Solar panels (Neural Network): Difference between revisions
Jump to navigation
Jump to search
Created page with "The Solar panels Neural Network is a Convolution Neural Network that identifies solar panels, mainly situated on roofs of buildings. An Inference Overlay can be configured with this Neural Network. Its default settings are: :Preferred grid cell size: 0.1m :Inference mode: BBox Detection :Mask threshold: :Score threshold (Inference Overlay)|Score..." |
No edit summary |
||
| (2 intermediate revisions by 2 users not shown) | |||
| Line 1: | Line 1: | ||
{{deprecated}} | |||
The Solar panels Neural Network is a Convolution Neural Network that identifies solar panels, mainly situated on roofs of buildings. | The Solar panels Neural Network is a Convolution Neural Network that identifies solar panels, mainly situated on roofs of buildings. | ||
| Line 4: | Line 5: | ||
:Preferred [[grid cell size]]: 0.1m | :Preferred [[grid cell size]]: 0.1m | ||
:[[Inference mode (Inference Overlay)|Inference mode]]: [[Inference mode (Inference Overlay)|BBox Detection]] | :[[Inference mode (Inference Overlay)|Inference mode]]: [[Inference mode (Inference Overlay)|BBox Detection]] | ||
:[[Mask threshold (Inference Overlay)|Mask threshold]]: | :[[Mask threshold (Inference Overlay)|Mask threshold]]: 0.9 | ||
:[[Score threshold (Inference Overlay)|Score threshold]]: | :[[Score threshold (Inference Overlay)|Score threshold]]: 0.2 | ||
:[[Stride fraction (Inference Overlay)|Stride fraction]]: 0.50 (50%) | :[[Stride fraction (Inference Overlay)|Stride fraction]]: 0.50 (50%) | ||
Latest revision as of 07:51, 9 October 2025
This functionality is deprecated and will be removed in the future.
The Solar panels Neural Network is a Convolution Neural Network that identifies solar panels, mainly situated on roofs of buildings.
An Inference Overlay can be configured with this Neural Network. Its default settings are:
- Preferred grid cell size: 0.1m
- Inference mode: BBox Detection
- Mask threshold: 0.9
- Score threshold: 0.2
- Stride fraction: 0.50 (50%)
Identifiable features:
- Solar panel blue (oldest type)
- Solar panel gray (mid-aged type)
- Solar panel black (newest type)
-
Labeled features on 0.1m satellite image
How-to's
- How to detect solar panels using an Inference Overlay
- How to update Buildings's solar panel attribute based on an Inference Overlay
