Inference Overlay: Difference between revisions

From Tygron Preview Support Wiki
Jump to navigation Jump to search
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]].  


{{gallery|
<gallery heights="300">
foliage_inference_labels.jpg|Labeled features|
foliage_inference_labels.jpg|Labeled features
foliage_inference_scores.jpg|Label Scores|
foliage_inference_scores.jpg|Label Scores
foliage_inference_masks.jpg|Pixel Masks|
foliage_inference_masks.jpg|Pixel Masks
foliage_inference_boxes.jpg|Bounding Boxes|
foliage_inference_boxes.jpg|Bounding Boxes
foliage_inference_foliage_height.jpg|DSM DTM on identified features|
foliage_inference_foliage_height.jpg|DSM DTM on identified features
foliage_inference_max_neighbhor_height.jpg|Iterated max neighboring height|
foliage_inference_max_neighbor_height.jpg|Iterated max neighboring height
}}
</gallery>


{{article end
{{article end

Revision as of 11:59, 14 October 2024

Trees detected with Inference Overlay.

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.