Object detection & grading
Find, classify and grade what's in an image at a consistency a human reviewer can't sustain across thousands of frames.
← Computer vision portfolio
·Computer vision · reference example
Measurement in messy real conditions — like Aquabyte
Aquabyte is underwater CV for aquaculture — biomass estimation and sea-lice counting. It's a recognisable benchmark for a system class I build — here's what it does, and how I'd build yours.
Reference example — not my client. Aquabyte is an independent product I'm not affiliated with, shown as a benchmark for this kind of build.
Live preview of www.aquabyte.ai — their site, shown as reference.
01What a Aquabyte-class system does
The shape of the build
At its core, Aquabyte is underwater CV for aquaculture — biomass estimation and sea-lice counting — the kind of system you reach for when you have object detection and measurement in the real world. Here is how I'd build one for you.
Measurement from images
Estimate size, count and quantity in variable lighting and angles, where the hard part is being right when conditions aren't ideal.
Edge & real-time inference
Models that run on-device and in real time for safety and monitoring, not just a batch job on a server.
Video event detection
Spot the moments that matter in a stream and turn them into structured events downstream systems can use.
02More Computer vision examples
Other benchmarks in this class
Same system class, different products. Each opens a page like this one.
Want something like Aquabyte?
Tell me what it needs to do and where it's getting stuck. I'll tell you honestly whether I'm the right person and what it would take — no pitch deck, no discovery call to book a discovery call.