# Merging, cropping, and filtering datasets

This guide explains how to merge multiple datasets and their internal tiles, crop a region for analysis, and apply classification-based filters before exporting to a file.

{% embed url="<https://youtu.be/-6sTF-DnY3M>" %}

### **Merging**

Point cloud datasets often consist of multiple tiles. Traditionally, these tiles must be merged manually in separate software. In LumiDB, dataset and tile boundaries are abstracted, allowing you to view them as a unified dataset directly in the browser.

Merging happens automatically. All datasets selected from the Datasets menu are combined for visualization, including their internal tiles.

### Cropping

1. Navigate to the area of interest on the map.
2. Use the Crop tool to draw a polygon around the area.
3. Adjust the polygon by dragging its corners.
4. The cropped area is previewed immediately in the visualization view.

<figure><img src="/files/6Q7oA1bzy3Dtrb7aVjBa" alt=""><figcaption></figcaption></figure>

### Remove cropping

1. Click any corner of the cropped area to open the Area crop panel.
2. Click Clear to remove the crop.

### **Filtering**

1. Open the *Filters* menu. The colors update to reflect classification data.
2. Use classification filters to refine the visible data, for example, to hide water or unclassified points.

<figure><img src="/files/PYpHHOU3z196FtoNrkKZ" alt=""><figcaption></figcaption></figure>

### **Export to file**

Once cropping and filtering are complete:

1. Open the Export menu from the *Area crop* panel.
2. Export the cropped and filtered dataset in standard formats such as LAZ or E57, or download the original tile files separately.
3. You can also share the dataset as a link with colleagues or as 3D Tiles for use in supported applications.


---

# Agent Instructions: 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:

```
GET https://docs.lumidb.com/user-guides/merging-cropping-and-filtering-datasets.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.
