A point cloud depicts reality in high detail – but a survey plan does not require millions of individual points, rather clearly defined geometric elements. A roadside should be available as a line. A guardrail should be captured as a coherent object. An embankment requires an upper and lower boundary. Ground markings must be available as lines or areas.

This is exactly the transformation our AI handles: it analyzes the three-dimensional geometry, classifies relevant structures, and generates coherent, surveying-ready geometries from them. The manual effort for digitizing, tracing, and structuring is thereby significantly reduced.

Not every object in a point cloud shares the same geometric properties. A guardrail differs fundamentally from a lane marking or an embankment. Our solution therefore combines machine learning, 3D geometry analysis, and rule-based post-processing – depending on the object class, different features are evaluated, such as height differences, local slopes, normal vectors, and spatial continuity.

When LiDAR intensity values or suitable image data are available, roadway markings can also be detected automatically. Geometry and reflection or image information are combined to achieve reliable detection results. The result is CAD-ready lines or areas with a defined object class that can be integrated directly into existing planning and GIS workflows.

In development – Break lines from Q2 2027, terrain model from Q3 2027

Slopes can require considerable manual analysis effort. Our solution analyzes local elevation changes, gradients, normal vectors, and the three-dimensional terrain shape. Continuous polylines are generated from the identified areas – precise and without time-consuming manual tracing.

Vertical and linear structures have distinctive geometric properties that allow them to be reliably classified from the point cloud. The required object classes are defined before project start and can be extended on a per-project basis – so the solution can be adapted to individual infrastructure requirements.

On request

For long road sections, it matters not only which object was detected, but also where along the route it is located. Our processing can therefore automatically divide detected lines into defined route segments – with a freely selectable segment length of 10, 12.5, or 25 meters, or project-specific. Each segment receives its own ID and attributes for GIS, inventory, and asset management.

Real road networks are complex. Intersections, driveways, side streets, traffic islands, or closely spaced objects can lead to ambiguities. Our processing therefore does not consider individual points alone – the AI always takes the spatial context into account.

Our goal is not to replace the surveyor. The AI primarily takes over repetitive and time-intensive digitization work. Professional review remains an integral part of the process. This way, the AI handles a large share of the manual work while surveying responsibility is preserved.

The generated geometries are delivered in the formats actually used in existing surveying, CAD, and GIS workflows. Layer structure, attribute schema, and data organization can be adapted to your own standards.

2D or 3D polylines with a defined layer structure for use in AutoCAD, BricsCAD, and other CAD systems. Layer names and data structure can be fully adapted to your existing CAD standards.

GIS-ready output for direct use in existing geographic information systems and infrastructure cadastre platforms. Geometries are delivered with a complete attribute schema – ready for integration into operational GIS workflows.

The economic benefit of automation grows with the volume of data. A few hundred meters of road can still be evaluated manually – at 20, 50, or 150 kilometers, manual digitization becomes the bottleneck. Our processing is therefore designed from the ground up for large data volumes.

The solution covers the full spectrum, from one-time asset surveying to continuous infrastructure management. Every application benefits from the same automated processing core, adapted to its specific requirements.

The standard is the Jaroona Cloud. Private cloud, customer-owned cloud, on-premise, and hybrid models are available on request.

Our solution is provided by default as a cloud service. This means large point clouds can be processed without the customer having to build any additional GPU or AI infrastructure. New measurement campaigns can be uploaded automatically, processed, and delivered as finished results.

For projects with particularly high requirements for data protection, information security, or data sovereignty, the entire processing can also be operated fully on-premise within the customer's infrastructure.

Point clouds can contain highly detailed information about roads, structures, and critical infrastructure. Controlled handling of this data is therefore an integral part of our solution – not an afterthought.

Processing takes place on servers in the EU. Data transfer is encrypted, with separate project workspaces and role-based access rights.