Skip to content
CrocoDocs
Starter GuideProgrammingEngineeringDesignPortfolio
Documentation

Introduction

IntroductionBIOBUZZ game overview

Getting started

Getting startedBlocksOnBot JavaAndroid StudioYour first OpModeJava basicsMotors and servosNonblocking codeDebugging robot code

Control systems

Control systemsJoystick mappingField-centric mecanum drivePID controlFeedforwardFlywheel velocity controlSystem identificationMotion profilingKalman filterLow-pass filter

Autonomous

AutonomousTimed and encoder movementOdometryLocalization troubleshootingMotion planningReliable autonomous sequencesPure PursuitSensor fusionAuto to TeleOp handoff

Season topics

Season topicsProjectile mathematicsTurret aimingShooting on the move

Code practices

Code practicesNaming conventionsCode organizationLoop timing and bulk readsFormattingComments and documentationTeam collaboration

Libraries

LibrariesNextFTCFTCLibSolversLibPedro PathingRoad RunnerFTC DashboardMercurial v2Mercurial v1PanelsSloth

Community software

Community softwareBlaze FTCOpenLoopHive Vision

Sensors and vision

Vision overviewVision basicsLimelight 3A
Starter Guide
Engineering
Design
Portfolio
Appearance

Vision overview

Choose and use camera-based vision tools in FTC

Computer vision

Computer vision turns camera images into information a program can use, such as a detected tag ID, a color region, or an estimated pose. Results depend on camera calibration, lighting, image quality, processing load, and how the robot uses the measurements.

FTC vision options

VisionPortal

VisionPortal is the SDK camera and processor interface. It manages camera selection, initialization, previews, and processors. Current SDK resources document AprilTag processing and the FTC color processors for color sensing and blob location. Use the SDK sample and current FTC Docs for APIs matching your installed SDK.

EasyOpenCV

EasyOpenCV is a community library built around OpenCV. It is useful when a team needs custom image processing or an existing OpenCV pipeline. It is not the same API as VisionPortal, and the two should not be mixed without following the guidance for the libraries involved.

Workflow

  1. Choose the simplest processor that answers the robot's actual question.
  2. Test camera access and image quality before writing detection logic.
  3. Validate detections under the lighting and distances the robot will encounter.
  4. Check confidence, visibility, calibration, and stale results before acting on a measurement.
  5. Test processor load and control-loop timing on the .

AprilTag IDs, cluster layouts, and scoring elements can be -specific. Do not hardcode an old season's IDs or colors into a current robot without checking the current Competition Manual and FTC SDK tag library.

Next steps

  • VisionPortal
  • AprilTag detection
  • EasyOpenCV basics
  • EOCV-Sim
  • Hive Vision — the BIOBUZZ neural model and a stationary detection preview for Limelight 3A.
  • Limelight 3A — pipeline setup, fresh results, target aiming, and field-pose integration.

Sources

  • FTC color processing
  • FTC VisionPortal overview
  • FTC programming resources

Hive Vision

Load the BIOBUZZ model onto a Limelight 3A and inspect detections before driving from them

Vision basics

Learn what a camera pipeline measures before writing robot decisions

On this page

Computer visionFTC vision optionsVisionPortalEasyOpenCVWorkflowNext stepsSources