Inference Overlay: Difference between revisions
No edit summary |
No edit summary |
||
| Line 2: | Line 2: | ||
The AI Inference Overlay is a [[Grid Overlay]] which can spatially identify features using one or more Prequel Grids. Features are identified using a Convolution [[Neural Network]]. This neural network takes a subsection (window) of the input grid and either classifies or detects one or more objects in that window. The window of detection marches over the input grid with a [[Stride fraction (Inference Overlay)|configurable stride]]. | The AI Inference Overlay is a [[Grid Overlay]] which can spatially identify features using one or more Prequel Grids. Features are identified using a Convolution [[Neural Network]]. This neural network takes a subsection (window) of the input grid and either classifies or detects one or more objects in that window. The window of detection marches over the input grid with a [[Stride fraction (Inference Overlay)|configurable stride]]. | ||
==Foliage Example== | |||
Using a [[Satellite Overlay]] of 0.1m detail, foliage features can be identified using an [[Inference Overlay]] and enhanced with a DTM, DSM, [[Combo Overlay]] to combine these and an optional iterative [[Avg & interpolation Overlay|Max Overlay]]. For more information, see this [[How to create foliage height areas from an inference overlay|how-to]]. | |||
<gallery widths="200"> | <gallery widths="200"> | ||
foliage_inference_labels.jpg|Labeled features on 0.1m satellite image | foliage_inference_labels.jpg|Labeled features on 0.1m satellite image | ||
Revision as of 12:27, 14 October 2024
The AI Inference Overlay is a Grid Overlay which can spatially identify features using one or more Prequel Grids. Features are identified using a Convolution Neural Network. This neural network takes a subsection (window) of the input grid and either classifies or detects one or more objects in that window. The window of detection marches over the input grid with a configurable stride.
Foliage Example
Using a Satellite Overlay of 0.1m detail, foliage features can be identified using an Inference Overlay and enhanced with a DTM, DSM, Combo Overlay to combine these and an optional iterative Max Overlay. For more information, see this how-to.
Labeled features on 0.1m satellite image
Label Scores
Pixel Masks
Bounding Boxes
DSM DTM on identified features
Max neighboring height within 0.25m, iterated 5 times
How-to's
- How to import trees based on an Inference Overlay
- How to use the Inference Overlay to detect and add solar panels to buildings based on a Satellite Overlay
See also
