1 / 14

Intelligent Ground Vehicle Competition

Intelligent Ground Vehicle Competition. Navigation Michael Lebson - mlebson@my.fit.edu James McLane - jmclane@my.fit.edu Image Processing Hamad Al Salem - halsalem@my.fit.edu Shane Brumbley - sbrumble@my.fit.edu Faculty Sponsor Dr. Eraldo Ribeiro - eribeiro@fit.edu Project Website

baina
Download Presentation

Intelligent Ground Vehicle Competition

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Intelligent Ground Vehicle Competition Navigation Michael Lebson - mlebson@my.fit.edu James McLane - jmclane@my.fit.edu Image Processing Hamad Al Salem - halsalem@my.fit.edu Shane Brumbley - sbrumble@my.fit.edu Faculty Sponsor Dr. EraldoRibeiro - eribeiro@fit.edu Project Website http://my.fit.edu/~mlebson/seniorDesign

  2. Introduction • Designing Control Software for autonomous obstacle course navigating vehicle. • Must navigate from waypoint to waypoint • Must use LIDAR, GPS, Digital Compass, and Camera to determine movement around the course • Must stay within lane lines and avoid obstacles in the completion lane

  3. Refactoring Progress • ~99% Done • Will continue as new code is written • Uses Hungarian notation • Consistent code style throughout • Reorganized as necessary

  4. Example

  5. Things to Change

  6. Current State of Navigation Roughly 30% done Vehicle has some “bugs” Grouping obstacles may be the problem Random, bad LiDAR data

  7. What’s to Come for Navigation Improve Think() Improve CostFunction() Integrate image processing Handle bad data Test

  8. Detecting Color Need to detect Yellow and White All color has Red, Green, and Blue values between 0 and 255 each. A combination of these three colors yields a shade. To detect color, you must look for a certain RGB combination.

  9. Handling White White occurs when all values of RGB are 255. In order to detect white, we set up a range, usually of 35 units. In our demo, if a pixel is determined to be white, we will change the blue value to 0(Zero)

  10. Handling Yellow Yellow occurs at red 255 and green 255, at a given range of 35 units each. Because a blue of 255 equals white, any blue value will create a lighter shade of yellow. In our demo, any yellow pixel is set to true yellow and non-yellow non-white pixels create are set to black.

  11. Line Detection • By Using Emgu CV library (Open CV for C#) and the camera attached on the laptop • We use this library for some Computer Vision functions. • Detect lines and edges in an image • Easy and fast for detecting lines and edges in a video image • Produce and update the image frame • Detect lines by Hough transform Algorithm • Available in the Emgu CV library • Required conversion from Image to Bitmap to display the image on the picture box

  12. Demo of Line Detection

  13. Milestone 4 Task Matrix

  14. Questions, Comments, or Concerns?

More Related