Computer Vision Lab 4 Overview & Tips
"Learn about the goals and architecture of Computer Vision Lab 4, including tips for success like starting early, modularizing tasks, and utilizing helpful modules for testing and debugging."
Download Presentation
Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
You are allowed to download the files provided on this website for personal or commercial use, subject to the condition that they are used lawfully. All files are the property of their respective owners.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.
E N D
Presentation Transcript
Lab 4 overview + tips -Aalhad Patankar, Bryan Li, David Watkins
Lab overview Goals: Follow a yellow line using computer vision Correct yourself when veering off course U-turn when orange stop line is encountered (at a certain distance) Extra credit: Achieve a turn
One possible architecture Find position Stop sign Detect Stop Sign Capture Image Apply Controller Homography Determine angle/distance Move robot to center line Filter colors Move forward Find hough lines U-turn
Additional helpful modules GPG2 control module wrapper to easily move and turn robot Camera module to control camera settings/config Homography module or script to obtain the correct transform and session parameters you will need Testing module to automatically iterate through testbed Try not to write it all in one long script --think about good coding practices
Tips and hints Start early!!! Purchase tape that we linked to in lab spec to be able to test anywhere on the go Or use the image set we gave you to do the same Separate assignment into logical modules, and work in parallel to build + test modules. Mock up where appropriate E.g. To test position + pose estimation code, mock up valid hough line + robot position Assign team roles. There are several components to this lab The core algorithms, software design + testing, integration, testing, etc.
Tips and hints Develop good debugging tools early, will help you in the long run Save good images so you can use them as mock data for modules raspistill command Be careful when working in homography transformed space to make sure all the data points you're working with have also been transformed (if doing pose or position estimation) Post on Piazza and help out teammates This will be updated as new hints come up
