08 / OpenCV and AprilTags

AprilTags and Field Pose

Use AprilTag detections, metadata, and estimated pose to align and localize.

80 minVisionOpenCV and AprilTags

You will

01Read AprilTag id, metadata, range, bearing, and pose data.
02Use known field tags for alignment decisions.
03Understand the difference between detection and localization.

Why AprilTags and Field Pose matters

This lesson is about turning camera images into trustworthy robot decisions. The goal is not to make vision seem magical; it is to show how camera setup, processor output, telemetry, and fallbacks make an autonomous decision safe enough to use.

Starting point

AprilTags are known field landmarks

FIRST field tags have known positions. A detection gives the robot information about a visible landmark, which can support alignment, scoring, or pose correction when used carefully.

Metadata matters

A tag id is useful only when the program knows what that id represents. Metadata connects detections to the field layout and prevents code from treating every tag the same.

Build path

Start with a visible stream and raw telemetry before making decisions. Then add regions, detections, metadata, or pose estimates. Autonomous should receive a simple result and confidence, not a pile of image-processing details.

For this specific lesson, students should first restate the goal in robot terms, then identify the value or behavior they expect to observe, then run the smallest test that proves the idea. The lesson should feel like a guided lab: predict, run, observe, explain, and only then extend.

AprilTagTelemetry.java · Java

for (AprilTagDetection detection : aprilTags.getDetections()) {
    if (detection.metadata == null) continue;

    telemetry.addData("Tag", detection.id);
    telemetry.addData("Name", detection.metadata.name);
    telemetry.addData("Range", detection.ftcPose.range);
    telemetry.addData("Bearing", detection.ftcPose.bearing);
    telemetry.addData("Yaw", detection.ftcPose.yaw);
}

Debugging and failure modes

Vision fails through lighting, camera placement, exposure, cable issues, wrong tag assumptions, and thresholds that only worked in the shop. The debugging habit is to show the image, print raw scores or detections, and define a safe fallback when the robot is not confident.

Checks

Unknown tags are handled safely.
Telemetry uses meaningful labels.
Alignment logic uses tag id or metadata intentionally.

Check your understanding

Module check

Why check AprilTag metadata before using a detection?

0 of 1 answered

References

FTC VisionPortal DocsOfficial VisionPortal overview and examples.FIRST FTC DocsOfficial FTC SDK and robot programming documentation.Game Manual 0Community FTC programming, control, and robot design reference.