The Internet belongs to everyone. Let’s keep it that way.

Protect Net Neutrality
Loading presentation...

Present Remotely

Send the link below via email or IM


Present to your audience

Start remote presentation

  • Invited audience members will follow you as you navigate and present
  • People invited to a presentation do not need a Prezi account
  • This link expires 10 minutes after you close the presentation
  • A maximum of 30 users can follow your presentation
  • Learn more about this feature in our knowledge base article

Do you really want to delete this prezi?

Neither you, nor the coeditors you shared it with will be able to recover it again.



Presentation for the beagleboard AutoHUD project for ECE597

Greg Jackson

on 20 May 2010

Comments (0)

Please log in to add your comment.

Report abuse

Transcript of AutoHUD

AutoHUD Beagle Board What is it? heads-up display for cars to detect road signs runs on the Beagle Board uses OpenCV to get camera input and process it outputs to a picoprojector How does it work? using OpenCV's Haar Wavelet detection to detect stop signs in real time What we have so far stop sign detection is functioning on the Beagle Board in realtime we wrote tools for automating and streamlining training our classifier we had to change bootargs and kernel to give us more kernel memory future directions we'd like to recognize signs other than stop signs like speed limit signs better, more extensive training maybe even use OCR to read the speed limits assembling into a consolidated HUD power system refinement right now, we're pulling power from several different sources fix issues with OpenCV it's trying to use libraries that are unavailable for the Beagle overlays camera image with sign indicator (100 ms response time) demo Questions? outputs to an X window (instead of the framebuffer) output directly to the framebuffer gst-dsp, gst-omapfb, dsp-bridge uses Gentle AdaBoost classifier
Full transcript