Foliage (Neural Network)

The Foliage Neural Network is a Region-based Convolutional Neural Network (RCNN) that identifies foliage of individual trees and bushes, mainly for gardens and private property. This Neural Network is not suited for identifying individual trees within forested areas.

An Inference Overlay can be configured with this Neural Network. Its default settings are:

Preferred grid cell size: 0.25m

Inference mode: BBox Detection

Mask threshold: 0.30 (30%)

Score threshold: 0.20 (20%)

Stride fraction: 0.50 (50%)

Identifiable features:

1. Deciduous Tree
2. Pine Tree
3. Heath area
4. Hedge
5. Bush
6. Reed
7. Flower bed
8. Leafless Tree Area

• 
  Labeled features on 0.25m satellite image
• 
  Label Scores
• 
  Pixel Masks
• 
  Bounding Boxes

Notes

• In order to use the identified foliage areas as input for a Heat Overlay, additional steps have to be taken to obtain an actual foliage height.

How-to's

• How to detect foliage using an Inference Overlay
• How to create foliage height areas based on an Inference Overlay
• How to create the input overlay for leafless trees detection using the Inference Overlay

See also

• Inference Overlay
• RCNN
• ONNX
• Foliage areas (Heat Overlay)

---

Inference Overlay

Group

Model attributes

Inference

Neural Network • Input tensor • Output tensor

Model attributes

Box overlap • Inference mode • Mask threshold • Prioritize labels • Score threshold • Stride fraction

Prequels

A • B

Result types

Boxes • Labels • Masks • Scores • Debug gt instances • Center points

Neural Networks

Foliage • Solar panels