Page:
Using Computer Vision in FTC
Pages
1. Updating the DS App
2. Updating the RC App
3. Updating Hub Firmware
4. Updating the Control Hub OS
5. Updating the Driver Hub OS
6. Updating FTC Software Tools
Advanced Topics
Android Studio Tutorial
AprilTags for FTC Blocks
Automatically Loading a Driver Controlled Op Mode
Blocks Reference Material
Blocks Sample Op Mode for TensorFlow Object Detection
Blocks Sample OpMode for TFOD
Blocks Sample TensorFlow Object Detection Op Mode
Blocks Tutorial
Changing PID Coefficients
Changing PIDF Coefficients
Choosing a Programming Tool
Computer Vision Overview
Configuring Your Android Devices
Configuring Your Hardware
Connecting Devices to a Control or Expansion Hub
Connecting a Laptop to the Program & Manage Network
Controlling a Servo (Android Studio)
Controlling a Servo (Blocks)
Controlling a Servo (OnBot Java)
Creating and Running an Op Mode (Android Studio)
Creating and Running an Op Mode (OnBot Java)
Custom FTC Blocks (myBlocks)
Custom TFOD Model with Blocks
DS app on Control Hub
Datalogging Part 2, Custom Data
Datalogging Part 3, RC File Transfer
Datalogging Part 4, Java Learning Exercise
Datalogging
Disabling Android Studio Instant Run
Downloading the Android Studio Project Folder
Driver Station Speech Telemetry
Enabling Developer Options
External Libraries in OnBot Java and Blocks
FTC Phone Pairing
FTC Self Inspect
FTC Single Hub
FTC Webcam Controls
Home
Identifying Vuforia VuMarks
Installing Android Studio
Installing a Javascript Enabled Browser
Java Sample Op Mode for TensorFlow Object Detection
Java Sample OpMode for TFOD
Java Sample TensorFlow Object Detection Op Mode
Managing Electrostatic Discharge Effects
Managing Your Control System
Managing a Control Hub
Managing a Smartphone Driver Station
Managing a Smartphone Robot Controller
OnBot Java Reference Info
OnBot Java Tutorial
Playing Audio Files
Required Materials
Running Your Op Mode
TFOD Sample OpMode with Java Builder
TensorFlow for Blocks
The FTC Control System
Timers in FTC Blocks
Troubleshooting
Universal IMU Interface
Updating FTC Software
Using Computer Vision in FTC
Using Sensors (Android Studio)
Using Sensors (Blocks)
Using Sensors (OnBot Java)
Using TensorFlow Lite for the Ultimate Goal Challenge
Using TensorFlow in Freight Frenzy
Using Two Expansion Hubs
Using Your Android Device
Using a Custom TensorFlow Model with Blocks
Using a Custom TensorFlow Model with Java
Using a TensorFlow Pretrained Model to Detect Everyday Objects
Using an External UVC Camera and a Powered USB Hub
Using an External Webcam with Control Hub
Using the utomatic TeleOp
Vuforia for Blocks
Webcams for FTC VisionPortal
Writing an I2C Driver
Writing an Op Mode with FTC Blocks
Clone
3
Using Computer Vision in FTC
FTC Engineering edited this page 2019-11-14 13:30:32 -05:00
Teams who compete in the FIRST Tech Challenge (FTC) can use computer vision (CV) to help their robots navigate autonomously during a match. The FTC software can "grab" images from a camera and use these images to look for and track objects on the field.
This tutorial provides information about how you can use the computer vision libraries that are included with the FTC control system software:
- Computer Vision Overview - This section provides a basic overview of the CV technologies that are included with the FTC software. It also compares the strengths and weaknesses of the respective technologies.
- Vuforia for Blocks - This section demonstrates how you can use Vuforia and Blocks to detect and track image targets in the FIRST Tech Challenge.
- TensorFlow for Blocks - This section demonstrates how you can use TensorFlow and Blocks to detect and track game elements in the FIRST Tech Challenge.