inv.geo.rs Belgrade, 2026
the viewer itself, driving the mission

Surveyed once,
read by machine.

One van, one pass, sixteen kilometres of Belgrade. From the laser and the panoramas the system reads kerbs, road markings, signs and covers — then checks every one of them against the city's own register of 82 surveyed layers.

Where we agree, and where we do not

Every kerb candidate the model found on mission 307-1, coloured by how far it is from the nearest line a surveyor measured.

92.0 % on the surveyed kerb, within 30 cm
0.8 % on another surveyed edge: island, median, pavement
2.4 % within a metre of a surveyed line
4.8 % nothing surveyed within a metre

The other direction matters more. Of 16.2 km of surveyed kerb inside the project corridor, 87 % has one of ours within 30 cm. The 13 % that does not is where to look first — and some of the red above is ours to answer for, not the register's.

Four ways in

Each one opens the live scene on this server, not a picture of it. The point cloud is streamed; nothing is pre-rendered.

DRIVE

The guided drive

The camera follows the van's own route and stops at twelve things worth showing. Nothing advances on a timer: one key puts the card away, the same key flies on.

DECK

The deck

Fourteen slides, the argument end to end. Every figure in it is a door: click one and the scene opens live at that exact camera.

307-1

Mission 307-1

755 million points. The kerb and marking overlays, the sign inventory with the photograph each reading came from, and the classes the model assigned.

306-5

Mission 306-5

A second mission, 13 km, in the same viewer — so the numbers above can be read against something other than themselves.

What it reads, and what it is checked against

Every class the model produces is compared with the layer the city already surveys it in. The codes are the register's own.

T05Kerb
T22–T26Road markings: crossings, arrows, lines
T19Signs, and the posts they stand on
T66Manhole covers
T65Gullies
T43Traffic mirrors
T06, T14Pavement edges
T08–T11Islands and medians