veyepar: Python, Robotics, OpenCV and Vision

Author(s):	Robert Seward
Location	Barbie Tootle
Date	jul Sun 29	Days Raw Files
Start	12:45	First Raw Start	12:16
Duration	0:30:0	Offset	0:28:22
End	13:15	Last Raw End	13:46
Chapters	00:00 0:01:35 0:31:34
Total cuts_time	32 min.

https://pyohio.org/2018/schedule/presentation/20/
raw-playlist raw-mp4-playlist encoded-files-playlist host archive mp4 svg png

assets release.pdf Python_Robotics_OpenCV_and_Vision.json
logs
Admin: episode episode list cut list raw files day marks day marks day image_files

State:

Locked:

clear this to unlock

Locked by:

user/process that locked.

Start:

initially scheduled time from master, adjusted to match reality

Duration:

length in hh:mm:ss

Name:

Video Title (shows in video search results)

Emails:

email(s) of the presenter(s)

Released:

has someone authorised pubication

Normalise:

Channelcopy:

m=mono, 01=copy left to right, 10=right to left, 00=ignore.

Thumbnail:

filename.png

Description:

markdown

A brief overview of using Python to power the Computer Vision function of our FIRST FRC Robotics Robot.
 
A FIRST robotics team mentor briefly talks about using Python to teach students how to integrate Computer Vision into our team's robot.

First we meet the robot. Robot baby pictures (yay!) and other fun stuff. Followed by a quick overview of what it means to be a mentor on a FIRST FRC robotics team. We end the section discussing the components of our robot and how they all fit together to integrate vision.

We explore working with the students to build GRIP pipelines. GRIP is an FRC tool to allow students to quickly build opencv feature detection routines for game elements. We discuss what opencv is and why you should care! The GRIP tool is a flexible development environment to quickly chain together opencv primitives and observe the end results. When game element features are being detected as the students need, the tool can export into our favorite language! Python!

Our team in the past has run this generated opencv GRIP Python "pipeline" on an external CPU. Due to our Team's budget constraints we use a Raspberry PI 3 with a USB web cam. (< $150) We mount and power the pi and camera on the robot. We run the "pipeline" and see things. Well almost!

In addition to the student generated pipeline, we also have a small python program that reads images from the camera as often as possible and detects features for the robot to target. This python code does some basic filtering and then sends the information to the robot control board (RoboRIO).

We end the talk with a brief description of using the vision information to control the robot.

Comment:

production notes