# Classifications

<figure><img src="/files/OVqxfnxNQYl6iujpehrb" alt=""><figcaption></figcaption></figure>

Each frame or sequence (aka task) can have properties called classifications that provide additional information about the overall frame or sequence, rather than individual objects. Classifications help capture specific characteristics, conditions, or states that apply broadly to the scene.

#### What Are Frame/Task Classifications?

Unlike object attributes (which describe individual annotations like cars or pedestrians), frame and sequence classifications describe:

* Frame-level: Properties of a single frame/timestamp
* Task-level: Properties of the entire sequence/batch

**Frame Classifications:**

* Weather conditions (sunny, rainy, foggy, snowy)
* Lighting conditions (day, night, dawn, dusk)
* Traffic density (light, moderate, heavy)
* Road surface (dry, wet, icy)
* Image quality (clear, blurry, overexposed)

**Sequence Classifications:**

* Location type (urban, suburban, highway, rural)
* Scenario type (normal driving, construction zone, parking lot)
* Recording conditions (stationary, moving vehicle)

Frame and task classifications use the same attribute types as object attributes:

* [Boolean](/3d-multi-sensor-fusion/labeling/category-schema/pct-class-level.md#boolean): Yes/no properties (e.g., "Is raining")
* [Single Select](/3d-multi-sensor-fusion/labeling/category-schema/pct-class-level.md#single-select-dropdown): One option from a list (e.g., Weather: Sunny/Cloudy/Rainy)
* [Multi-Select:](/3d-multi-sensor-fusion/labeling/category-schema/pct-class-level.md#multi-select-dropdown) Multiple options (e.g., Road features: Speed bumps, Potholes, Crosswalks)
* [Text:](/3d-multi-sensor-fusion/labeling/category-schema/pct-class-level.md#text) Free-form input (e.g., Session notes)


---

# 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.imerit.net/3d-multi-sensor-fusion/labeling/category-schema/classifications.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.