BUILDINGS AND TREES
For this particular work, Lowe needed three rule sets —
a main, comprehensive workflow and two smaller, more
targeted workflows — which together required more than
100 individual processing steps.
Given the breadth and rigor of the first rule set, Lowe
used eCognition Server technology to batch-process the
workflow, which analyzed all the data inputs to delineate
and classify building footprints and vegetation. Once the
trees were classified, eCognition then classified shadows
and individual tree contours at 2-m to 3-m intervals.
The second rule set targeted each AOIs building
footprints and classified them like they are in the real
world, with different levels and elevations. The final
rule set refined the vegetation and building height
classifications to ensure building elevations weren't
skewed by trees on rooftop gardens.