Remote-Sensing Research

Intelligence at the edge. No cloud required.

Read the R&D log ↗
What we do

Multi-modal real-time situational awareness.

We fuse acoustic, optical, LiDAR, and radar into a single real-time picture — detection, classification, and tracking that runs on-device, in the field, with no cloud in the loop.

03Core capabilities
06Civilian domains
05Sensor modalities
In the field

Sensors, deployed.

▸ RECFIELD-FOOTAGE_0100:00 / --:--
Placeholder — drop a deployment reel or demo capture here: a drone LiDAR sweep, a hydrophone array on station, an edge board inferring in situ.
What we do

Three core capabilities.

Edge hardware — board / sensor macro
Field deployment — drone / vessel / site
Data — spectrogram / point cloud / map
Selected work

Signal in the noise

Underwater target recognition, from a multichannel hydrophone array — the faintest signature drawn out of restless ocean noise by a model held in exact balance. Every point of accuracy weighed against every cycle of compute; engineered light enough to live where it works — at the sensor, in the water.

Read the engineering notes ↗
Faint signal · high noise▸ REC
ACC 0.94LAT 11msSNR −6dBPWR 0.4W
ACOUSTICRGBMULTISPECTRALLIDARRADAR
The authority engine

Latest from the R&D log

All posts ↗
2026-05-14EDGE

Quantizing a vibration-anomaly model for a $60 edge board

INT8 on a Cortex-M55 without losing the tail of the distribution.

7 min read
2026-04-22ACOUSTICS

What 10,000 synthetic spectrograms taught us about input design

A clean-room study on representation choices for condition monitoring.

11 min read
2026-03-30FIELD NOTES

LiDAR mapping a rail siding with a sub-250g drone

What a featherweight platform can — and cannot — resolve.

5 min read

Have a sensor, a site, or a fleet that should be smarter?

We take on a limited number of engagements per quarter. If your problem involves edge constraints, unusual sensors, or no labeled data — that's our specialty.

Book a technical consultationSend us your problem