighting, mounted on a precision motion-stage rig.
Camera, telecentric lens and beam-splitter
A compact HSCAM camera, sharing the same ridged housing pattern as the STREAMER family, mounted on the motion-stage rig.
The camera beside the dispensing valve

The valve is mounted on a precision XY stage so the camera can be positioned relative to the droplet with sub-millimetre repeatability — the same kind of precision integration work described in HSCAM's engineering & custom integration .

Half two — NANO

Trigger on the image, characterize the frame

An HSCAM NANO unit runs alongside the STREAMER camera in this pipeline. In the evaluation setup both cameras look at the droplets: STREAMER records at a high frame rate, NANO decides which frame to take.

01

Image-based triggering

NANO scans the image and triggers the capture of a single frame at the right moment, from the image content and not from a separate sensor. Only relevant frames are captured, which cuts the image data to a few frames per second without giving up fast detection of events.

02

ROI extraction on the VSoC

The droplet's region of interest is extracted on the VSoC sensor chip itself.

03

Characterization on the camera

The captured frame is characterized by the camera's integrated image processing and AI: the neural processing unit of the additional microcontroller on the NANO camera, with no host PC involved.

04

Goal: regulation

The characterization is the basis for regulating the droplet generator's parameters. That regulation is a development goal of the project.

HSCAM NANO is a prototype, and this evaluation setup is part of its development. See the NANO product page for the camera itself.

Demonstrated Results

What the STREAMER camera actually captures

Real recorded footage from the rig: a backlit droplet, and the smaller satellite droplets that a good frame needs to capture too — exactly what an inspection model has to learn to tell apart.

Recorded footage

Droplet and satellite droplets, backlit

Recorded at
8,000 fps
Image size
1,280 × 128 px
Frame
Backlit silhouette
Shows
Main droplet + satellites

One frame carries a drawn line between two points — an analysis overlay from the capture setup, not added for this page.

A laptop screen showing a live, high-contrast silhouette of a single paint droplet captured by the camera rig beside it. Research application — Fraunhofer IIS/EAS Dresden

Live view on-screen

Realtime Droplet Inspection — STREAMER high-frame-rate footage, NANO image-triggered characterization

A compact HSCAM STREAMER camera, backlit through a beam-splitter cube, observes the whole droplet path and captures high-contrast droplet silhouettes to generate an AI training set. An HSCAM NANO unit triggers on the image: it captures one frame at the right moment and characterizes it on the camera (ROI extraction on the VSoC chip, AI in the camera’s microcontroller with NPU). The characterization is the basis for regulating the droplet generator.

STREAMER role
Observes the whole droplet path, generates AI training data
NANO role
Image-based trigger captures one frame at the right moment; ROI extraction on the VSoC chip; characterization by the camera’s microcontroller with NPU; basis for regulating the droplet generator
Close-up of the camera's lens and telecentric mount on the motion-stage rig.
Camera lens and mount, close up

Why HSCAM here

One vendor, from wide observation to the right frame

Generating usable training images depends on image quality and how tightly the camera fits a purpose-built optical path. Picking and characterizing the right frame depends on a different kind of speed: scanning and processing on the camera, with no host PC. HSCAM builds both ends.

Compact housing

Small enough to mount directly on a beam-splitter cube on a shared optical axis, alongside the dispensing hardware it's imaging.

Clean, high-contrast capture

Backlit droplets are captured as sharp silhouettes — exactly the kind of image that's fast to label and easy for a model to learn from.

Triggered on the camera

NANO triggers and characterizes on the camera, so picking the frame does not wait for a host PC round trip.

Recognize this problem in your own inspection or research setup?

I have a similar problem

This is a research application. Whether a similar approach suits another process is checked case by case, in your own setup, before a limited test is agreed. See how a pilot project works.

Talk to an engineer about a research or inspection setup

Tell us about your optical path, your object, and what you need the images for.

Helpful, but not required

  • What your process does and what goes wrong, or what you cannot see today
  • Speed or cycle time, if you know it
  • Measurement or trigger signals that exist on the machine
  • Environment: temperature, lighting, mounting space
HSCAM GmbH · Angerstraße 40–42, Haus B · 04177 Leipzig, Germany
contact@hscam.com · hscam.com

* Required

Frame rate and image area still unknown? Just describe the sequence – we help with the design.

Your details are sent to HSCAM to answer this enquiry only — see our privacy notice, which also covers the Cloudflare spam check below. If you arrived through a campaign link, its utm_ parameters and the page you are on are sent with your enquiry.

Sent straight to contact@hscam.com.