01 · The environment
Jam the link, and most ISR payloads become dead weight. The intelligence was never at the sensor.
Conventional ISR streams video to a ground station where a person watches it. That chain breaks in three places: bandwidth, jamming, and the attention of an operator three hours into a shift. Scotopic moves detection and tracking to the sensor itself, so the chain has one link left. What goes down is track state, 26 bytes per update instead of megabits of video, and it buffers when the link drops.
The same shift is now doctrine. Fibre-guided drones carry no radio, which is exactly why the RF layer that used to raise the first alarm no longer does, and why optical detection is being bought again. The SAPIENT architecture — written by Dstl for the UK MoD, published as BSI Flex 335 v2.0, demonstrated across NATO TIE exercises and under STANAG ratification — asks sensor edge nodes to process locally and report summaries rather than raw feeds. Scotopic was built that way from the first commit.
02 · Capability
One hard problem, done properly.
Small aerial targets at range, against sky, terrain and clutter. A drone at 2 km is a handful of pixels: at that scale shape carries almost no information, and most detectors quietly stop working. This is the part we built for.
Kalman tracking with coasting through occlusion, so a target that passes behind terrain is picked up again rather than lost. Motion is what separates a drone from a bird when shape cannot.
A versioned track contract with bearing, elevation, size and per-component uncertainty. Buffers on link loss, flushes losslessly on reconnect. The human makes the call.
Detect → Track → Report → Human decision
03 · Architecture
System architecture
Perception and tracking run at the sensor. Guidance-free. The operator makes the call.
04 · The product line
One module in the line today.
Other modules are in development. They will appear here when there is something measured to put next to them, and not before.
06 · Where this sits
A component, not a replacement.
There is real work happening in autonomy right now, and some of it is very good. Almost none of it is aimed at the specific problem of finding a small aerial target at range, on COTS silicon, with a false-alarm rate an operator will tolerate. That is where we started, and it is the only thing we publish numbers for yet.
A number is worth what the source is willing to publish beside it. That is why the cross-dataset figure and the uncharacterised rows sit on this page next to the good ones, in the same type. If you would rather not take ours on faith, do not start from the range — start from the threshold. We publish the 8 px floor precisely so you can work out what it means for your own optics, with a pencil, without asking us. Access to the detector itself runs as a scoped evaluation, on your hardware, with us in the room.
07 · About
Why software, and why us.
Scotopic started in robotics. Building machines that move is a good problem, but after a while the interesting part stops being the mechanism and starts being the judgement: what the machine sees, what it makes of it, and what it hands back to the person responsible.
That question got sharper when it stopped being academic. On this flank of Europe the airspace is contested now, and the aircraft flying in it go blind the moment someone decides to jam them.
Hardware is where you get locked in. Software is where you stay free. A perception layer is not tied to one airframe, one vendor or one supply chain. It runs on parts anyone can buy, on aircraft that already exist, and it makes them better without replacing them. That is the whole thesis: do not build another platform, build the thing that gives the platforms already in the air something worth having.
As for why us. We are small, and small is the wrong reason to buy from someone, so here is the right one. We started with one narrow problem, small aerial targets at range on COTS silicon, and we measure it the way it deserves. When our validation set turned out to be flattering us, we rebuilt it and wrote down that every number before that line was wrong. That habit is the product as much as the code is.
Scotopic is built in Romania, on the eastern flank, against the threat picture that is actually here. The decision stays with a human operator, by design and not by accident.
2025 S.R.L.
07 · Contact
Request a scoped evaluation.
Request a scoped evaluationOn your hardware, with your camera, on your footage. Ask for the method note, the track contract specification, or integration support for next-generation SAPIENT architectures.