Robot Tracking

Using OpenCV2 and Numpy to track a Scribbler 2 robot. A raspberry pi with a camera is used to locate and track the robot. The ultimate objective of this script is to be able to click somewhere within a window and have the robot move to that location based on alternate color space tracking.

Table of Contents

• Getting Started
• Prerequisites
• Raspberry Pi Setup
• Changing Camera Properties
• Usage
• Result
• Support

Getting Started

Clone Repo (No official release built yet)

Prerequisites

• Raspberry Pi and Camera
• Python 3.6+
• OpenCV
• Numpy
• PySerial
• Myro v3.0.0+ Install Instructions

Raspberry Pi Setup

• Ensure that the Raspberry Pi is completely up to date with: sudo apt-get update sudo apt-get upgrade

• Run sudo raspi-config and enable the camera

• Python3 should be preinstalled with Raspbian, otherwise install it:

  sudo apt install python3
  

• Install the rest of the dependencies

  pip3 install picamera socketserver http
  

• This script must be running on the raspberry pi at all times to connect to the camera.

Changing Camera Properties

TODO (This still needs to be implemented in the livecam level.)

Usage

TODO (Include more information about multithreading implementation, and calibration/orientation keybinds.)

Result

Robot Picked

Front Picked

Centroids

Support

Reach out to me at one of the following places!

• Email (Best) at joshua.gf.arul@gmail.com
• Twitter at @jarulsamy_

---