• State Resolved
  • Locked Locked
  • Replies 1 reply
  • Subscribers 102 subscribers
  • Views 267 views
  • Users 0 members are here
Support feedback
Options
Options
Similar topics

This thread has been locked.

If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.

OMAP-L132: Embedded Vision Application - Object Tracking Robot

5258907
Prodigy 10 points
Part Number: OMAP-L132
Other Parts Discussed in Thread: OMAP-L138, AWR1642, AWR1243

Hello!

 I'm a student at the University of Florida, and I'm hoping to determine which processor family would help my team realize our senior design project. My team's goal is to design a robot that can recognize, track, and pursue objects of interest whilst avoiding obstacles. The C6000 family seems promising. We would use the OpenCV library to develop the vision capabilities, which I believe the C6000 family supports. My concern is that a single core processor may be insufficient for both image processing and control. For that reason, the C6000 with the combination of DSP and ARM processor cores seems appropriate. 


Any suggests or recommendations would be much appreciated. Also, we would need a development kit with which to prototype our project. Would the OMAP-L138 be suitable?

Thank You

  • 0
    TI__Genius 9065 points

    Hi there,

    Welcome to TI's E2E forum! I had the pleasure to work with summer interns from University of Florida and it was all very wonderful experience.

    For your question, I would recommend Sitara AM57x family (AM570x, AM571x, AM572x to AM574x) which has both DSP & ARM cores. The solution is scalable with a compatible API provided by Processor SDK. And OpenCV is supported. You can find an overview here:

    http://www.ti.com/processors/sitara-arm/overview.html

    It seems your project would also need mmWave radar sensor to detect obstacles, you can take a look at AWR1243, or AWR1642. You can find an overview here:

    http://www.ti.com/sensors/mmwave/overview.html

    We are also working on a beagleboard AI. It will be less than $100 to get the board once that becomes available in coming months. I believe the beagleboard AI would be perfect for your project. You can find more information here.

    https://beagleboard.org/ai

    best regards,

    David Zhou