UVS Vision — UVS Dynamics

Onboard computer vision for UAVs — GPS-denied navigation and automatic target detection

A standalone onboard module built around Nvidia Jetson Orin Nano Super and a high-resolution CSI camera. Two operating modes: GPS-denied visual navigation (map matching → drone position) and automatic detection of military hardware in aerial imagery.

UVS Vision is a separate product line from UVS Dynamics, built around onboard computer vision for UAVs. Unlike our radio links, this module doesn’t depend on a comms channel: all inference runs locally on an onboard Nvidia Jetson Orin Nano Super.

The drone matches its live camera feed against a pre-loaded satellite map of the area. The system determines the current position by identifying which map tile the camera is looking at — with no external signal at all. A solution for areas where GPS is jammed by EW or spoofed.

Left — a frame from the drone's onboard camera; right — the matching tile from the pre-loaded satellite reference, found by our system. A precise match, no GPS.

How it behaves across terrain types

Three examples from different flights below. The bigger the contrast between terrain types, the more interesting it gets — the algorithm has to handle both feature-rich scenes and near-uniform fields.

Populated terrain

Buildings, roads and field boundaries provide plenty of unique features. The easiest scenario — position is found in a fraction of a second and stays stable even under fast movement.

Forested terrain

Uniform texture, few obvious landmarks. The model finds unique fragments of pattern and geometry — paths, clearing edges, forest-water boundaries — and holds position where a GPS system would have to fall back to dead reckoning.

Open fields and low-feature terrain

The hardest case — large featureless areas: open fields, snow, steppe. Inter-frame integration and a wider search window do the work here: the algorithm refines its position hypothesis the moment a single characteristic object enters the frame.

Automatic target detection

The second mode is searching for and classifying military hardware in aerial imagery. The system runs in two operating modes:

Sector scan. The drone takes wide-area shots from altitude. Each frame is sliced into tiles no larger than 100 × 100 m. A fast single-stage detector runs the first-pass search; the camera then automatically re-focuses and takes a detail shot; a two-stage verifier confirms the class with high precision.
Real-time tracking. Continuous analysis of the video stream. The camera automatically pans and adjusts focus to keep the target in frame.

Why a separate product

UVS Vision is built on a different set of competencies than the radio links — computer vision, deep-learning models, aerial-imagery processing. The ML engineers on the team run their own pipeline: dataset assembly from open sources, in-house annotation tooling that runs fully offline, training and verification of models.

This line evolves in parallel with the radio products: separate customers, separate roadmap. As a module, UVS Vision can be installed on any UAV platform — both where UVS Link or UVS Link Pro is already running, and where customers have taken only the vision stack from us.