Project · Planning and Construction · USA

VIATechnik: Automatically Detecting Doors, Windows and Light Fixtures in Construction Drawings

Your contact for a similar project is Daniel Giebelhaus in Zurich. Our development team does the implementation.

Client
VIATechnik LLC
Location
Chicago, USA
Industry
Building Planning and Construction

1 to 5 s

per drawing sheet

CSV / JSON

list of every detected element with coordinates and dimensions

Starting point

Doors, windows, light fixtures and other elements in construction drawings are usually searched for and counted by hand, sheet by sheet. That is slow, tedious and error-prone, and every error carries forward into quantities, reviews and cost estimates.

What we built

A Windows application. You load a drawing as a vector PDF and choose the element type, for example doors, windows or light fixtures. The software reads the drawing's vector data directly instead of interpreting a scanned image, and finds the elements using templates, geometry and attributes. That is more accurate than working from an image. Detected elements are marked in red and exported as an image, together with a CSV or JSON report giving coordinates and dimensions for every element.

Result

Every drawing sheet is processed in 1 to 5 seconds. Reviewers get a marked-up drawing and a machine-readable list of every detected element. Finding and counting elements for drawing review and quantity takeoff becomes fast and repeatable.

Technologies

C++OpenCVTensorFlowInkscapeSVG parsingVector template matching

Describe your task in two sentences

We will tell you whether a dedicated tool is worth it and what it would take.

Describe your task