> For the complete documentation index, see [llms.txt](https://docs-7.phoenixlidar.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs-7.phoenixlidar.com/lidarmill-desktop/workflow-kk/classification.md).

# Filter/Classification

## Summary

Once a pointcloud has been created and calibrated, the CLOUD file is ready to be filtered, or classified.

SpatialExplorer enables the user to classify a pointcloud using the following filters:

1. [Find Ground](https://docs.phoenixlidar.com/lidarmill-desktop/post-processing/workflow-kk/classification/find-ground)
2. [Find Ground (PTD)](https://docs.phoenixlidar.com/lidarmill-desktop/post-processing/workflow-kk/classification/find-ground-ptd)
3. [Statistical Outlier Removal](https://docs.phoenixlidar.com/lidarmill-desktop/post-processing/workflow-kk/classification/statistical-outlier-removal)
4. [Find Noise](https://docs.phoenixlidar.com/lidarmill-desktop/post-processing/workflow-kk/classification/find-noise)
5. [Assign Class](https://docs.phoenixlidar.com/lidarmill-desktop/post-processing/workflow-kk/classification/assign-class)

## Details

### Common Workflow:

* All points begin in class "Created, never classified"

### 1. Find Noise/Statistical Outlier Removal

* Used to classify points that are "noisy", or "Statistical outliers"
* Routine useful for finding isolated points up in the air or below the ground
* Input class = "Created, never classified", Output Class = "Low point (Noise)"

### 2. Find Ground/Find Ground (PTD)

* Required to generate Digital Terrain Model representing the bare ground surface
* Used to generate ground classified points ("[Find Ground (PTD)](https://docs.phoenixlidar.com/lidarmill-desktop/post-processing/workflow-kk/classification/find-ground-ptd)" filter recommended)
* The routine is best suited for classifying ground where there is natural terrain. 
* Input class = "Created, never classified", Output Class = "Ground"
* The routine is sensitive to low error points in the pointcloud, so it is recommended to run a "Find Noise" filter prior to using one of these ground routines. 

### 3. Assign Class

* Used to change one or multiple class(es) to another class
* Assigns the output class to all points that match any of the selected input classes
* Input class = "Created, never classified", Output Class = "Unclassified"

## Video Walkthrough

In this video, we cover the classification modules in SpatialExplorer 6 and walk through how to extract features of interest from your point cloud.

{% embed url="<https://www.youtube.com/watch?v=85n7bk_ehno>" %}