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.
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.
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.
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.
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
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.
Related
More ways HSCAM cameras get integrated
Recognize this problem in your own inspection or research setup?
I have a similar problemThis 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
contact@hscam.com · hscam.com