> For the complete documentation index, see [llms.txt](https://docs.aeroai.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.aeroai.io/siega-web-features/analysis/point-cloud-classification.md).
# Point Cloud Classification
LiDAR point clouds usually come with a classification value baked into every point that tells you what the point
represents, like ground, vegetation, or a building. SiEGA Web reads that classification straight from the tileset and
lets you decide how each class is colored, which classes are visible in the scene, and how large the points draw on
screen. This is what makes it possible to look at a raw scan and quickly isolate just the surfaces you care about.
This page covers the classification side of the panel. Encroachment styling lives in the same panel and is covered on
its own page.
### Features
* Switch between coloring points by their native scan colors and coloring them by class.
* Auto detect the per point property that holds the class value, with a manual override for non standard files.
* See which class IDs are actually present in your point cloud at a glance.
* Edit a full table of classification entries, each with an ID, name, color, and visibility toggle.
* Add or remove class rows so the table matches the classes actually used in your point cloud.
* Resize every point on screen with a single Point Size input.
### Opening the classification panel
The classification controls live inside the Scene Layers panel and only appear for assets that the viewer has detected
as a point cloud, so make sure the point cloud you want to style has already been loaded from the Asset Sidebar.
1. Click "Layers" in the top toolbar to open the Scene Layers panel on the right side of the screen
2. Expand the category that contains your point cloud, such as Tileset, to reveal the assets inside it.
3. Click the chevron to the left of the asset name to open its inline details, where the Point Cloud Classification section will appear below Transform.
4. Click Point Cloud Classification to expand the subsection and reveal the styling controls.
### Switching Between RGB and Classes Modes
The top of the subsection has two buttons that decide how the point cloud is colored. Click "RGB" on the left to color
each point using its original color from the scan, which is the default when the file already carries real color
values. Click "Classes" on the right to color and filter points by their classification ID instead, which reveals the
Property field, the class table, and the Detected classes readout below the toggle.
### Editing the Class Table
The class table is where you decide how each classification is styled. The viewer ships with the standard ASPRS LAS
class list already filled in, with rows for ground, low, medium, and high vegetation, buildings, water, road surface, transmission towers, and the other common classes, so you can start tweaking right away.
#### Applying your changes
Edits in the panel do not show up in the scene until you push them out.
1. When the panel looks the way you want, click "Apply Changes" at the bottom.
2. Image: Apply Changes button at the bottom of the panel.
3. The point cloud in the scene updates with the new colors, sizes, and visibility.
4. Image: styled point cloud in the viewer.
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:
```
GET https://docs.aeroai.io/siega-web-features/analysis/point-cloud-classification.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.