> For the complete documentation index, see [llms.txt](https://yall.yassrobotics.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://yall.yassrobotics.com/documentation/how-to-guides/how-do-i-read-raw-fiducials-and-detections.md).

# How do I read raw fiducials and detections?

`getLatestResults()` parses a full JSON `limelight.results` payload with Jackson every call. If you only need tag/detection geometry and not the full frame, read the equivalent raw NetworkTables entries directly instead.

## Raw AprilTag detections

```java
for (RawFiducial tag : limelight.getData().getRawFiducials()) {
    // tag.id, tag.txnc, tag.tync, tag.ta
    // tag.distToCamera, tag.distToRobot (meters)
    // tag.ambiguity (0-1, lower is more trustworthy)
}
```

This is the same `RawFiducial` type populated in `PoseEstimate.rawFiducials`, since the pose estimator already uses this path internally.

## Raw neural detections

```java
for (RawDetection detection : limelight.getData().getRawDetections()) {
    // detection.classId, detection.txnc, detection.tync, detection.ta
    // detection.corner0_X .. detection.corner3_Y are the bounding-quad corners in pixels
}
```

`RawDetection` includes the four bounding-box corners, which the JSON `NeuralDetector` result does not expose.

## When to use the JSON path instead

Reach for `getLatestResults()` when you need:

* Multiple pipeline types' results at once (e.g. classifier *and* fiducial in the same frame)
* Hardware/IMU telemetry (`HardwareReport`, `IMUResults`, `RewindStats`)
* Barcode or retroreflective results, since there's no raw-NT equivalent for those

## See Also

* [Results JSON vs. Raw NetworkTables](/documentation/understanding/results-json-vs-raw-networktables.md)
* [Object Detection tutorial](/documentation/tutorials/object-detection.md)


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://yall.yassrobotics.com/documentation/how-to-guides/how-do-i-read-raw-fiducials-and-detections.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.